diff --git a/images/news/2405Bushuk.png b/images/news/2405Bushuk.png
new file mode 100644
index 000000000..b6724d54d
Binary files /dev/null and b/images/news/2405Bushuk.png differ
diff --git a/images/news/2405Chapman.png b/images/news/2405Chapman.png
new file mode 100644
index 000000000..2b34ff28e
Binary files /dev/null and b/images/news/2405Chapman.png differ
diff --git a/index.xml b/index.xml
index 1c3c9715d..604e03760 100644
--- a/index.xml
+++ b/index.xml
@@ -5,7 +5,7 @@ Those ML models will be used to deepen our understanding of subgrid processes, a
 Atmospheric convection and clouds (O&amp;rsquo;Gorman, Yuval) Atmospheric boundary layer processes at the ocean and sea-ice interface (Gentine, Connolly) Ocean mesoscale buoyancy fluxes (Abernathey, Balwada) Ocean submesoscale processes (Le Sommer, Gorbunova) Ocean mesoscale momentum, energy and air-sea interactions (Zanna, Perezhogin) Vertical mixing (Adcroft, Reichl, Sane) Sea-ice heterogeneity and its influence on air-sea-ice interactions (Holland, Zampieri)</description></item><item><title>Ziwei Li</title><link>https://m2lines.github.io/team/former/ziweili/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/ziweili/</guid><description>NYU, Courant Institute</description></item><item><title>Alistair Adcroft</title><link>https://m2lines.github.io/team/alistairadcroft/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/alistairadcroft/</guid><description>Princeton University, Affiliate NOAA-GFDL in Ocean division</description></item><item><title>Improving coupled climate models</title><link>https://m2lines.github.io/research/research3/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/research/research3/</guid><description>Predicting future climate conditions on earth, and in particular, the impacts of climate change, would not be possible without climate models. Climate models are complex mathematical representations of the physical processes happening in each of the climate system components: ocean, atmosphere, sea-ice and land surface, as well as their interactions with each other.
 Climate models divide the globe into three dimensional grid cells representing a specific location and elevation. The resolution of the models, their “level of detail”, is dependent on the size chosen for the grid cells: the smaller the grid size the higher the resolution.</description></item><item><title>Carlos Fernandez-Granda</title><link>https://m2lines.github.io/team/carlosferndandezgranda/</link><pubDate>Mon, 19 Nov 2018 10:47:58 +1000</pubDate><guid>https://m2lines.github.io/team/carlosferndandezgranda/</guid><description>NYU, Courant Institute + Center for Data Science</description></item><item><title>Joan Bruna</title><link>https://m2lines.github.io/team/joan-bruna/</link><pubDate>Mon, 19 Nov 2018 10:47:58 +1000</pubDate><guid>https://m2lines.github.io/team/joan-bruna/</guid><description>NYU, Courant Institute + Computer Science + Center for Data Science</description></item><item><title>Ryan Abernathey</title><link>https://m2lines.github.io/team/ryanabernathy/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/ryanabernathy/</guid><description>Lamont/Columbia University</description></item><item><title>Brandon Reichl</title><link>https://m2lines.github.io/team/brandonreichl/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/brandonreichl/</guid><description>NOAA-GFDL in Ocean division</description></item><item><title>Feiyu Lu</title><link>https://m2lines.github.io/team/feiyulu/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/feiyulu/</guid><description>Princeton University, Affiliate NOAA-GFDL in Seasonal-decadal division</description></item><item><title>Judith Berner</title><link>https://m2lines.github.io/team/judithberner/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/judithberner/</guid><description>National Center for Atmospheric Research</description></item><item><title>Marika Holland</title><link>https://m2lines.github.io/team/marikaholland/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/marikaholland/</guid><description>National Center for Atmospheric Research</description></item><item><title>Mitch Bushuk</title><link>https://m2lines.github.io/team/mitchbushuk/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/mitchbushuk/</guid><description>UCAR, Affiliate NOAA-GFDL in Ocean division</description></item><item><title>Pierre Gentine</title><link>https://m2lines.github.io/team/pierregentine/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/pierregentine/</guid><description>Columbia University</description></item><item><title>Paul O'Gorman</title><link>https://m2lines.github.io/team/paulogorman/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/paulogorman/</guid><description>MIT</description></item><item><title>Julie Deshayes</title><link>https://m2lines.github.io/team/juliedeshayes/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/juliedeshayes/</guid><description>CNRS-IPSL</description></item><item><title>Julien Le Sommer</title><link>https://m2lines.github.io/team/julienlesommer/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/julienlesommer/</guid><description>L&amp;rsquo;Institut des Géosciences de l&amp;rsquo;Environnement (IGE)</description></item><item><title>Arthur Guillaumin</title><link>https://m2lines.github.io/team/arthurguillaumin/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/arthurguillaumin/</guid><description>Queen Mary University of London</description></item><item><title>Janni Yuval</title><link>https://m2lines.github.io/team/janniyuval/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/janniyuval/</guid><description>Google Research</description></item><item><title>Alex Connolly</title><link>https://m2lines.github.io/team/alexconnolly/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/alexconnolly/</guid><description>Columbia University</description></item><item><title>Julius Busecke</title><link>https://m2lines.github.io/team/juliusbusecke/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/juliusbusecke/</guid><description>Columbia University</description></item><item><title>Aakash Sane</title><link>https://m2lines.github.io/team/aakashsane/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/aakashsane/</guid><description>Princeton University, Affiliate NOAA-GFDL in Ocean Division</description></item><item><title>Andrew Ross</title><link>https://m2lines.github.io/team/former/andrewross/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/andrewross/</guid><description>NYU, Courant Institute</description></item><item><title>Lorenzo Zampieri</title><link>https://m2lines.github.io/team/lorenzozampieri/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/lorenzozampieri/</guid><description>National Center for Atmospheric Research</description></item><item><title>Cem Gultekin</title><link>https://m2lines.github.io/team/cemgultekin/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/cemgultekin/</guid><description>NYU, Courant Institute</description></item><item><title>Tarun Verma</title><link>https://m2lines.github.io/team/tarunverma/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/tarunverma/</guid><description>Princeton University</description></item><item><title>Dhruv Balwada</title><link>https://m2lines.github.io/team/dhruvbalwada/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/dhruvbalwada/</guid><description>Lamont/Columbia University</description></item><item><title>Cheng Zhang</title><link>https://m2lines.github.io/team/chengzhang/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/chengzhang/</guid><description>Princeton University</description></item><item><title>Anastasiia Gorbunova</title><link>https://m2lines.github.io/team/former/anastasiiagorbunova/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/anastasiiagorbunova/</guid><description>L&amp;rsquo;Institut des Géosciences de l&amp;rsquo;Environnement (IGE)</description></item><item><title>Pavel Perezhogin</title><link>https://m2lines.github.io/team/pavelperezhogin/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/pavelperezhogin/</guid><description>NYU, Courant Institute</description></item><item><title>Will Chapman</title><link>https://m2lines.github.io/team/willchapman/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/willchapman/</guid><description>National Center for Atmospheric Research</description></item><item><title>Will Gregory</title><link>https://m2lines.github.io/team/willgregory/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/willgregory/</guid><description>Princeton University, Affiliate NOAA-GFDL</description></item><item><title>Abigail Bodner</title><link>https://m2lines.github.io/team/abigailbodner/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/abigailbodner/</guid><description>NYU, Courant Institute</description></item><item><title>Andrew Brettin</title><link>https://m2lines.github.io/team/andrewbrettin/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/andrewbrettin/</guid><description>NYU, Courant Institute</description></item><item><title>Mario Herrero-Gonzalez</title><link>https://m2lines.github.io/team/former/marioherrerogonzalez/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/marioherrerogonzalez/</guid><description>Columbia University</description></item><item><title>Karl Otness</title><link>https://m2lines.github.io/team/karlotness/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/karlotness/</guid><description>NYU, Courant Institute</description></item><item><title>Mohamed Aziz Bhouri</title><link>https://m2lines.github.io/team/azizbhouri/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/azizbhouri/</guid><description>Columbia University</description></item><item><title>Hugo Frezat</title><link>https://m2lines.github.io/team/former/hugofrezat/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/hugofrezat/</guid><description>L’Institut des Géosciences de l’Environnement (IGE)</description></item><item><title>Adrien Burq</title><link>https://m2lines.github.io/team/former/adrienburq/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/adrienburq/</guid><description>Columbia University</description></item><item><title>Fabrizio Falasca</title><link>https://m2lines.github.io/team/fabriziofalasca/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/fabriziofalasca/</guid><description>NYU, Courant Institute</description></item><item><title>Adam Subel</title><link>https://m2lines.github.io/team/adamsubel/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/adamsubel/</guid><description>NYU, Courant Institute</description></item><item><title>Alexis Barge</title><link>https://m2lines.github.io/team/alexisbarge/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/alexisbarge/</guid><description>CNRS-IGE</description></item><item><title>Maud Tissot</title><link>https://m2lines.github.io/team/maudtissot/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/maudtissot/</guid><description>CNRS-IPSL</description></item><item><title>Elizabeth Yankovsky</title><link>https://m2lines.github.io/team/former/elizabethyankovsky/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/elizabethyankovsky/</guid><description>NYU, Courant Institute</description></item><item><title>Sara Shamekh</title><link>https://m2lines.github.io/team/sarashamekh/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/sarashamekh/</guid><description>Columbia University</description></item><item><title>Chris Dupuis</title><link>https://m2lines.github.io/team/former/chrisdupuis/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/chrisdupuis/</guid><description>Lamont/Columbia University</description></item><item><title>J Emmanuel Johnson</title><link>https://m2lines.github.io/team/former/jemanjohnson/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/jemanjohnson/</guid><description>L’Institut des Géosciences de l’Environnement (IGE)</description></item><item><title>Chris Pedersen</title><link>https://m2lines.github.io/team/chrispedersen/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/chrispedersen/</guid><description>NYU, Courant Institute</description></item><item><title>Emily Newsom</title><link>https://m2lines.github.io/team/emilynewsom/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/emilynewsom/</guid><description>NYU, Courant Institute</description></item><item><title>Etienne Meunier</title><link>https://m2lines.github.io/team/etiennemeunier/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/etiennemeunier/</guid><description>CNRS-IPSL</description></item><item><title>Maria Prat Colomer</title><link>https://m2lines.github.io/team/former/mariapratcolomer/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/mariapratcolomer/</guid><description>NYU, Courant Institute</description></item><item><title>Nora Loose</title><link>https://m2lines.github.io/team/noraloose/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/noraloose/</guid><description>Princeton University</description></item><item><title>David Kamm</title><link>https://m2lines.github.io/team/davidkamm/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/davidkamm/</guid><description>CNRS-IPSL</description></item><item><title>Patricia Luc</title><link>https://m2lines.github.io/team/patricialuc/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/patricialuc/</guid><description>Columbia University</description></item><item><title>Kelsey Everard</title><link>https://m2lines.github.io/team/kelseyeverard/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/kelseyeverard/</guid><description>NYU, Courant Institute</description></item><item><title>Matias Ortiz</title><link>https://m2lines.github.io/team/former/matiasortiz/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/matiasortiz/</guid><description>NYU, Courant Institute</description></item><item><title>Shubham Gupta</title><link>https://m2lines.github.io/team/shubham/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/shubham/</guid><description>NYU, Tandon School of Engineering</description></item><item><title>Surya Dheeshjith</title><link>https://m2lines.github.io/team/suryadheeshjith/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/suryadheeshjith/</guid><description>NYU, Courant Institute</description></item><item><title>Leo Liu</title><link>https://m2lines.github.io/team/former/leoliu/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/leoliu/</guid><description>NYU, Courant Institute</description></item><item><title>Shantanu Acharya</title><link>https://m2lines.github.io/team/former/shantanu/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/shantanu/</guid><description>NYU, Courant Institute</description></item><item><title>Griffin Mooers</title><link>https://m2lines.github.io/team/griffinmooers/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/griffinmooers/</guid><description>MIT</description></item><item><title>Friedrich Ginnold</title><link>https://m2lines.github.io/team/former/friedrichginnold/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/former/friedrichginnold/</guid><description>ETH Zürich</description></item><item><title>Prani Nalluri</title><link>https://m2lines.github.io/team/praninalluri/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/praninalluri/</guid><description>Columbia University</description></item><item><title>Renaud Falga</title><link>https://m2lines.github.io/team/renaudfalga/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/renaudfalga/</guid><description>NYU, Courant Institute</description></item><item><title>Jisu Han</title><link>https://m2lines.github.io/team/jisuhan/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/jisuhan/</guid><description>Columbia University</description></item><item><title>Julia Simpson</title><link>https://m2lines.github.io/team/juliasimpson/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/juliasimpson/</guid><description>Columbia University</description></item><item><title>Jiarong Wu</title><link>https://m2lines.github.io/team/jiarongwu/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/jiarongwu/</guid><description>NYU
 Ocean, Coupled Physics, Ocean Surface Waves</description></item><item><title>Yongquan Qu</title><link>https://m2lines.github.io/team/yongquanqu-/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/team/yongquanqu-/</guid><description>Columbia University
-Atmosphere, Machine Learning, Data Assimilation</description></item><item><title>Advances in Machine Learning Techniques for Sea Ice Applications</title><link>https://m2lines.github.io/news/2404zampieri/</link><pubDate>Wed, 03 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404zampieri/</guid><description>Forty-two international researchers, including Lorenzo Zampieri, were invited to Gwangmyeong (South Korea) to discuss recent advances in sea ice modelling to help guide the development of a state-of-the-art Korean sea ice modelling program under the leadership of the Korean Polar Research Institute (KOPRI). The workshop produced a report , which highlights 1) the opportunity to use AI techniques in support of various sea ice modelling tasks both for short-term and climate predictions and 2) the need for strengthened collaborations among international groups to connect existing “research bubbles” and facilitate the dissemination of ideas.</description></item><item><title>Joint Parameter and Parameterization Inference by Yongquan</title><link>https://m2lines.github.io/news/2404qu/</link><pubDate>Tue, 02 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404qu/</guid><description>In this article , Yongquan Qu, Mohamed Aziz Bhouri, and Pierre Gentine, tackle the joint inference and uncertainty quantification of poorly known physical parameters and machine learning parametrizations, for sub-grid scale dynamics. Achieved through a Bayesian framework enabled by differentiable programming, this method not only offers accurate parameter estimates, but also enables skillful forecasting, each accompanied by quantified uncertainty. This work is accepted at the ICLR 2024 Workshop on AI4Differential Equations In Science.</description></item><item><title>Building Ocean Climate Emulators by Adam</title><link>https://m2lines.github.io/news/2404adam/</link><pubDate>Mon, 01 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404adam/</guid><description>AI can accelerate climate modeling by generating computationally cheap emulators of existing simulations. The design of climate emulators is an exciting and open challenge in AI+Climate. In this work , PhD student Adam Subel and Laure Zanna focus on two fundamental questions to facilitate the creation of ocean emulators: 1) the role of the atmosphere in improving the decadal skill of the emulator and 2) the representation of variables with distinct timescales (e.</description></item><item><title>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</title><link>https://m2lines.github.io/news/2402bhouri/</link><pubDate>Sat, 03 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402bhouri/</guid><description>Machine Learning (ML)-based parameterizations of atmospheric convection have long been hailed as a promising alternative, with the potential to yield higher accuracy at a fraction of the cost of more explicit simulations. This work , co-authored by Mohamed Aziz Bhouri, investigates the coupled out-of-distribution extrapolation capabilities in &amp;ldquo;online&amp;rdquo; testing of different ML-based parameterization designs of atmospheric convection. Their results show that these design decisions are not enough to obtain satisfactory generalization benefits.</description></item><item><title>Stochastic Optimal Control Matching by Joan</title><link>https://m2lines.github.io/news/2402joan/</link><pubDate>Fri, 02 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402joan/</guid><description>Joan Bruna is a co-author in this preprint , introducing Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control. Stochastic optimal control’s goal is to drive the behavior of noisy systems. In this work, the control is learned via a least squares problem by trying to fit a matching vector field. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that is of independent interest, e.</description></item><item><title>Restratification Effect of Mesoscale Eddies by Noora</title><link>https://m2lines.github.io/news/2402noora/</link><pubDate>Thu, 01 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402noora/</guid><description>Nora Loose is lead author of this new paper - part of the Climate Process Team funded by NSF and NOAA - which compares two parameterizations (“GM90” and “GL90”) for the restratification effect of mesoscale eddies. The authors conclude that the less commonly used GL90 parameterization is a promising alternative to the popular GM90 scheme for isopycnal coordinate models, where it is more consistent with theory, computationally more efficient, easier to implement, and numerically more stable.</description></item><item><title>Data-driven equation discovery ocean model by Pavel</title><link>https://m2lines.github.io/news/2401pavel/</link><pubDate>Tue, 02 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401pavel/</guid><description>Pavel Perezhogin is lead author of this new M²LInES preprint , describing the implementation, in the GFDL MOM6 ocean model, of a data-driven equation-discovery parameterization of mesoscale eddies. This scale-aware parametrization improved biases in the mean flow and energetics for a range of resolutions and in different ocean configurations. The work was done in collaboration with Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda and Laure Zanna.</description></item><item><title>Learning Machine Learning with Lorenz-96</title><link>https://m2lines.github.io/news/2401l96/</link><pubDate>Mon, 01 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401l96/</guid><description>The M²LInES team is proud to share our Jupyter Book on Learning Machine Learning with Lorenz-96 . This educational tool provides a computationally accessible framework to understand how machine learning techniques can tackle climate science problems, including emulators, parameterizations, data assimilation, and uncertainty quantification. It is for all climate scientists wanting to learn or test machine learning algorithms or for machine learning experts to learn about climate modeling or develop new algorithms.</description></item><item><title>ClimSim awarded Best Paper Award at NeurIPS</title><link>https://m2lines.github.io/news/2312climsim/</link><pubDate>Tue, 12 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312climsim/</guid><description>ClimSim has been awarded Best Paper Award at NeurIPS ! The open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators, emerged out of the Science and Technology Center LEAP, received contributions from numerous M²LInES members. Congratulations to all authors!</description></item><item><title>Will Gregory's latest article featured in Advance Science News</title><link>https://m2lines.github.io/news/2312willgfeature/</link><pubDate>Fri, 01 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312willgfeature/</guid><description>The latest M²LInES article, led by Will Gregory (Princeton) is being featured in Advance Science News. The article details how Will and other colleagues, including M²LInES members Mitch Bushuk, Alistair Adcroft, and Laure Zanna, are using Machine Learning to enhance predictions of Arctic sea ice loss. Read the article by Giorgio Graffino here</description></item><item><title>OceanBench by J. Emmanuel Johnson</title><link>https://m2lines.github.io/news/2311johnson/</link><pubDate>Wed, 01 Nov 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2311johnson/</guid><description>OceanBench is a suite of tools for designing experiments relevant to the oceanography community like interpolation, forecasting and estimation. Lead author J. Emmanuel Johnson and co-authors, including Anastasiia Gorbunova and Julien Le Sommer, demonstrate its use within a benchmark setting for sea surface height interpolation, using general circulation model simulations and real satellite observations.</description></item><item><title>UNetKF by Feiyu Lu</title><link>https://m2lines.github.io/news/2310lu/</link><pubDate>Tue, 03 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310lu/</guid><description>This study by Feiyu Lu incorporates deep learning methods to compliment and improve the ensemble Kalman filter data assimilation algorithm. More specifically, a convolutional neural network is trained to predict the error statistics of a model ensemble, which will reduce the computational costs of the ensemble Kalman filter. This approach is tested in a quasi-geostrophic dynamic model to demonstrate its feasibility in more advanced weather and climate applications.</description></item><item><title>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</title><link>https://m2lines.github.io/news/2310bhouri/</link><pubDate>Mon, 02 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310bhouri/</guid><description>In this preprint , Mohamed Aziz Bhouri and co-authors, including Pierre Gentine, developed a probabilistic multi-fidelity atmospheric parameterization for heat and moisture tendency. They implemented it on CESM CAM5 and SPCAM5 data and showed its capabilities to well extrapolate to unseen warmer climate simulations while returning trustworthy uncertainty quantification.</description></item><item><title>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</title><link>https://m2lines.github.io/news/2310chapman/</link><pubDate>Sun, 01 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310chapman/</guid><description>Stochastic and deterministic tendency adjustments are applied to multiple experiments in the community atmosphere model version 6. The tendency adjustments are gleaned from the DART data assimilation system and a linear relaxation towards ERA-interim reanalysis. In this preprint , Will Chapman and Judith Berner show that the tendency adjustment significantly enhances the representation of the background state climatology for key prognostic and surface variables. Additionally, they show that stochastic tendencies are essential to accurately represent model variability of major atmospheric modes when making tendency adjustments.</description></item><item><title> Blog Post - A New Generation of Climate Models</title><link>https://m2lines.github.io/news/2309blogpost/</link><pubDate>Mon, 11 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309blogpost/</guid><description>M²LInES can now demonstrate the impact of data-driven Machine Learning parameterizations in global models! 🌎You can read about new gen climate models with AI in our blog post</description></item><item><title>New climate simulation model ensemble by Marika Holland</title><link>https://m2lines.github.io/news/2309holland/</link><pubDate>Mon, 04 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309holland/</guid><description>Climate simulation uncertainties arise from internal variability, model structure, and external forcings. These uncertainty sources are difficult to disentangle across model generations because both model structure and external forcings typically change. This preprint , led by Marika Holland, presents new ensemble simulations which allow for the separation of uncertainty sources between two large ensembles (LEs) of the Community Earth System Model (CESM). Importantly, we find a strong influence of historical forcing uncertainty in differences between CESM1-LE and CESM2-LE due to aerosol effects on simulated climate.</description></item><item><title>Understanding Extreme Precipitation Changes by Griffin Mooers</title><link>https://m2lines.github.io/news/2309mooers/</link><pubDate>Sun, 03 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309mooers/</guid><description>Griffin Mooers is lead author in this preprint that leverages Variational Autoencoders on SPCAM5 output to examine the changes in the upper quantiles of precipitation between a control and warmed simulation. They find intense precipitation changes are mostly controlled by spatial shifts in deep convection.</description></item><item><title>Reliable coarse-grained turbulent simulations by Chris Pederson</title><link>https://m2lines.github.io/news/2309pederson/</link><pubDate>Sat, 02 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309pederson/</guid><description>In this preprint , M²LInES postdoc Chris Pedersen, along with Pavel Perezhogin, Joan Bruna, and Laure Zanna, show that the standard offline learning paradigm used to produce ML models of unresolved dynamics can be complemented with some learned time evolution of the system, and produce more stable hybrid physics and ML models.</description></item><item><title>Background Pycnocline depth constrains FOHUE by Emily Newsom</title><link>https://m2lines.github.io/news/2308newsom/</link><pubDate>Thu, 03 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308newsom/</guid><description>In this paper , Emily Newsom and co-authors Laure Zanna and Jonathan Gregory, showed that the relative depth of ocean heat sequestration, which varies widely across climate models and paces the rate of surface climate warming, is strongly correlated to interior ocean stratification. Using a novel regional decomposition method, they showed that this relationship is entirely driven by mid-latitude ventilation processes and explains 70% of the variance in heat penetration depth across CMIP5/CMIP6 models.</description></item><item><title>ClimSim: LEAP publication</title><link>https://m2lines.github.io/news/2308bhouri/</link><pubDate>Wed, 02 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308bhouri/</guid><description>Several of M²LInES members and affiliates (Bhouri, Gentine, Zanna, Abernathey, Busecke, Mooers, Shamekh, and Yuval) have contributed to this LEAP paper presenting ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. The data and code are open access.</description></item><item><title>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</title><link>https://m2lines.github.io/news/2308shamekh/</link><pubDate>Tue, 01 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308shamekh/</guid><description>This preprint , by Sara Shamekh and Pierre Gentine, proposes a novel data-driven parameterization of vertical turbulent fluxes in convective boundary layer, that models the fluxes of various scalars across turbulent regimes. By incorporating a physics-based constraint this approach allows us to decompose the total vertical flux into two main modes of variability based on large scale forces that control the turbulence in the atmosphere.</description></item><item><title>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</title><link>https://m2lines.github.io/news/2307sane/</link><pubDate>Sat, 01 Jul 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2307sane/</guid><description>Small scale vertical mixing processes in the upper ocean region cannot be resolved by ocean models due to the lack of computing resources, and are thus parameterized. Existing models have a few ad hoc approximations which cause uncertainty in climate change simulations. In this breakthrough preprint , Aakash Sane and co-authors - Brandon Reichl, Alistair Adcroft, and Laure Zanna - replace such an approximation using data driven neural networks (NN), leading to improved physics in an ocean model simulation and a reduction of model bias in the Tropics.</description></item><item><title>Smart correction model for winter sky temperatures by Lorenzo Zampieri</title><link>https://m2lines.github.io/news/2306zampieri/</link><pubDate>Thu, 01 Jun 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2306zampieri/</guid><description>This study , led by Lorenzo Zampieri, and co-authored by Marika Holland, illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea-ice-covered regions of the Arctic under clear-sky conditions. The corrected reanalysis temperature can be employed to support polar research activities, and in particular to better simulate the evolution of the interacting sea ice and ocean system within numerical models.</description></item><item><title>Data-driven subgrid parameterizations by Karl Otness</title><link>https://m2lines.github.io/news/2305otness/</link><pubDate>Mon, 01 May 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2305otness/</guid><description>In this ongoing project , Karl Otness and co-authors are evaluating a proof of concept multiscale approach to predicting subgrid forcings in climate models. They see encouraging preliminary results from first making a prediction in a fine-to-coarse direction which yields a lower resolution, but more confident prediction followed by a refinement to predict finer scale details.
+Atmosphere, Machine Learning, Data Assimilation</description></item><item><title>FTORCH and FORPY libraries now integrated to CESM!</title><link>https://m2lines.github.io/news/2405chapman/</link><pubDate>Thu, 02 May 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2405chapman/</guid><description>The M²LInES team, assisted by Jack Atkinson (ICCS) and NCAR software engineers, have integrated the FTORCH and FORPY libraries for machine learning into CESM2.1.5. To set up a machine learning-enabled CESM instance on NCAR machines, follow the steps outlined in this repository . Contact Will Chapman for questions!</description></item><item><title>Predicting September Arctic Sea Ice by Dr. Bushuk</title><link>https://m2lines.github.io/news/2405bushuk/</link><pubDate>Wed, 01 May 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2405bushuk/</guid><description>This study , led by Mitch Bushuk, provides a comparison of September Arctic sea ice seasonal prediction skill across a diverse set of 34 dynamical and statistical prediction models, quantifying the state-of-the-art in the rapidly growing sea ice prediction research community. The authors find that both dynamical and statistical prediction models can skillfully predict September Arctic sea ice 0–3 months in advance on Pan-Arctic, regional, and local spatial scales. These results demonstrate that there are bright prospects for skillful operational seasonal predictions of Arctic sea ice and highlight a number of crucial prediction system design aspects to guide future improvements.</description></item><item><title>Advances in Machine Learning Techniques for Sea Ice Applications</title><link>https://m2lines.github.io/news/2404zampieri/</link><pubDate>Wed, 03 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404zampieri/</guid><description>Forty-two international researchers, including Lorenzo Zampieri, were invited to Gwangmyeong (South Korea) to discuss recent advances in sea ice modelling to help guide the development of a state-of-the-art Korean sea ice modelling program under the leadership of the Korean Polar Research Institute (KOPRI). The workshop produced a report , which highlights 1) the opportunity to use AI techniques in support of various sea ice modelling tasks both for short-term and climate predictions and 2) the need for strengthened collaborations among international groups to connect existing “research bubbles” and facilitate the dissemination of ideas.</description></item><item><title>Joint Parameter and Parameterization Inference by Yongquan</title><link>https://m2lines.github.io/news/2404qu/</link><pubDate>Tue, 02 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404qu/</guid><description>In this article , Yongquan Qu, Mohamed Aziz Bhouri, and Pierre Gentine, tackle the joint inference and uncertainty quantification of poorly known physical parameters and machine learning parametrizations, for sub-grid scale dynamics. Achieved through a Bayesian framework enabled by differentiable programming, this method not only offers accurate parameter estimates, but also enables skillful forecasting, each accompanied by quantified uncertainty. This work is accepted at the ICLR 2024 Workshop on AI4Differential Equations In Science.</description></item><item><title>Building Ocean Climate Emulators by Adam</title><link>https://m2lines.github.io/news/2404adam/</link><pubDate>Mon, 01 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404adam/</guid><description>AI can accelerate climate modeling by generating computationally cheap emulators of existing simulations. The design of climate emulators is an exciting and open challenge in AI+Climate. In this work , PhD student Adam Subel and Laure Zanna focus on two fundamental questions to facilitate the creation of ocean emulators: 1) the role of the atmosphere in improving the decadal skill of the emulator and 2) the representation of variables with distinct timescales (e.</description></item><item><title>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</title><link>https://m2lines.github.io/news/2402bhouri/</link><pubDate>Sat, 03 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402bhouri/</guid><description>Machine Learning (ML)-based parameterizations of atmospheric convection have long been hailed as a promising alternative, with the potential to yield higher accuracy at a fraction of the cost of more explicit simulations. This work , co-authored by Mohamed Aziz Bhouri, investigates the coupled out-of-distribution extrapolation capabilities in &amp;ldquo;online&amp;rdquo; testing of different ML-based parameterization designs of atmospheric convection. Their results show that these design decisions are not enough to obtain satisfactory generalization benefits.</description></item><item><title>Stochastic Optimal Control Matching by Joan</title><link>https://m2lines.github.io/news/2402joan/</link><pubDate>Fri, 02 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402joan/</guid><description>Joan Bruna is a co-author in this preprint , introducing Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control. Stochastic optimal control’s goal is to drive the behavior of noisy systems. In this work, the control is learned via a least squares problem by trying to fit a matching vector field. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that is of independent interest, e.</description></item><item><title>Restratification Effect of Mesoscale Eddies by Noora</title><link>https://m2lines.github.io/news/2402noora/</link><pubDate>Thu, 01 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402noora/</guid><description>Nora Loose is lead author of this new paper - part of the Climate Process Team funded by NSF and NOAA - which compares two parameterizations (“GM90” and “GL90”) for the restratification effect of mesoscale eddies. The authors conclude that the less commonly used GL90 parameterization is a promising alternative to the popular GM90 scheme for isopycnal coordinate models, where it is more consistent with theory, computationally more efficient, easier to implement, and numerically more stable.</description></item><item><title>Data-driven equation discovery ocean model by Pavel</title><link>https://m2lines.github.io/news/2401pavel/</link><pubDate>Tue, 02 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401pavel/</guid><description>Pavel Perezhogin is lead author of this new M²LInES preprint , describing the implementation, in the GFDL MOM6 ocean model, of a data-driven equation-discovery parameterization of mesoscale eddies. This scale-aware parametrization improved biases in the mean flow and energetics for a range of resolutions and in different ocean configurations. The work was done in collaboration with Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda and Laure Zanna.</description></item><item><title>Learning Machine Learning with Lorenz-96</title><link>https://m2lines.github.io/news/2401l96/</link><pubDate>Mon, 01 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401l96/</guid><description>The M²LInES team is proud to share our Jupyter Book on Learning Machine Learning with Lorenz-96 . This educational tool provides a computationally accessible framework to understand how machine learning techniques can tackle climate science problems, including emulators, parameterizations, data assimilation, and uncertainty quantification. It is for all climate scientists wanting to learn or test machine learning algorithms or for machine learning experts to learn about climate modeling or develop new algorithms.</description></item><item><title>ClimSim awarded Best Paper Award at NeurIPS</title><link>https://m2lines.github.io/news/2312climsim/</link><pubDate>Tue, 12 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312climsim/</guid><description>ClimSim has been awarded Best Paper Award at NeurIPS ! The open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators, emerged out of the Science and Technology Center LEAP, received contributions from numerous M²LInES members. Congratulations to all authors!</description></item><item><title>Will Gregory's latest article featured in Advance Science News</title><link>https://m2lines.github.io/news/2312willgfeature/</link><pubDate>Fri, 01 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312willgfeature/</guid><description>The latest M²LInES article, led by Will Gregory (Princeton) is being featured in Advance Science News. The article details how Will and other colleagues, including M²LInES members Mitch Bushuk, Alistair Adcroft, and Laure Zanna, are using Machine Learning to enhance predictions of Arctic sea ice loss. Read the article by Giorgio Graffino here</description></item><item><title>OceanBench by J. Emmanuel Johnson</title><link>https://m2lines.github.io/news/2311johnson/</link><pubDate>Wed, 01 Nov 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2311johnson/</guid><description>OceanBench is a suite of tools for designing experiments relevant to the oceanography community like interpolation, forecasting and estimation. Lead author J. Emmanuel Johnson and co-authors, including Anastasiia Gorbunova and Julien Le Sommer, demonstrate its use within a benchmark setting for sea surface height interpolation, using general circulation model simulations and real satellite observations.</description></item><item><title>UNetKF by Feiyu Lu</title><link>https://m2lines.github.io/news/2310lu/</link><pubDate>Tue, 03 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310lu/</guid><description>This study by Feiyu Lu incorporates deep learning methods to compliment and improve the ensemble Kalman filter data assimilation algorithm. More specifically, a convolutional neural network is trained to predict the error statistics of a model ensemble, which will reduce the computational costs of the ensemble Kalman filter. This approach is tested in a quasi-geostrophic dynamic model to demonstrate its feasibility in more advanced weather and climate applications.</description></item><item><title>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</title><link>https://m2lines.github.io/news/2310bhouri/</link><pubDate>Mon, 02 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310bhouri/</guid><description>In this preprint , Mohamed Aziz Bhouri and co-authors, including Pierre Gentine, developed a probabilistic multi-fidelity atmospheric parameterization for heat and moisture tendency. They implemented it on CESM CAM5 and SPCAM5 data and showed its capabilities to well extrapolate to unseen warmer climate simulations while returning trustworthy uncertainty quantification.</description></item><item><title>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</title><link>https://m2lines.github.io/news/2310chapman/</link><pubDate>Sun, 01 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310chapman/</guid><description>Stochastic and deterministic tendency adjustments are applied to multiple experiments in the community atmosphere model version 6. The tendency adjustments are gleaned from the DART data assimilation system and a linear relaxation towards ERA-interim reanalysis. In this preprint , Will Chapman and Judith Berner show that the tendency adjustment significantly enhances the representation of the background state climatology for key prognostic and surface variables. Additionally, they show that stochastic tendencies are essential to accurately represent model variability of major atmospheric modes when making tendency adjustments.</description></item><item><title> Blog Post - A New Generation of Climate Models</title><link>https://m2lines.github.io/news/2309blogpost/</link><pubDate>Mon, 11 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309blogpost/</guid><description>M²LInES can now demonstrate the impact of data-driven Machine Learning parameterizations in global models! 🌎You can read about new gen climate models with AI in our blog post</description></item><item><title>New climate simulation model ensemble by Marika Holland</title><link>https://m2lines.github.io/news/2309holland/</link><pubDate>Mon, 04 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309holland/</guid><description>Climate simulation uncertainties arise from internal variability, model structure, and external forcings. These uncertainty sources are difficult to disentangle across model generations because both model structure and external forcings typically change. This preprint , led by Marika Holland, presents new ensemble simulations which allow for the separation of uncertainty sources between two large ensembles (LEs) of the Community Earth System Model (CESM). Importantly, we find a strong influence of historical forcing uncertainty in differences between CESM1-LE and CESM2-LE due to aerosol effects on simulated climate.</description></item><item><title>Understanding Extreme Precipitation Changes by Griffin Mooers</title><link>https://m2lines.github.io/news/2309mooers/</link><pubDate>Sun, 03 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309mooers/</guid><description>Griffin Mooers is lead author in this preprint that leverages Variational Autoencoders on SPCAM5 output to examine the changes in the upper quantiles of precipitation between a control and warmed simulation. They find intense precipitation changes are mostly controlled by spatial shifts in deep convection.</description></item><item><title>Reliable coarse-grained turbulent simulations by Chris Pederson</title><link>https://m2lines.github.io/news/2309pederson/</link><pubDate>Sat, 02 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309pederson/</guid><description>In this preprint , M²LInES postdoc Chris Pedersen, along with Pavel Perezhogin, Joan Bruna, and Laure Zanna, show that the standard offline learning paradigm used to produce ML models of unresolved dynamics can be complemented with some learned time evolution of the system, and produce more stable hybrid physics and ML models.</description></item><item><title>Background Pycnocline depth constrains FOHUE by Emily Newsom</title><link>https://m2lines.github.io/news/2308newsom/</link><pubDate>Thu, 03 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308newsom/</guid><description>In this paper , Emily Newsom and co-authors Laure Zanna and Jonathan Gregory, showed that the relative depth of ocean heat sequestration, which varies widely across climate models and paces the rate of surface climate warming, is strongly correlated to interior ocean stratification. Using a novel regional decomposition method, they showed that this relationship is entirely driven by mid-latitude ventilation processes and explains 70% of the variance in heat penetration depth across CMIP5/CMIP6 models.</description></item><item><title>ClimSim: LEAP publication</title><link>https://m2lines.github.io/news/2308bhouri/</link><pubDate>Wed, 02 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308bhouri/</guid><description>Several of M²LInES members and affiliates (Bhouri, Gentine, Zanna, Abernathey, Busecke, Mooers, Shamekh, and Yuval) have contributed to this LEAP paper presenting ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. The data and code are open access.</description></item><item><title>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</title><link>https://m2lines.github.io/news/2308shamekh/</link><pubDate>Tue, 01 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308shamekh/</guid><description>This preprint , by Sara Shamekh and Pierre Gentine, proposes a novel data-driven parameterization of vertical turbulent fluxes in convective boundary layer, that models the fluxes of various scalars across turbulent regimes. By incorporating a physics-based constraint this approach allows us to decompose the total vertical flux into two main modes of variability based on large scale forces that control the turbulence in the atmosphere.</description></item><item><title>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</title><link>https://m2lines.github.io/news/2307sane/</link><pubDate>Sat, 01 Jul 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2307sane/</guid><description>Small scale vertical mixing processes in the upper ocean region cannot be resolved by ocean models due to the lack of computing resources, and are thus parameterized. Existing models have a few ad hoc approximations which cause uncertainty in climate change simulations. In this breakthrough preprint , Aakash Sane and co-authors - Brandon Reichl, Alistair Adcroft, and Laure Zanna - replace such an approximation using data driven neural networks (NN), leading to improved physics in an ocean model simulation and a reduction of model bias in the Tropics.</description></item><item><title>Smart correction model for winter sky temperatures by Lorenzo Zampieri</title><link>https://m2lines.github.io/news/2306zampieri/</link><pubDate>Thu, 01 Jun 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2306zampieri/</guid><description>This study , led by Lorenzo Zampieri, and co-authored by Marika Holland, illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea-ice-covered regions of the Arctic under clear-sky conditions. The corrected reanalysis temperature can be employed to support polar research activities, and in particular to better simulate the evolution of the interacting sea ice and ocean system within numerical models.</description></item><item><title>Data-driven subgrid parameterizations by Karl Otness</title><link>https://m2lines.github.io/news/2305otness/</link><pubDate>Mon, 01 May 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2305otness/</guid><description>In this ongoing project , Karl Otness and co-authors are evaluating a proof of concept multiscale approach to predicting subgrid forcings in climate models. They see encouraging preliminary results from first making a prediction in a fine-to-coarse direction which yields a lower resolution, but more confident prediction followed by a refinement to predict finer scale details.
 This paper won “Best ML innovation” at the ICLR 2023 Workshop: Tackling Climate Change with Machine Learning.</description></item><item><title>Emulating Cloud Superparameterization by Pierre Gentine</title><link>https://m2lines.github.io/news/2301gentine/</link><pubDate>Tue, 03 Jan 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2301gentine/</guid><description>M²LInES PI Pierre Gentine is the senior author in this new publication on using deep learning for emulating cloud superparameterization in climate models. Research Scientist Tom Beucler is a co-author. Read their paper here</description></item><item><title> M²LInES at AGU 22</title><link>https://m2lines.github.io/news/2212agu22/</link><pubDate>Tue, 06 Dec 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2212agu22/</guid><description>AGU M²LInES Highlights The M²LInES team is excited to present our recent scientific advances at the Fall 2022 AGU meeting in Chicago and online. Below is a summary of the talks (all times are CST). For your convenience, you can download the schedule for the talks by following this link .
 Machine learning for physics discovery &amp;amp; modeling We have an extensive lineup of talks and posters from M²LInES team members and affiliates.</description></item><item><title> Direct observational evidence of an oceanic dual kinetic energy cascade and its seasonality</title><link>https://m2lines.github.io/news/2211balwada/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211balwada/</guid><description>In this article , led by Dhruv Balwada, ocean drifter observations show wave and turbulence merge and split flows, simultaneously transferring energy to large and small scales.</description></item><item><title> Implicit learning of convective organization explains precipitation stochasticity</title><link>https://m2lines.github.io/news/2211shamekh/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211shamekh/</guid><description>Cloud and convection take many structure and degrees of organization, which are still absent in most parameterizations. But does that structure matter for precipitation? This preprint , led by Sara Shamekh, proposes an elegant method to include organization in the parameterization of precipitation that results in a significant improvement in predicting precipitation, especially extremes, at GCM scale.</description></item><item><title> Ocean currents break up a tabular iceberg</title><link>https://m2lines.github.io/news/2211adcroft/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211adcroft/</guid><description>This article examines the mechanism that led to the breakup of massive iceberg A68 in Dec 2020. The authors, including Alistair Adcroft, demonstrate that the A68a breakup event may have been triggered by ocean-current shear, a new breakup mechanism not previously reported. Their paper was featured in the news .</description></item><item><title> On Gradient Descent Convergence beyond the Edge of Stability</title><link>https://m2lines.github.io/news/2211bruna/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211bruna/</guid><description>Joan Bruna is the senior author in this preprint on Gradient Descent (GD) convergence in unstable conditions. The study examines the conditions for such unstable convergence, focusing on simple, yet representative, learning problems.</description></item><item><title> A year-round satellite sea-ice thickness record from CryoSat-2</title><link>https://m2lines.github.io/news/2210bushuk/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210bushuk/</guid><description>This study , co-authored by Mitch Bushuk, produced the first ever year-round satellite observational record of Arctic sea ice thickness, employing a deep learning model to produce estimates of sea ice freeboard. These data span the period 2010-2020 and will be critical for better monitoring the changing Arctic climate, advancing climate model evaluation, and improving sea ice predictions.</description></item><item><title> Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning</title><link>https://m2lines.github.io/news/2210gentine/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210gentine/</guid><description>High resolution data is overwhelming and this paper , co-authored by Pierre Gentine and Tom Beucler, tries to define an unsupervised machine learning technique to better compare Storm Resolving Climate Models (SRMs). Their analysis found that only six out of nine considered SRMs are dynamically consistent. This split among SRMs highlights the need to further investigate sub-grid parameterization choices.</description></item><item><title> Semi-automatic tuning of coupled climate models with multiple intrinsic timescales</title><link>https://m2lines.github.io/news/2210deshayes/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210deshayes/</guid><description>Using the two-scale Lorenz96 model, this article evaluates the potential of History Matching to tune a climate system with multi-scale dynamics. This semi-automatic tuning was more efficient when combined with physical expertise. Julie Deshayes and V Balaji are co-authors on this study.</description></item><item><title> Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</title><link>https://m2lines.github.io/news/2208ross/</link><pubDate>Tue, 02 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208ross/</guid><description>In this work , led by Andrew Ross, with Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda and Laure Zanna, we provide a framework for systematically benchmarking the offline and online performance of physical and ML-based subgrid parameterizations. We find that the choice of filtering operator is critical for performance. To help with interpretability, we also propose a novel equation-discovery approach combining linear regression and genetic programming which generalizes better than physical and neural network parameterizations.</description></item><item><title> Cloud-based framework for inter-comparing submesoscale permitting realistic ocean models</title><link>https://m2lines.github.io/news/2208uchida/</link><pubDate>Mon, 01 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208uchida/</guid><description>This study presents a cloud-based workflow for intercomparing high-resolution ocean models and provides an assessment of one of the most used parameterizations of ocean submesoscales. Julien Le Sommer, Ryan Abernathey, and Aurelie Albert contributed to the research.</description></item><item><title> Non-Linear Dimensionality Reduction with a VED to Understand Convective Processes in Climate Models</title><link>https://m2lines.github.io/news/2208behrens/</link><pubDate>Mon, 01 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208behrens/</guid><description>Pierre Gentine and Tom Beucler are co-authors in this article , which demonstrates that Variational Encoder Decoder structures (VED) are capable of learning and accurately reproducing convective processes in an aquaplanet superparameterized climate model simulation, while enabling interpretability and better understanding of sub-grid-scale physical processes.</description></item><item><title> A potential energy analysis of ocean surface mixed layers - Brandon Reichl</title><link>https://m2lines.github.io/news/2207reichl/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207reichl/</guid><description>Analysis of the ocean mixed layer requires one to estimate its vertical extent, for which there are various definitions. In this paper , Brandon Reichl and co-authors, including Alistair Adcroft, show that using the potential energy anomaly to identify the mixed layer depth is practical and it offers conceptual benefits by directly linking to the physics of upper ocean vertical mixing.</description></item><item><title> New preprint led by Adam Subel on transfer learning</title><link>https://m2lines.github.io/news/2207subel/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207subel/</guid><description>Adam Subel is the lead author in this article , which builds a framework to understand and implement transfer learning, a powerful machine learning technique for enabling generalization between datasets from different configurations of a system or of varying quality/quantity, in multiscale physical systems.</description></item><item><title> Subseasonal Earth System Prediction with CESM2 - Judith Berner</title><link>https://m2lines.github.io/news/2207berner/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207berner/</guid><description>Judith Berner is a co-author in this article , which describes the design and prediction skill of two subseasonal prediction systems based on two configurations of the Community Earth System Model, version 2 (CESM2): with the Community Atmosphere Model and with Whole Atmosphere Community Climate Model as its atmospheric component. Both systems are compared to NOAA CFSv2 and ECMWF.</description></item><item><title> Deep Learning for Subgrid-Scale Turbulence Modeling in LES of the Convective Atmospheric Boundary Layer</title><link>https://m2lines.github.io/news/gentine-abernathey/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/gentine-abernathey/</guid><description>This article , co-authored by Pierre Gentine and Ryan Abernathey, replaces the typically used physically based assumptions with deep learning in subgrid-scale modeling, in large eddy simulations of turbulence. They show that the latter performs better in a priori (offline) tests of atmospheric turbulence. The deep neural networks model also captures key statistics of turbulence in a posteriori (online) tests.</description></item><item><title> Lorenzo Zampieri - A machine learning correction model</title><link>https://m2lines.github.io/news/zampieri2022/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/zampieri2022/</guid><description>Lorenzo Zampieri et al. illustrate in this preprint , a novel method based on ML for reducing the surface temperature errors of atmospheric reanalyses in sea-ice-covered regions of the Arctic. The corrected temperature can be employed to support polar research activities, and to better simulate the evolution of the interacting sea ice and ocean systems in numerical models.</description></item><item><title> Will Gregory - Network connectivity article</title><link>https://m2lines.github.io/news/gregory2022/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/gregory2022/</guid><description>Will Gregory and co-authors hypothesized in this publication that regional biases in sea ice thickness may hinder the ability of CMIP6 models to reproduce an important atmospheric driver of summer sea ice variability, and hence their ability to make reliable sea ice predictions on seasonal to inter-annual time scales.</description></item><item><title> 2022 CESM workshop: Info and submission deadline</title><link>https://m2lines.github.io/news/cesmworkshop2022/</link><pubDate>Mon, 02 May 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/cesmworkshop2022/</guid><description>Registration is open for the 2022 CESM Workshop on June 13-16, 2022. Please visit the website to register as well as submit working group session talks and /or posters. The deadline to submit a talk / poster is Monday, May 16th.
 The full workshop agenda can be found here .
diff --git a/news/2405bushuk/index.html b/news/2405bushuk/index.html
new file mode 100644
index 000000000..0091c4f55
--- /dev/null
+++ b/news/2405bushuk/index.html
@@ -0,0 +1,13 @@
+<!doctype html><html lang=en><head><meta charset=utf-8><meta http-equiv=x-ua-compatible content="ie=edge"><title>Predicting September Arctic Sea Ice by Dr. Bushuk - M²LInES</title><meta name=viewport content="width=device-width,initial-scale=1"><link rel=icon href=https://m2lines.github.io/favicon.png><link rel=stylesheet href=../../css/style.min.dbd2db6b7e1187dfa89c2bd4a021de2eee6be3bbf7112b261ba2605ae8d04a18.css></head><body class=page><div id=main-menu-mobile class=main-menu-mobile><ul><li class=menu-item-about><a href=../../about/><span>About</span></a></li><li class="menu-item-join us"><a href=../../jobs/><span>Join us</span></a></li><li class="menu-item-current members"><a href=../../team/><span>Team: Current members</span></a></li><li class="menu-item-former members"><a href=../../team/former><span>Team: Former members</span></a></li><li class=menu-item-themes><a href=../../research/><span>Research: Themes</span></a></li><li class=menu-item-talks><a href=../../research/talks/><span>Research: Talks</span></a></li><li class=menu-item-code><a href=../../code/><span>Code</span></a></li><li class=menu-item-latest><a href=../../publications/><span>Publications: Latest</span></a></li><li class=menu-item-archive><a href=../../publications/archive><span>Publications: Archive</span></a></li><li class="menu-item-our news"><a href=../../news/><span>News: Our news</span></a></li><li class=menu-item-newsletters><a href=../../news/newsletters/><span>News: Newsletters</span></a></li></ul></div><div id=wrapper class=wrapper><div class="header header-absolute"><div class=container><div class=logo><a href=https://m2lines.github.io/><img alt="M²LInES homepage" src=https://m2lines.github.io/images/newlogo.png></a></div><div class=logo-mobile><a href=https://m2lines.github.io/><img alt="M²LInES homepage" src=https://m2lines.github.io/images/newlogo.png></a></div><nav class=menu><ul class=menu__list><li class=menu__item><a class=menu__link href=../../about/><span class=menu__text>About</span></a></li><li class=menu__item><a class=menu__link href=../../jobs/><span class=menu__text>Join us</span></a></li><li class="menu__item menu__dropdown"><a class=menu__link href=../../team/><span class=menu__text>Team</span>
+<label class=drop-icon for=Team>▾</label></a>
+<input type=checkbox id=Team><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../team/><span class=menu__text>Current members</span></a></li><li class=menu__item><a class=menu__link href=../../team/former><span class=menu__text>Former members</span></a></li></ul></li><li class="menu__item menu__dropdown"><a class=menu__link href><span class=menu__text>Research</span>
+<label class=drop-icon for=Research>▾</label></a>
+<input type=checkbox id=Research><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../research/><span class=menu__text>Themes</span></a></li><li class=menu__item><a class=menu__link href=../../research/talks/><span class=menu__text>Talks</span></a></li></ul></li><li class=menu__item><a class=menu__link href=../../code/><span class=menu__text>Code</span></a></li><li class="menu__item menu__dropdown"><a class=menu__link href=../../publications/><span class=menu__text>Publications</span>
+<label class=drop-icon for=Publications>▾</label></a>
+<input type=checkbox id=Publications><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../publications/><span class=menu__text>Latest</span></a></li><li class=menu__item><a class=menu__link href=../../publications/archive><span class=menu__text>Archive</span></a></li></ul></li><li class="menu__item menu__dropdown"><a class=menu__link href><span class=menu__text>News</span>
+<label class=drop-icon for=News>▾</label></a>
+<input type=checkbox id=News><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../news/><span class=menu__text>Our news</span></a></li><li class=menu__item><a class=menu__link href=../../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
+<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style="background-image:url('/')"><div class=container><div class=hero-text><span class=hero-section>news</span><h1></h1><p>Predicting September Arctic Sea Ice: A Multi-Model Seasonal Skill Comparison</p></div></div></div><div class="container pt-1 pt-md-1 pb-4 pb-md-10"><div class="row justify-content-start"><div class="col-12 pt-1 pt-md-1"><h2 class="mb-1 text-uppercase"></h2><div class=masonry><div class="work-image item"><img class="img-fluid mx-auto d-block" src=../../images/news/2405Bushuk.png></div></div></div><div class="col-12 col-auto"><div class="work work-single"><div class="text text-justify mx-auto"><p>This <a href=https://journals.ametsoc.org/view/journals/bams/aop/BAMS-D-23-0163.1/BAMS-D-23-0163.1.xml target=_blank>study</a>
+, led by <strong>Mitch Bushuk</strong>, provides a comparison of September Arctic sea ice seasonal prediction skill across a diverse set of 34 dynamical and statistical prediction models, quantifying the state-of-the-art in the rapidly growing sea ice prediction research community. The authors find that both dynamical and statistical prediction models can skillfully predict September Arctic sea ice 0–3 months in advance on Pan-Arctic, regional, and local spatial scales. These results demonstrate that there are bright prospects for skillful operational seasonal predictions of Arctic sea ice and highlight a number of crucial prediction system design aspects to guide future improvements.</p></div></div></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+<a href=https://twitter.com/M2LInES target=blank><img src=../../images/twitter.svg title=Twitter alt=Twitter></a>
+<a href=https://github.com/m2lines target=blank><img src=../../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/news/2405chapman/index.html b/news/2405chapman/index.html
new file mode 100644
index 000000000..f0c63742f
--- /dev/null
+++ b/news/2405chapman/index.html
@@ -0,0 +1,13 @@
+<!doctype html><html lang=en><head><meta charset=utf-8><meta http-equiv=x-ua-compatible content="ie=edge"><title>FTORCH and FORPY libraries now integrated to CESM! - M²LInES</title><meta name=viewport content="width=device-width,initial-scale=1"><link rel=icon href=https://m2lines.github.io/favicon.png><link rel=stylesheet href=../../css/style.min.dbd2db6b7e1187dfa89c2bd4a021de2eee6be3bbf7112b261ba2605ae8d04a18.css></head><body class=page><div id=main-menu-mobile class=main-menu-mobile><ul><li class=menu-item-about><a href=../../about/><span>About</span></a></li><li class="menu-item-join us"><a href=../../jobs/><span>Join us</span></a></li><li class="menu-item-current members"><a href=../../team/><span>Team: Current members</span></a></li><li class="menu-item-former members"><a href=../../team/former><span>Team: Former members</span></a></li><li class=menu-item-themes><a href=../../research/><span>Research: Themes</span></a></li><li class=menu-item-talks><a href=../../research/talks/><span>Research: Talks</span></a></li><li class=menu-item-code><a href=../../code/><span>Code</span></a></li><li class=menu-item-latest><a href=../../publications/><span>Publications: Latest</span></a></li><li class=menu-item-archive><a href=../../publications/archive><span>Publications: Archive</span></a></li><li class="menu-item-our news"><a href=../../news/><span>News: Our news</span></a></li><li class=menu-item-newsletters><a href=../../news/newsletters/><span>News: Newsletters</span></a></li></ul></div><div id=wrapper class=wrapper><div class="header header-absolute"><div class=container><div class=logo><a href=https://m2lines.github.io/><img alt="M²LInES homepage" src=https://m2lines.github.io/images/newlogo.png></a></div><div class=logo-mobile><a href=https://m2lines.github.io/><img alt="M²LInES homepage" src=https://m2lines.github.io/images/newlogo.png></a></div><nav class=menu><ul class=menu__list><li class=menu__item><a class=menu__link href=../../about/><span class=menu__text>About</span></a></li><li class=menu__item><a class=menu__link href=../../jobs/><span class=menu__text>Join us</span></a></li><li class="menu__item menu__dropdown"><a class=menu__link href=../../team/><span class=menu__text>Team</span>
+<label class=drop-icon for=Team>▾</label></a>
+<input type=checkbox id=Team><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../team/><span class=menu__text>Current members</span></a></li><li class=menu__item><a class=menu__link href=../../team/former><span class=menu__text>Former members</span></a></li></ul></li><li class="menu__item menu__dropdown"><a class=menu__link href><span class=menu__text>Research</span>
+<label class=drop-icon for=Research>▾</label></a>
+<input type=checkbox id=Research><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../research/><span class=menu__text>Themes</span></a></li><li class=menu__item><a class=menu__link href=../../research/talks/><span class=menu__text>Talks</span></a></li></ul></li><li class=menu__item><a class=menu__link href=../../code/><span class=menu__text>Code</span></a></li><li class="menu__item menu__dropdown"><a class=menu__link href=../../publications/><span class=menu__text>Publications</span>
+<label class=drop-icon for=Publications>▾</label></a>
+<input type=checkbox id=Publications><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../publications/><span class=menu__text>Latest</span></a></li><li class=menu__item><a class=menu__link href=../../publications/archive><span class=menu__text>Archive</span></a></li></ul></li><li class="menu__item menu__dropdown"><a class=menu__link href><span class=menu__text>News</span>
+<label class=drop-icon for=News>▾</label></a>
+<input type=checkbox id=News><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../news/><span class=menu__text>Our news</span></a></li><li class=menu__item><a class=menu__link href=../../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
+<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style="background-image:url('/')"><div class=container><div class=hero-text><span class=hero-section>news</span><h1></h1><p>FTORCH and FORPY libraries now integrated to CESM!</p></div></div></div><div class="container pt-1 pt-md-1 pb-4 pb-md-10"><div class="row justify-content-start"><div class="col-12 pt-1 pt-md-1"><h2 class="mb-1 text-uppercase"></h2><div class=masonry><div class="work-image item"><img class="img-fluid mx-auto d-block" src=../../images/news/2405Chapman.png></div></div></div><div class="col-12 col-auto"><div class="work work-single"><div class="text text-justify mx-auto"><p>The <strong>M²LInES team</strong>, assisted by Jack Atkinson (ICCS) and NCAR software engineers, have integrated the FTORCH and FORPY libraries for machine learning into CESM2.1.5. To set up a machine learning-enabled CESM instance on NCAR machines, follow the <a href=https://github.com/WillyChap/CESM/tree/cesm2.1.5_FTORCH_FORPY target=_blank>steps outlined in this repository</a>
+. Contact <strong>Will Chapman</strong> for questions!</p></div></div></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+<a href=https://twitter.com/M2LInES target=blank><img src=../../images/twitter.svg title=Twitter alt=Twitter></a>
+<a href=https://github.com/m2lines target=blank><img src=../../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/news/index.html b/news/index.html
index eeca46938..8570711da 100644
--- a/news/index.html
+++ b/news/index.html
@@ -7,6 +7,6 @@
 <input type=checkbox id=Publications><ul class=submenu__list><li class=menu__item><a class=menu__link href=../publications/><span class=menu__text>Latest</span></a></li><li class=menu__item><a class=menu__link href=../publications/archive><span class=menu__text>Archive</span></a></li></ul></li><li class="menu__item menu__dropdown menu__item--active"><a class=menu__link href><span class=menu__text>News</span>
 <label class=drop-icon for=News>▾</label></a>
 <input type=checkbox id=News><ul class=submenu__list><li class="menu__item menu__item--active"><a class=menu__link href=../news/><span class=menu__text>Our news</span></a></li><li class=menu__item><a class=menu__link href=../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
-<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style=background-image:url(/images/photo-newspapers-unsplash.jpeg)><div class=container><div class=hero-text><span class=hero-section></span><h1>News</h1><p>M²LInES in the news and news from M²LInES</p></div></div></div><div class="container pb-3 pt-3 pb-md-5 pt-md-5"><div class=row><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404zampieri/><div class=image-container><img src=../images/newlogo.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404zampieri/>Advances in Machine Learning Techniques for Sea Ice Applications</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404qu/><div class=image-container><img src=../images/news/2404Qu.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404qu/>Joint Parameter and Parameterization Inference by Yongquan</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404adam/><div class=image-container><img src=../images/news/2404Adam.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404adam/>Building Ocean Climate Emulators by Adam</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402bhouri/><div class=image-container><img src=../images/news/2402Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402bhouri/>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402joan/><div class=image-container><img src=../images/news/2402Joan.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402joan/>Stochastic Optimal Control Matching by Joan</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402noora/><div class=image-container><img src=../images/news/2402Noora.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402noora/>Restratification Effect of Mesoscale Eddies by Noora</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2401pavel/><div class=image-container><img src=../images/news/2401Pavel.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2401pavel/>Data-driven equation discovery ocean model by Pavel</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2401l96/><div class=image-container><img src=../images/news/2401L96.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2401l96/>Learning Machine Learning with Lorenz-96</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2312climsim/><div class=image-container><img src=../images/news/ClimSIm.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2312climsim/>ClimSim awarded Best Paper Award at NeurIPS</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2312willgfeature/><div class=image-container><img src=../images/news/tina-rolf-yuF2B5Zyz88-unsplash.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2312willgfeature/>Will Gregory's latest article featured in Advance Science News</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2311johnson/><div class=image-container><img src=../images/news/2311Johnson.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2311johnson/>OceanBench by J. Emmanuel Johnson</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310lu/><div class=image-container><img src=../images/news/2310Lu.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310lu/>UNetKF by Feiyu Lu</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310bhouri/><div class=image-container><img src=../images/news/2310Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310bhouri/>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310chapman/><div class=image-container><img src=../images/news/2310Chapman.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310chapman/>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309blogpost/><div class=image-container><img src=../images/news/SSH.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309blogpost/>Blog Post - A New Generation of Climate Models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309holland/><div class=image-container><img src=../images/news/2309-Holland.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309holland/>New climate simulation model ensemble by Marika Holland</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309mooers/><div class=image-container><img src=../images/news/2309-Moors.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309mooers/>Understanding Extreme Precipitation Changes by Griffin Mooers</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309pederson/><div class=image-container><img src=../images/publications/rcts_23.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309pederson/>Reliable coarse-grained turbulent simulations by Chris Pederson</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308newsom/><div class=image-container><img src=../images/news/2308-Newsom.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308newsom/>Background Pycnocline depth constrains FOHUE by Emily Newsom</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308bhouri/><div class=image-container><img src=../images/news/2308-Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308bhouri/>ClimSim: LEAP publication</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308shamekh/><div class=image-container><img src=../images/news/2308-Shamekh.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308shamekh/>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2307sane/><div class=image-container><img src=../images/news/2307-Sane.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2307sane/>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2306zampieri/><div class=image-container><img src=../images/news/2306-Zampieri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2306zampieri/>Smart correction model for winter sky temperatures by Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2305otness/><div class=image-container><img src=../images/news/2305-Otness.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2305otness/>Data-driven subgrid parameterizations by Karl Otness</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2301gentine/><div class=image-container><img src=../images/news/Pierrepaper1-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2301gentine/>Emulating Cloud Superparameterization by Pierre Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2212agu22/><div class=image-container><img src=../images/news/2212-WillGregory.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2212agu22/>M²LInES at AGU 22</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211balwada/><div class=image-container><img src=../images/news/2211Balwada.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211balwada/>Direct observational evidence of an oceanic dual kinetic energy cascade and its seasonality</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211shamekh/><div class=image-container><img src=../images/news/2211Shamekh.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211shamekh/>Implicit learning of convective organization explains precipitation stochasticity</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211adcroft/><div class=image-container><img src=../images/news/2211Adcroft.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211adcroft/>Ocean currents break up a tabular iceberg</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211bruna/><div class=image-container><img src=../images/news/2211Bruna.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211bruna/>On Gradient Descent Convergence beyond the Edge of Stability</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210bushuk/><div class=image-container><img src=../images/news/2210Bushuk.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210bushuk/>A year-round satellite sea-ice thickness record from CryoSat-2</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210gentine/><div class=image-container><img src=../images/news/2210Gentine.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210gentine/>Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210deshayes/><div class=image-container><img src=../images/news/2210Lguensat.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210deshayes/>Semi-automatic tuning of coupled climate models with multiple intrinsic timescales</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208ross/><div class=image-container><img src=../images/news/2208-Ross.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208ross/>Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208uchida/><div class=image-container><img src=../images/news/2208-Uchida.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208uchida/>Cloud-based framework for inter-comparing submesoscale permitting realistic ocean models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208behrens/><div class=image-container><img src=../images/news/2208-Behrens.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208behrens/>Non-Linear Dimensionality Reduction with a VED to Understand Convective Processes in Climate Models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207reichl/><div class=image-container><img src=../images/news/2207-Reichl.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207reichl/>A potential energy analysis of ocean surface mixed layers - Brandon Reichl</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207subel/><div class=image-container><img src=../images/news/2207-Subel.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207subel/>New preprint led by Adam Subel on transfer learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207berner/><div class=image-container><img src=../images/news/2207-Berner.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207berner/>Subseasonal Earth System Prediction with CESM2 - Judith Berner</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gentine-abernathey/><div class=image-container><img src=../images/news/Gentine22.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gentine-abernathey/>Deep Learning for Subgrid-Scale Turbulence Modeling in LES of the Convective Atmospheric Boundary Layer</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampieri2022/><div class=image-container><img src=../images/news/Zampieri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampieri2022/>Lorenzo Zampieri - A machine learning correction model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gregory2022/><div class=image-container><img src=../images/news/Gregory2022.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gregory2022/>Will Gregory - Network connectivity article</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/cesmworkshop2022/><div class=image-container><img src=../images/news/cesm-workshop-2021.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/cesmworkshop2022/>2022 CESM workshop: Info and submission deadline</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gorbunova2021/><div class=image-container><img src=../images/news/Gorbunova.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gorbunova2021/>Anastasiia Gorbunova - Eulerian spatiotemporal correlations in passive scalar turbulence</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gcmfilter/><div class=image-container><img src=../images/news/GCMfilters.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gcmfilter/>GCM-Filters publication</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/holland2022/><div class=image-container><img src=../images/news/Holland.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/holland2022/>Marika Holland - Arctic sea ice sensitivity to lateral melting representation</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balaji2022/><div class=image-container><img src=../images/news/Balaji.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balaji2022/>Balaji - Are GCMs obsolete?</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401subel/><div class=image-container><img src=../images/news/2204-Subel.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401subel/>Adam Subel - Stable a posteriori LES of 2D turbulence using convolutional neural networks</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401bruna/><div class=image-container><img src=../images/news/2204-Bruna.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401bruna/>Joan Bruna - Neural Galerkin Scheme preprint</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401bushuk/><div class=image-container><img src=../images/news/2204-Bushuk.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401bushuk/>Mitch Bushuk on the Mechanisms of Regional Arctic Sea Ice Predictability</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balwadazanna22/><div class=image-container><img src=../images/news/BalwadaZannaSIAM.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balwadazanna22/>Dhruv Balwada and Laure Zanna article in SIAM news</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/m2linesmovie/><div class=image-container><img src=../images/news/m2linesmovie.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/m2linesmovie/>Movie about M²LInES and featured on AGU TV!</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/sanepaper2022/><div class=image-container><img src=../images/news/SanePaper2022.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/sanepaper2022/>Aakash Sane - Evaluating Coupled Climate Model Parameterizations</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/abernatheychapter/><div class=image-container><img src=../images/news/AbernatheyChapter.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/abernatheychapter/>Book Chapter - Isopycnal mixing by Ryan Abernathey</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/beuclerpreprint/><div class=image-container><img src=../images/news/Beuclerpreprint.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/beuclerpreprint/>Climate-Invariant Machine Learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/fernandezgranda21/><div class=image-container><img src=../images/news/FernandezGranda21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/fernandezgranda21/>Deep Probability Estimation</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/frezatpreprint/><div class=image-container><img src=../images/news/Frezat-al-2021b_summary_small.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/frezatpreprint/>Hugo Frezat - A posteriori learning of quasi-geostrophic turbulence parametrization</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/ziweili21/><div class=image-container><img src=../images/news/ZiweiLi21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/ziweili21/>Tropical precipitation clusters as islands on a rough water-vapor topography</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/agupresentation/><div class=image-container><img src=../images/news/JanniYuval.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/agupresentation/>AGU presentations by M²LInES team members</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/kickoffoct/><div class=image-container><img src=../images/news/merged_screenshot.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/kickoffoct/>M²LInES Kickoff meeting</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/hollandetal/><div class=image-container><img src=../images/news/Hollandetal.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/hollandetal/>The influence of snow on sea ice as assessed from simulations of CESM2 - Marika Holland</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/chapmanetal/><div class=image-container><img src=../images/news/Chapmanetal.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/chapmanetal/>Probabilistic Predictions from Deterministic Atmospheric River Forecasts with Deep Learning - Will Chapman</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampierietal21/><div class=image-container><img src=../images/news/Zampieri21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampierietal21/>Response of Northern Hemisphere Weather and Climate to Arctic Sea Ice Decline - Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/aiforgood/><div class=image-container><img src=../images/news/Aiforgood-1920x1080-zoom-discovery-banner-1-1130x650.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/aiforgood/>UN AI for Good: AI and Climate Science seminars</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/fernandezgranda/><div class=image-container><img src=../images/news/Carlos-fig.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/fernandezgranda/>Adaptive Denoising via GainTuning - Carlos Fernandez-Granda</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampierijames/><div class=image-container><img src=../images/news/Zampieri-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampierijames/>Impact of Sea-Ice Model Complexity on model performance by Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balwada-article/><div class=image-container><img src=../images/news/Dhruv-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balwada-article/>Article by Dhruv Balwada et al. - Role of submesoscale flows on vertical fluxes</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/abernatheypaper/><div class=image-container><img src=../images/news/Abernathey-article.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/abernatheypaper/>Estimating Ocean Surface Currents With Machine Learning - Ryan Abernathey</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/bushukarticle/><div class=image-container><img src=../images/news/Bushuk-fig.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/bushukarticle/>Seasonal Prediction and Predictability of Regional Antarctic Sea Ice - Mitch Bushuk</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/ziweiliarticle/><div class=image-container><img src=../images/news/ZiweilLi-fig4.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/ziweiliarticle/>Neural Networks as Geometric Chaotic Maps - by Ziwei Li</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/articleyuval/><div class=image-container><img src=../images/news/yuval-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/articleyuval/>Neural network parametrization of a subgrid process - by Janni Yuval and Paul O'Gorman</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/articlejamescall/><div class=image-container><img src=../images/news/Yuval-article.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/articlejamescall/>Article in Eos by Yuval et al. - Call for Papers on Machine Learning and Earth System Modeling</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/oneworld/><div class=image-container><img src=../images/news/OneWorldseminar.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/oneworld/>Upcoming Seminar by Laure Zanna at One World Mathematics of Climate - 7/6</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/willgregorypaper/><div class=image-container><img src=../images/news/WillGregory-figure1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/willgregorypaper/>A Bayesian approach towards sea ice freeboard estimates - paper by Will Gregory</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/s2schallenge/><div class=image-container><img src=../images/news/ML_model_schematic.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/s2schallenge/>s2s challenge</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/kitpconference/><div class=image-container><img src=../images/news/climate-c21-logo.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/kitpconference/>KITP conference: Machine Learning for Climate</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/cesmworkshop/><div class=image-container><img src=../images/news/cesm-workshop-2021.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/cesmworkshop/>2021 CESM workshop: M²LInES team members presenting on June 17th</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/5jamescall/><div class=image-container><img src=../images/news/JAMEScall.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/5jamescall/>Call for Papers for JAMES</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/3gentinepaper1/><div class=image-container><img src=../images/news/Pierrepaper1-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/3gentinepaper1/>Using deep learning to emulate cloud superparameterization - new paper by PI Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/4gentinepaper2/><div class=image-container><img src=../images/news/Pierrepaper2-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/4gentinepaper2/>Neural Network emulating physical constraints - paper by PI Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/1guillauminpaper/><div class=image-container><img src=../images/news/Arthur-fig2.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/1guillauminpaper/>New paper on deep learning parametrization by Guillaumin and Zanna</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2jlesommerpaper/><div class=image-container><img src=../images/news/Julien-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2jlesommerpaper/>Modelisation using neural network - paper by PI Le Sommer</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/newsletters/>Newsletters</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style=background-image:url(/images/photo-newspapers-unsplash.jpeg)><div class=container><div class=hero-text><span class=hero-section></span><h1>News</h1><p>M²LInES in the news and news from M²LInES</p></div></div></div><div class="container pb-3 pt-3 pb-md-5 pt-md-5"><div class=row><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2405chapman/><div class=image-container><img src=../images/news/2405Chapman.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2405chapman/>FTORCH and FORPY libraries now integrated to CESM!</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2405bushuk/><div class=image-container><img src=../images/news/2405Bushuk.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2405bushuk/>Predicting September Arctic Sea Ice by Dr. Bushuk</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404zampieri/><div class=image-container><img src=../images/newlogo.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404zampieri/>Advances in Machine Learning Techniques for Sea Ice Applications</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404qu/><div class=image-container><img src=../images/news/2404Qu.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404qu/>Joint Parameter and Parameterization Inference by Yongquan</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2404adam/><div class=image-container><img src=../images/news/2404Adam.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2404adam/>Building Ocean Climate Emulators by Adam</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402bhouri/><div class=image-container><img src=../images/news/2402Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402bhouri/>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402joan/><div class=image-container><img src=../images/news/2402Joan.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402joan/>Stochastic Optimal Control Matching by Joan</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2402noora/><div class=image-container><img src=../images/news/2402Noora.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2402noora/>Restratification Effect of Mesoscale Eddies by Noora</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2401pavel/><div class=image-container><img src=../images/news/2401Pavel.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2401pavel/>Data-driven equation discovery ocean model by Pavel</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2401l96/><div class=image-container><img src=../images/news/2401L96.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2401l96/>Learning Machine Learning with Lorenz-96</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2312climsim/><div class=image-container><img src=../images/news/ClimSIm.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2312climsim/>ClimSim awarded Best Paper Award at NeurIPS</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2312willgfeature/><div class=image-container><img src=../images/news/tina-rolf-yuF2B5Zyz88-unsplash.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2312willgfeature/>Will Gregory's latest article featured in Advance Science News</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2311johnson/><div class=image-container><img src=../images/news/2311Johnson.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2311johnson/>OceanBench by J. Emmanuel Johnson</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310lu/><div class=image-container><img src=../images/news/2310Lu.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310lu/>UNetKF by Feiyu Lu</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310bhouri/><div class=image-container><img src=../images/news/2310Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310bhouri/>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2310chapman/><div class=image-container><img src=../images/news/2310Chapman.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2310chapman/>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309blogpost/><div class=image-container><img src=../images/news/SSH.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309blogpost/>Blog Post - A New Generation of Climate Models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309holland/><div class=image-container><img src=../images/news/2309-Holland.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309holland/>New climate simulation model ensemble by Marika Holland</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309mooers/><div class=image-container><img src=../images/news/2309-Moors.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309mooers/>Understanding Extreme Precipitation Changes by Griffin Mooers</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2309pederson/><div class=image-container><img src=../images/publications/rcts_23.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2309pederson/>Reliable coarse-grained turbulent simulations by Chris Pederson</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308newsom/><div class=image-container><img src=../images/news/2308-Newsom.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308newsom/>Background Pycnocline depth constrains FOHUE by Emily Newsom</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308bhouri/><div class=image-container><img src=../images/news/2308-Bhouri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308bhouri/>ClimSim: LEAP publication</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2308shamekh/><div class=image-container><img src=../images/news/2308-Shamekh.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2308shamekh/>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2307sane/><div class=image-container><img src=../images/news/2307-Sane.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2307sane/>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2306zampieri/><div class=image-container><img src=../images/news/2306-Zampieri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2306zampieri/>Smart correction model for winter sky temperatures by Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2305otness/><div class=image-container><img src=../images/news/2305-Otness.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2305otness/>Data-driven subgrid parameterizations by Karl Otness</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2301gentine/><div class=image-container><img src=../images/news/Pierrepaper1-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2301gentine/>Emulating Cloud Superparameterization by Pierre Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2212agu22/><div class=image-container><img src=../images/news/2212-WillGregory.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2212agu22/>M²LInES at AGU 22</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211balwada/><div class=image-container><img src=../images/news/2211Balwada.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211balwada/>Direct observational evidence of an oceanic dual kinetic energy cascade and its seasonality</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211shamekh/><div class=image-container><img src=../images/news/2211Shamekh.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211shamekh/>Implicit learning of convective organization explains precipitation stochasticity</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211adcroft/><div class=image-container><img src=../images/news/2211Adcroft.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211adcroft/>Ocean currents break up a tabular iceberg</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2211bruna/><div class=image-container><img src=../images/news/2211Bruna.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2211bruna/>On Gradient Descent Convergence beyond the Edge of Stability</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210bushuk/><div class=image-container><img src=../images/news/2210Bushuk.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210bushuk/>A year-round satellite sea-ice thickness record from CryoSat-2</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210gentine/><div class=image-container><img src=../images/news/2210Gentine.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210gentine/>Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2210deshayes/><div class=image-container><img src=../images/news/2210Lguensat.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2210deshayes/>Semi-automatic tuning of coupled climate models with multiple intrinsic timescales</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208ross/><div class=image-container><img src=../images/news/2208-Ross.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208ross/>Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208uchida/><div class=image-container><img src=../images/news/2208-Uchida.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208uchida/>Cloud-based framework for inter-comparing submesoscale permitting realistic ocean models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2208behrens/><div class=image-container><img src=../images/news/2208-Behrens.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2208behrens/>Non-Linear Dimensionality Reduction with a VED to Understand Convective Processes in Climate Models</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207reichl/><div class=image-container><img src=../images/news/2207-Reichl.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207reichl/>A potential energy analysis of ocean surface mixed layers - Brandon Reichl</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207subel/><div class=image-container><img src=../images/news/2207-Subel.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207subel/>New preprint led by Adam Subel on transfer learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2207berner/><div class=image-container><img src=../images/news/2207-Berner.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2207berner/>Subseasonal Earth System Prediction with CESM2 - Judith Berner</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gentine-abernathey/><div class=image-container><img src=../images/news/Gentine22.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gentine-abernathey/>Deep Learning for Subgrid-Scale Turbulence Modeling in LES of the Convective Atmospheric Boundary Layer</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampieri2022/><div class=image-container><img src=../images/news/Zampieri.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampieri2022/>Lorenzo Zampieri - A machine learning correction model</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gregory2022/><div class=image-container><img src=../images/news/Gregory2022.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gregory2022/>Will Gregory - Network connectivity article</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/cesmworkshop2022/><div class=image-container><img src=../images/news/cesm-workshop-2021.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/cesmworkshop2022/>2022 CESM workshop: Info and submission deadline</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gorbunova2021/><div class=image-container><img src=../images/news/Gorbunova.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gorbunova2021/>Anastasiia Gorbunova - Eulerian spatiotemporal correlations in passive scalar turbulence</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/gcmfilter/><div class=image-container><img src=../images/news/GCMfilters.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/gcmfilter/>GCM-Filters publication</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/holland2022/><div class=image-container><img src=../images/news/Holland.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/holland2022/>Marika Holland - Arctic sea ice sensitivity to lateral melting representation</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balaji2022/><div class=image-container><img src=../images/news/Balaji.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balaji2022/>Balaji - Are GCMs obsolete?</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401subel/><div class=image-container><img src=../images/news/2204-Subel.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401subel/>Adam Subel - Stable a posteriori LES of 2D turbulence using convolutional neural networks</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401bruna/><div class=image-container><img src=../images/news/2204-Bruna.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401bruna/>Joan Bruna - Neural Galerkin Scheme preprint</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/220401bushuk/><div class=image-container><img src=../images/news/2204-Bushuk.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/220401bushuk/>Mitch Bushuk on the Mechanisms of Regional Arctic Sea Ice Predictability</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balwadazanna22/><div class=image-container><img src=../images/news/BalwadaZannaSIAM.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balwadazanna22/>Dhruv Balwada and Laure Zanna article in SIAM news</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/m2linesmovie/><div class=image-container><img src=../images/news/m2linesmovie.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/m2linesmovie/>Movie about M²LInES and featured on AGU TV!</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/sanepaper2022/><div class=image-container><img src=../images/news/SanePaper2022.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/sanepaper2022/>Aakash Sane - Evaluating Coupled Climate Model Parameterizations</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/abernatheychapter/><div class=image-container><img src=../images/news/AbernatheyChapter.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/abernatheychapter/>Book Chapter - Isopycnal mixing by Ryan Abernathey</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/beuclerpreprint/><div class=image-container><img src=../images/news/Beuclerpreprint.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/beuclerpreprint/>Climate-Invariant Machine Learning</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/fernandezgranda21/><div class=image-container><img src=../images/news/FernandezGranda21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/fernandezgranda21/>Deep Probability Estimation</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/frezatpreprint/><div class=image-container><img src=../images/news/Frezat-al-2021b_summary_small.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/frezatpreprint/>Hugo Frezat - A posteriori learning of quasi-geostrophic turbulence parametrization</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/ziweili21/><div class=image-container><img src=../images/news/ZiweiLi21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/ziweili21/>Tropical precipitation clusters as islands on a rough water-vapor topography</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/agupresentation/><div class=image-container><img src=../images/news/JanniYuval.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/agupresentation/>AGU presentations by M²LInES team members</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/kickoffoct/><div class=image-container><img src=../images/news/merged_screenshot.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/kickoffoct/>M²LInES Kickoff meeting</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/hollandetal/><div class=image-container><img src=../images/news/Hollandetal.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/hollandetal/>The influence of snow on sea ice as assessed from simulations of CESM2 - Marika Holland</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/chapmanetal/><div class=image-container><img src=../images/news/Chapmanetal.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/chapmanetal/>Probabilistic Predictions from Deterministic Atmospheric River Forecasts with Deep Learning - Will Chapman</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampierietal21/><div class=image-container><img src=../images/news/Zampieri21.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampierietal21/>Response of Northern Hemisphere Weather and Climate to Arctic Sea Ice Decline - Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/aiforgood/><div class=image-container><img src=../images/news/Aiforgood-1920x1080-zoom-discovery-banner-1-1130x650.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/aiforgood/>UN AI for Good: AI and Climate Science seminars</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/fernandezgranda/><div class=image-container><img src=../images/news/Carlos-fig.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/fernandezgranda/>Adaptive Denoising via GainTuning - Carlos Fernandez-Granda</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/zampierijames/><div class=image-container><img src=../images/news/Zampieri-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/zampierijames/>Impact of Sea-Ice Model Complexity on model performance by Lorenzo Zampieri</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/balwada-article/><div class=image-container><img src=../images/news/Dhruv-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/balwada-article/>Article by Dhruv Balwada et al. - Role of submesoscale flows on vertical fluxes</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/abernatheypaper/><div class=image-container><img src=../images/news/Abernathey-article.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/abernatheypaper/>Estimating Ocean Surface Currents With Machine Learning - Ryan Abernathey</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/bushukarticle/><div class=image-container><img src=../images/news/Bushuk-fig.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/bushukarticle/>Seasonal Prediction and Predictability of Regional Antarctic Sea Ice - Mitch Bushuk</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/ziweiliarticle/><div class=image-container><img src=../images/news/ZiweilLi-fig4.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/ziweiliarticle/>Neural Networks as Geometric Chaotic Maps - by Ziwei Li</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/articleyuval/><div class=image-container><img src=../images/news/yuval-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/articleyuval/>Neural network parametrization of a subgrid process - by Janni Yuval and Paul O'Gorman</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/articlejamescall/><div class=image-container><img src=../images/news/Yuval-article.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/articlejamescall/>Article in Eos by Yuval et al. - Call for Papers on Machine Learning and Earth System Modeling</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/oneworld/><div class=image-container><img src=../images/news/OneWorldseminar.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/oneworld/>Upcoming Seminar by Laure Zanna at One World Mathematics of Climate - 7/6</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/willgregorypaper/><div class=image-container><img src=../images/news/WillGregory-figure1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/willgregorypaper/>A Bayesian approach towards sea ice freeboard estimates - paper by Will Gregory</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/s2schallenge/><div class=image-container><img src=../images/news/ML_model_schematic.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/s2schallenge/>s2s challenge</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/kitpconference/><div class=image-container><img src=../images/news/climate-c21-logo.jpg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/kitpconference/>KITP conference: Machine Learning for Climate</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/cesmworkshop/><div class=image-container><img src=../images/news/cesm-workshop-2021.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/cesmworkshop/>2021 CESM workshop: M²LInES team members presenting on June 17th</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/5jamescall/><div class=image-container><img src=../images/news/JAMEScall.jpeg class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/5jamescall/>Call for Papers for JAMES</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/3gentinepaper1/><div class=image-container><img src=../images/news/Pierrepaper1-fig1.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/3gentinepaper1/>Using deep learning to emulate cloud superparameterization - new paper by PI Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/4gentinepaper2/><div class=image-container><img src=../images/news/Pierrepaper2-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/4gentinepaper2/>Neural Network emulating physical constraints - paper by PI Gentine</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/1guillauminpaper/><div class=image-container><img src=../images/news/Arthur-fig2.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/1guillauminpaper/>New paper on deep learning parametrization by Guillaumin and Zanna</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class="work-image item"><a href=../news/2jlesommerpaper/><div class=image-container><img src=../images/news/Julien-fig3.png class=responsive-image-container></div></a></div><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/2jlesommerpaper/>Modelisation using neural network - paper by PI Le Sommer</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div><div class="col-12 col-md-6 mb-1"><div class="work work-summary responsive-widget"><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/news/newsletters/>Newsletters</a></h2></div></div><style>.responsive-image-container{width:auto;height:auto;display:flex;max-width:100%;max-height:calc(40vh - 100px);padding-top:calc(17vh - 100px)}.responsive-image{width:auto;height:100%;max-height:100%}.responsive-widget{height:20vw;display:flex;align-items:center;overflow:hidden}.image-container{margin:0 auto}</style></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
 <a href=https://twitter.com/M2LInES target=blank><img src=../images/twitter.svg title=Twitter alt=Twitter></a>
 <a href=https://github.com/m2lines target=blank><img src=../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/news/index.xml b/news/index.xml
index b1730fcd3..ad9883168 100644
--- a/news/index.xml
+++ b/news/index.xml
@@ -1,4 +1,4 @@
-<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>News on M²LInES</title><link>https://m2lines.github.io/news/</link><description>Recent content in News on M²LInES</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Wed, 03 Apr 2024 09:29:16 +1000</lastBuildDate><atom:link href="https://m2lines.github.io/news/index.xml" rel="self" type="application/rss+xml"/><item><title>Advances in Machine Learning Techniques for Sea Ice Applications</title><link>https://m2lines.github.io/news/2404zampieri/</link><pubDate>Wed, 03 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404zampieri/</guid><description>Forty-two international researchers, including Lorenzo Zampieri, were invited to Gwangmyeong (South Korea) to discuss recent advances in sea ice modelling to help guide the development of a state-of-the-art Korean sea ice modelling program under the leadership of the Korean Polar Research Institute (KOPRI). The workshop produced a report , which highlights 1) the opportunity to use AI techniques in support of various sea ice modelling tasks both for short-term and climate predictions and 2) the need for strengthened collaborations among international groups to connect existing “research bubbles” and facilitate the dissemination of ideas.</description></item><item><title>Joint Parameter and Parameterization Inference by Yongquan</title><link>https://m2lines.github.io/news/2404qu/</link><pubDate>Tue, 02 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404qu/</guid><description>In this article , Yongquan Qu, Mohamed Aziz Bhouri, and Pierre Gentine, tackle the joint inference and uncertainty quantification of poorly known physical parameters and machine learning parametrizations, for sub-grid scale dynamics. Achieved through a Bayesian framework enabled by differentiable programming, this method not only offers accurate parameter estimates, but also enables skillful forecasting, each accompanied by quantified uncertainty. This work is accepted at the ICLR 2024 Workshop on AI4Differential Equations In Science.</description></item><item><title>Building Ocean Climate Emulators by Adam</title><link>https://m2lines.github.io/news/2404adam/</link><pubDate>Mon, 01 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404adam/</guid><description>AI can accelerate climate modeling by generating computationally cheap emulators of existing simulations. The design of climate emulators is an exciting and open challenge in AI+Climate. In this work , PhD student Adam Subel and Laure Zanna focus on two fundamental questions to facilitate the creation of ocean emulators: 1) the role of the atmosphere in improving the decadal skill of the emulator and 2) the representation of variables with distinct timescales (e.</description></item><item><title>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</title><link>https://m2lines.github.io/news/2402bhouri/</link><pubDate>Sat, 03 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402bhouri/</guid><description>Machine Learning (ML)-based parameterizations of atmospheric convection have long been hailed as a promising alternative, with the potential to yield higher accuracy at a fraction of the cost of more explicit simulations. This work , co-authored by Mohamed Aziz Bhouri, investigates the coupled out-of-distribution extrapolation capabilities in &amp;ldquo;online&amp;rdquo; testing of different ML-based parameterization designs of atmospheric convection. Their results show that these design decisions are not enough to obtain satisfactory generalization benefits.</description></item><item><title>Stochastic Optimal Control Matching by Joan</title><link>https://m2lines.github.io/news/2402joan/</link><pubDate>Fri, 02 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402joan/</guid><description>Joan Bruna is a co-author in this preprint , introducing Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control. Stochastic optimal control’s goal is to drive the behavior of noisy systems. In this work, the control is learned via a least squares problem by trying to fit a matching vector field. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that is of independent interest, e.</description></item><item><title>Restratification Effect of Mesoscale Eddies by Noora</title><link>https://m2lines.github.io/news/2402noora/</link><pubDate>Thu, 01 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402noora/</guid><description>Nora Loose is lead author of this new paper - part of the Climate Process Team funded by NSF and NOAA - which compares two parameterizations (“GM90” and “GL90”) for the restratification effect of mesoscale eddies. The authors conclude that the less commonly used GL90 parameterization is a promising alternative to the popular GM90 scheme for isopycnal coordinate models, where it is more consistent with theory, computationally more efficient, easier to implement, and numerically more stable.</description></item><item><title>Data-driven equation discovery ocean model by Pavel</title><link>https://m2lines.github.io/news/2401pavel/</link><pubDate>Tue, 02 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401pavel/</guid><description>Pavel Perezhogin is lead author of this new M²LInES preprint , describing the implementation, in the GFDL MOM6 ocean model, of a data-driven equation-discovery parameterization of mesoscale eddies. This scale-aware parametrization improved biases in the mean flow and energetics for a range of resolutions and in different ocean configurations. The work was done in collaboration with Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda and Laure Zanna.</description></item><item><title>Learning Machine Learning with Lorenz-96</title><link>https://m2lines.github.io/news/2401l96/</link><pubDate>Mon, 01 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401l96/</guid><description>The M²LInES team is proud to share our Jupyter Book on Learning Machine Learning with Lorenz-96 . This educational tool provides a computationally accessible framework to understand how machine learning techniques can tackle climate science problems, including emulators, parameterizations, data assimilation, and uncertainty quantification. It is for all climate scientists wanting to learn or test machine learning algorithms or for machine learning experts to learn about climate modeling or develop new algorithms.</description></item><item><title>ClimSim awarded Best Paper Award at NeurIPS</title><link>https://m2lines.github.io/news/2312climsim/</link><pubDate>Tue, 12 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312climsim/</guid><description>ClimSim has been awarded Best Paper Award at NeurIPS ! The open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators, emerged out of the Science and Technology Center LEAP, received contributions from numerous M²LInES members. Congratulations to all authors!</description></item><item><title>Will Gregory's latest article featured in Advance Science News</title><link>https://m2lines.github.io/news/2312willgfeature/</link><pubDate>Fri, 01 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312willgfeature/</guid><description>The latest M²LInES article, led by Will Gregory (Princeton) is being featured in Advance Science News. The article details how Will and other colleagues, including M²LInES members Mitch Bushuk, Alistair Adcroft, and Laure Zanna, are using Machine Learning to enhance predictions of Arctic sea ice loss. Read the article by Giorgio Graffino here</description></item><item><title>OceanBench by J. Emmanuel Johnson</title><link>https://m2lines.github.io/news/2311johnson/</link><pubDate>Wed, 01 Nov 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2311johnson/</guid><description>OceanBench is a suite of tools for designing experiments relevant to the oceanography community like interpolation, forecasting and estimation. Lead author J. Emmanuel Johnson and co-authors, including Anastasiia Gorbunova and Julien Le Sommer, demonstrate its use within a benchmark setting for sea surface height interpolation, using general circulation model simulations and real satellite observations.</description></item><item><title>UNetKF by Feiyu Lu</title><link>https://m2lines.github.io/news/2310lu/</link><pubDate>Tue, 03 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310lu/</guid><description>This study by Feiyu Lu incorporates deep learning methods to compliment and improve the ensemble Kalman filter data assimilation algorithm. More specifically, a convolutional neural network is trained to predict the error statistics of a model ensemble, which will reduce the computational costs of the ensemble Kalman filter. This approach is tested in a quasi-geostrophic dynamic model to demonstrate its feasibility in more advanced weather and climate applications.</description></item><item><title>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</title><link>https://m2lines.github.io/news/2310bhouri/</link><pubDate>Mon, 02 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310bhouri/</guid><description>In this preprint , Mohamed Aziz Bhouri and co-authors, including Pierre Gentine, developed a probabilistic multi-fidelity atmospheric parameterization for heat and moisture tendency. They implemented it on CESM CAM5 and SPCAM5 data and showed its capabilities to well extrapolate to unseen warmer climate simulations while returning trustworthy uncertainty quantification.</description></item><item><title>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</title><link>https://m2lines.github.io/news/2310chapman/</link><pubDate>Sun, 01 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310chapman/</guid><description>Stochastic and deterministic tendency adjustments are applied to multiple experiments in the community atmosphere model version 6. The tendency adjustments are gleaned from the DART data assimilation system and a linear relaxation towards ERA-interim reanalysis. In this preprint , Will Chapman and Judith Berner show that the tendency adjustment significantly enhances the representation of the background state climatology for key prognostic and surface variables. Additionally, they show that stochastic tendencies are essential to accurately represent model variability of major atmospheric modes when making tendency adjustments.</description></item><item><title> Blog Post - A New Generation of Climate Models</title><link>https://m2lines.github.io/news/2309blogpost/</link><pubDate>Mon, 11 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309blogpost/</guid><description>M²LInES can now demonstrate the impact of data-driven Machine Learning parameterizations in global models! 🌎You can read about new gen climate models with AI in our blog post</description></item><item><title>New climate simulation model ensemble by Marika Holland</title><link>https://m2lines.github.io/news/2309holland/</link><pubDate>Mon, 04 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309holland/</guid><description>Climate simulation uncertainties arise from internal variability, model structure, and external forcings. These uncertainty sources are difficult to disentangle across model generations because both model structure and external forcings typically change. This preprint , led by Marika Holland, presents new ensemble simulations which allow for the separation of uncertainty sources between two large ensembles (LEs) of the Community Earth System Model (CESM). Importantly, we find a strong influence of historical forcing uncertainty in differences between CESM1-LE and CESM2-LE due to aerosol effects on simulated climate.</description></item><item><title>Understanding Extreme Precipitation Changes by Griffin Mooers</title><link>https://m2lines.github.io/news/2309mooers/</link><pubDate>Sun, 03 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309mooers/</guid><description>Griffin Mooers is lead author in this preprint that leverages Variational Autoencoders on SPCAM5 output to examine the changes in the upper quantiles of precipitation between a control and warmed simulation. They find intense precipitation changes are mostly controlled by spatial shifts in deep convection.</description></item><item><title>Reliable coarse-grained turbulent simulations by Chris Pederson</title><link>https://m2lines.github.io/news/2309pederson/</link><pubDate>Sat, 02 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309pederson/</guid><description>In this preprint , M²LInES postdoc Chris Pedersen, along with Pavel Perezhogin, Joan Bruna, and Laure Zanna, show that the standard offline learning paradigm used to produce ML models of unresolved dynamics can be complemented with some learned time evolution of the system, and produce more stable hybrid physics and ML models.</description></item><item><title>Background Pycnocline depth constrains FOHUE by Emily Newsom</title><link>https://m2lines.github.io/news/2308newsom/</link><pubDate>Thu, 03 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308newsom/</guid><description>In this paper , Emily Newsom and co-authors Laure Zanna and Jonathan Gregory, showed that the relative depth of ocean heat sequestration, which varies widely across climate models and paces the rate of surface climate warming, is strongly correlated to interior ocean stratification. Using a novel regional decomposition method, they showed that this relationship is entirely driven by mid-latitude ventilation processes and explains 70% of the variance in heat penetration depth across CMIP5/CMIP6 models.</description></item><item><title>ClimSim: LEAP publication</title><link>https://m2lines.github.io/news/2308bhouri/</link><pubDate>Wed, 02 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308bhouri/</guid><description>Several of M²LInES members and affiliates (Bhouri, Gentine, Zanna, Abernathey, Busecke, Mooers, Shamekh, and Yuval) have contributed to this LEAP paper presenting ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. The data and code are open access.</description></item><item><title>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</title><link>https://m2lines.github.io/news/2308shamekh/</link><pubDate>Tue, 01 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308shamekh/</guid><description>This preprint , by Sara Shamekh and Pierre Gentine, proposes a novel data-driven parameterization of vertical turbulent fluxes in convective boundary layer, that models the fluxes of various scalars across turbulent regimes. By incorporating a physics-based constraint this approach allows us to decompose the total vertical flux into two main modes of variability based on large scale forces that control the turbulence in the atmosphere.</description></item><item><title>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</title><link>https://m2lines.github.io/news/2307sane/</link><pubDate>Sat, 01 Jul 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2307sane/</guid><description>Small scale vertical mixing processes in the upper ocean region cannot be resolved by ocean models due to the lack of computing resources, and are thus parameterized. Existing models have a few ad hoc approximations which cause uncertainty in climate change simulations. In this breakthrough preprint , Aakash Sane and co-authors - Brandon Reichl, Alistair Adcroft, and Laure Zanna - replace such an approximation using data driven neural networks (NN), leading to improved physics in an ocean model simulation and a reduction of model bias in the Tropics.</description></item><item><title>Smart correction model for winter sky temperatures by Lorenzo Zampieri</title><link>https://m2lines.github.io/news/2306zampieri/</link><pubDate>Thu, 01 Jun 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2306zampieri/</guid><description>This study , led by Lorenzo Zampieri, and co-authored by Marika Holland, illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea-ice-covered regions of the Arctic under clear-sky conditions. The corrected reanalysis temperature can be employed to support polar research activities, and in particular to better simulate the evolution of the interacting sea ice and ocean system within numerical models.</description></item><item><title>Data-driven subgrid parameterizations by Karl Otness</title><link>https://m2lines.github.io/news/2305otness/</link><pubDate>Mon, 01 May 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2305otness/</guid><description>In this ongoing project , Karl Otness and co-authors are evaluating a proof of concept multiscale approach to predicting subgrid forcings in climate models. They see encouraging preliminary results from first making a prediction in a fine-to-coarse direction which yields a lower resolution, but more confident prediction followed by a refinement to predict finer scale details.
+<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>News on M²LInES</title><link>https://m2lines.github.io/news/</link><description>Recent content in News on M²LInES</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Thu, 02 May 2024 09:29:16 +1000</lastBuildDate><atom:link href="https://m2lines.github.io/news/index.xml" rel="self" type="application/rss+xml"/><item><title>FTORCH and FORPY libraries now integrated to CESM!</title><link>https://m2lines.github.io/news/2405chapman/</link><pubDate>Thu, 02 May 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2405chapman/</guid><description>The M²LInES team, assisted by Jack Atkinson (ICCS) and NCAR software engineers, have integrated the FTORCH and FORPY libraries for machine learning into CESM2.1.5. To set up a machine learning-enabled CESM instance on NCAR machines, follow the steps outlined in this repository . Contact Will Chapman for questions!</description></item><item><title>Predicting September Arctic Sea Ice by Dr. Bushuk</title><link>https://m2lines.github.io/news/2405bushuk/</link><pubDate>Wed, 01 May 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2405bushuk/</guid><description>This study , led by Mitch Bushuk, provides a comparison of September Arctic sea ice seasonal prediction skill across a diverse set of 34 dynamical and statistical prediction models, quantifying the state-of-the-art in the rapidly growing sea ice prediction research community. The authors find that both dynamical and statistical prediction models can skillfully predict September Arctic sea ice 0–3 months in advance on Pan-Arctic, regional, and local spatial scales. These results demonstrate that there are bright prospects for skillful operational seasonal predictions of Arctic sea ice and highlight a number of crucial prediction system design aspects to guide future improvements.</description></item><item><title>Advances in Machine Learning Techniques for Sea Ice Applications</title><link>https://m2lines.github.io/news/2404zampieri/</link><pubDate>Wed, 03 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404zampieri/</guid><description>Forty-two international researchers, including Lorenzo Zampieri, were invited to Gwangmyeong (South Korea) to discuss recent advances in sea ice modelling to help guide the development of a state-of-the-art Korean sea ice modelling program under the leadership of the Korean Polar Research Institute (KOPRI). The workshop produced a report , which highlights 1) the opportunity to use AI techniques in support of various sea ice modelling tasks both for short-term and climate predictions and 2) the need for strengthened collaborations among international groups to connect existing “research bubbles” and facilitate the dissemination of ideas.</description></item><item><title>Joint Parameter and Parameterization Inference by Yongquan</title><link>https://m2lines.github.io/news/2404qu/</link><pubDate>Tue, 02 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404qu/</guid><description>In this article , Yongquan Qu, Mohamed Aziz Bhouri, and Pierre Gentine, tackle the joint inference and uncertainty quantification of poorly known physical parameters and machine learning parametrizations, for sub-grid scale dynamics. Achieved through a Bayesian framework enabled by differentiable programming, this method not only offers accurate parameter estimates, but also enables skillful forecasting, each accompanied by quantified uncertainty. This work is accepted at the ICLR 2024 Workshop on AI4Differential Equations In Science.</description></item><item><title>Building Ocean Climate Emulators by Adam</title><link>https://m2lines.github.io/news/2404adam/</link><pubDate>Mon, 01 Apr 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2404adam/</guid><description>AI can accelerate climate modeling by generating computationally cheap emulators of existing simulations. The design of climate emulators is an exciting and open challenge in AI+Climate. In this work , PhD student Adam Subel and Laure Zanna focus on two fundamental questions to facilitate the creation of ocean emulators: 1) the role of the atmosphere in improving the decadal skill of the emulator and 2) the representation of variables with distinct timescales (e.</description></item><item><title>Stress-testing the coupled behavior of hybrid physics-machine simulations by Bhouri</title><link>https://m2lines.github.io/news/2402bhouri/</link><pubDate>Sat, 03 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402bhouri/</guid><description>Machine Learning (ML)-based parameterizations of atmospheric convection have long been hailed as a promising alternative, with the potential to yield higher accuracy at a fraction of the cost of more explicit simulations. This work , co-authored by Mohamed Aziz Bhouri, investigates the coupled out-of-distribution extrapolation capabilities in &amp;ldquo;online&amp;rdquo; testing of different ML-based parameterization designs of atmospheric convection. Their results show that these design decisions are not enough to obtain satisfactory generalization benefits.</description></item><item><title>Stochastic Optimal Control Matching by Joan</title><link>https://m2lines.github.io/news/2402joan/</link><pubDate>Fri, 02 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402joan/</guid><description>Joan Bruna is a co-author in this preprint , introducing Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control. Stochastic optimal control’s goal is to drive the behavior of noisy systems. In this work, the control is learned via a least squares problem by trying to fit a matching vector field. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that is of independent interest, e.</description></item><item><title>Restratification Effect of Mesoscale Eddies by Noora</title><link>https://m2lines.github.io/news/2402noora/</link><pubDate>Thu, 01 Feb 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2402noora/</guid><description>Nora Loose is lead author of this new paper - part of the Climate Process Team funded by NSF and NOAA - which compares two parameterizations (“GM90” and “GL90”) for the restratification effect of mesoscale eddies. The authors conclude that the less commonly used GL90 parameterization is a promising alternative to the popular GM90 scheme for isopycnal coordinate models, where it is more consistent with theory, computationally more efficient, easier to implement, and numerically more stable.</description></item><item><title>Data-driven equation discovery ocean model by Pavel</title><link>https://m2lines.github.io/news/2401pavel/</link><pubDate>Tue, 02 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401pavel/</guid><description>Pavel Perezhogin is lead author of this new M²LInES preprint , describing the implementation, in the GFDL MOM6 ocean model, of a data-driven equation-discovery parameterization of mesoscale eddies. This scale-aware parametrization improved biases in the mean flow and energetics for a range of resolutions and in different ocean configurations. The work was done in collaboration with Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda and Laure Zanna.</description></item><item><title>Learning Machine Learning with Lorenz-96</title><link>https://m2lines.github.io/news/2401l96/</link><pubDate>Mon, 01 Jan 2024 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2401l96/</guid><description>The M²LInES team is proud to share our Jupyter Book on Learning Machine Learning with Lorenz-96 . This educational tool provides a computationally accessible framework to understand how machine learning techniques can tackle climate science problems, including emulators, parameterizations, data assimilation, and uncertainty quantification. It is for all climate scientists wanting to learn or test machine learning algorithms or for machine learning experts to learn about climate modeling or develop new algorithms.</description></item><item><title>ClimSim awarded Best Paper Award at NeurIPS</title><link>https://m2lines.github.io/news/2312climsim/</link><pubDate>Tue, 12 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312climsim/</guid><description>ClimSim has been awarded Best Paper Award at NeurIPS ! The open large-scale dataset for training high-resolution physics emulators in hybrid multi-scale climate simulators, emerged out of the Science and Technology Center LEAP, received contributions from numerous M²LInES members. Congratulations to all authors!</description></item><item><title>Will Gregory's latest article featured in Advance Science News</title><link>https://m2lines.github.io/news/2312willgfeature/</link><pubDate>Fri, 01 Dec 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2312willgfeature/</guid><description>The latest M²LInES article, led by Will Gregory (Princeton) is being featured in Advance Science News. The article details how Will and other colleagues, including M²LInES members Mitch Bushuk, Alistair Adcroft, and Laure Zanna, are using Machine Learning to enhance predictions of Arctic sea ice loss. Read the article by Giorgio Graffino here</description></item><item><title>OceanBench by J. Emmanuel Johnson</title><link>https://m2lines.github.io/news/2311johnson/</link><pubDate>Wed, 01 Nov 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2311johnson/</guid><description>OceanBench is a suite of tools for designing experiments relevant to the oceanography community like interpolation, forecasting and estimation. Lead author J. Emmanuel Johnson and co-authors, including Anastasiia Gorbunova and Julien Le Sommer, demonstrate its use within a benchmark setting for sea surface height interpolation, using general circulation model simulations and real satellite observations.</description></item><item><title>UNetKF by Feiyu Lu</title><link>https://m2lines.github.io/news/2310lu/</link><pubDate>Tue, 03 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310lu/</guid><description>This study by Feiyu Lu incorporates deep learning methods to compliment and improve the ensemble Kalman filter data assimilation algorithm. More specifically, a convolutional neural network is trained to predict the error statistics of a model ensemble, which will reduce the computational costs of the ensemble Kalman filter. This approach is tested in a quasi-geostrophic dynamic model to demonstrate its feasibility in more advanced weather and climate applications.</description></item><item><title>Multi-fidelity climate model parameterization by Mohamed Aziz Bhouri</title><link>https://m2lines.github.io/news/2310bhouri/</link><pubDate>Mon, 02 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310bhouri/</guid><description>In this preprint , Mohamed Aziz Bhouri and co-authors, including Pierre Gentine, developed a probabilistic multi-fidelity atmospheric parameterization for heat and moisture tendency. They implemented it on CESM CAM5 and SPCAM5 data and showed its capabilities to well extrapolate to unseen warmer climate simulations while returning trustworthy uncertainty quantification.</description></item><item><title>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</title><link>https://m2lines.github.io/news/2310chapman/</link><pubDate>Sun, 01 Oct 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2310chapman/</guid><description>Stochastic and deterministic tendency adjustments are applied to multiple experiments in the community atmosphere model version 6. The tendency adjustments are gleaned from the DART data assimilation system and a linear relaxation towards ERA-interim reanalysis. In this preprint , Will Chapman and Judith Berner show that the tendency adjustment significantly enhances the representation of the background state climatology for key prognostic and surface variables. Additionally, they show that stochastic tendencies are essential to accurately represent model variability of major atmospheric modes when making tendency adjustments.</description></item><item><title> Blog Post - A New Generation of Climate Models</title><link>https://m2lines.github.io/news/2309blogpost/</link><pubDate>Mon, 11 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309blogpost/</guid><description>M²LInES can now demonstrate the impact of data-driven Machine Learning parameterizations in global models! 🌎You can read about new gen climate models with AI in our blog post</description></item><item><title>New climate simulation model ensemble by Marika Holland</title><link>https://m2lines.github.io/news/2309holland/</link><pubDate>Mon, 04 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309holland/</guid><description>Climate simulation uncertainties arise from internal variability, model structure, and external forcings. These uncertainty sources are difficult to disentangle across model generations because both model structure and external forcings typically change. This preprint , led by Marika Holland, presents new ensemble simulations which allow for the separation of uncertainty sources between two large ensembles (LEs) of the Community Earth System Model (CESM). Importantly, we find a strong influence of historical forcing uncertainty in differences between CESM1-LE and CESM2-LE due to aerosol effects on simulated climate.</description></item><item><title>Understanding Extreme Precipitation Changes by Griffin Mooers</title><link>https://m2lines.github.io/news/2309mooers/</link><pubDate>Sun, 03 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309mooers/</guid><description>Griffin Mooers is lead author in this preprint that leverages Variational Autoencoders on SPCAM5 output to examine the changes in the upper quantiles of precipitation between a control and warmed simulation. They find intense precipitation changes are mostly controlled by spatial shifts in deep convection.</description></item><item><title>Reliable coarse-grained turbulent simulations by Chris Pederson</title><link>https://m2lines.github.io/news/2309pederson/</link><pubDate>Sat, 02 Sep 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2309pederson/</guid><description>In this preprint , M²LInES postdoc Chris Pedersen, along with Pavel Perezhogin, Joan Bruna, and Laure Zanna, show that the standard offline learning paradigm used to produce ML models of unresolved dynamics can be complemented with some learned time evolution of the system, and produce more stable hybrid physics and ML models.</description></item><item><title>Background Pycnocline depth constrains FOHUE by Emily Newsom</title><link>https://m2lines.github.io/news/2308newsom/</link><pubDate>Thu, 03 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308newsom/</guid><description>In this paper , Emily Newsom and co-authors Laure Zanna and Jonathan Gregory, showed that the relative depth of ocean heat sequestration, which varies widely across climate models and paces the rate of surface climate warming, is strongly correlated to interior ocean stratification. Using a novel regional decomposition method, they showed that this relationship is entirely driven by mid-latitude ventilation processes and explains 70% of the variance in heat penetration depth across CMIP5/CMIP6 models.</description></item><item><title>ClimSim: LEAP publication</title><link>https://m2lines.github.io/news/2308bhouri/</link><pubDate>Wed, 02 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308bhouri/</guid><description>Several of M²LInES members and affiliates (Bhouri, Gentine, Zanna, Abernathey, Busecke, Mooers, Shamekh, and Yuval) have contributed to this LEAP paper presenting ClimSim, the largest-ever dataset designed for hybrid ML-physics research. It comprises multi-scale climate simulations, global in coverage, spans multiple years at high sampling frequency, and is designed such that resulting emulators are compatible with downstream coupling into operational climate simulators. The data and code are open access.</description></item><item><title>Learning Atmospheric Boundary Layer Turbulence by Sara Shamekh</title><link>https://m2lines.github.io/news/2308shamekh/</link><pubDate>Tue, 01 Aug 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2308shamekh/</guid><description>This preprint , by Sara Shamekh and Pierre Gentine, proposes a novel data-driven parameterization of vertical turbulent fluxes in convective boundary layer, that models the fluxes of various scalars across turbulent regimes. By incorporating a physics-based constraint this approach allows us to decompose the total vertical flux into two main modes of variability based on large scale forces that control the turbulence in the atmosphere.</description></item><item><title>Parameterizing vertical mixing coefficients in the Ocean by Akash Sane</title><link>https://m2lines.github.io/news/2307sane/</link><pubDate>Sat, 01 Jul 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2307sane/</guid><description>Small scale vertical mixing processes in the upper ocean region cannot be resolved by ocean models due to the lack of computing resources, and are thus parameterized. Existing models have a few ad hoc approximations which cause uncertainty in climate change simulations. In this breakthrough preprint , Aakash Sane and co-authors - Brandon Reichl, Alistair Adcroft, and Laure Zanna - replace such an approximation using data driven neural networks (NN), leading to improved physics in an ocean model simulation and a reduction of model bias in the Tropics.</description></item><item><title>Smart correction model for winter sky temperatures by Lorenzo Zampieri</title><link>https://m2lines.github.io/news/2306zampieri/</link><pubDate>Thu, 01 Jun 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2306zampieri/</guid><description>This study , led by Lorenzo Zampieri, and co-authored by Marika Holland, illustrates a novel method based on machine learning for reducing the systematic surface temperature errors that characterize multiple atmospheric reanalyses in sea-ice-covered regions of the Arctic under clear-sky conditions. The corrected reanalysis temperature can be employed to support polar research activities, and in particular to better simulate the evolution of the interacting sea ice and ocean system within numerical models.</description></item><item><title>Data-driven subgrid parameterizations by Karl Otness</title><link>https://m2lines.github.io/news/2305otness/</link><pubDate>Mon, 01 May 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2305otness/</guid><description>In this ongoing project , Karl Otness and co-authors are evaluating a proof of concept multiscale approach to predicting subgrid forcings in climate models. They see encouraging preliminary results from first making a prediction in a fine-to-coarse direction which yields a lower resolution, but more confident prediction followed by a refinement to predict finer scale details.
 This paper won “Best ML innovation” at the ICLR 2023 Workshop: Tackling Climate Change with Machine Learning.</description></item><item><title>Emulating Cloud Superparameterization by Pierre Gentine</title><link>https://m2lines.github.io/news/2301gentine/</link><pubDate>Tue, 03 Jan 2023 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2301gentine/</guid><description>M²LInES PI Pierre Gentine is the senior author in this new publication on using deep learning for emulating cloud superparameterization in climate models. Research Scientist Tom Beucler is a co-author. Read their paper here</description></item><item><title> M²LInES at AGU 22</title><link>https://m2lines.github.io/news/2212agu22/</link><pubDate>Tue, 06 Dec 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2212agu22/</guid><description>AGU M²LInES Highlights The M²LInES team is excited to present our recent scientific advances at the Fall 2022 AGU meeting in Chicago and online. Below is a summary of the talks (all times are CST). For your convenience, you can download the schedule for the talks by following this link .
 Machine learning for physics discovery &amp;amp; modeling We have an extensive lineup of talks and posters from M²LInES team members and affiliates.</description></item><item><title> Direct observational evidence of an oceanic dual kinetic energy cascade and its seasonality</title><link>https://m2lines.github.io/news/2211balwada/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211balwada/</guid><description>In this article , led by Dhruv Balwada, ocean drifter observations show wave and turbulence merge and split flows, simultaneously transferring energy to large and small scales.</description></item><item><title> Implicit learning of convective organization explains precipitation stochasticity</title><link>https://m2lines.github.io/news/2211shamekh/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211shamekh/</guid><description>Cloud and convection take many structure and degrees of organization, which are still absent in most parameterizations. But does that structure matter for precipitation? This preprint , led by Sara Shamekh, proposes an elegant method to include organization in the parameterization of precipitation that results in a significant improvement in predicting precipitation, especially extremes, at GCM scale.</description></item><item><title> Ocean currents break up a tabular iceberg</title><link>https://m2lines.github.io/news/2211adcroft/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211adcroft/</guid><description>This article examines the mechanism that led to the breakup of massive iceberg A68 in Dec 2020. The authors, including Alistair Adcroft, demonstrate that the A68a breakup event may have been triggered by ocean-current shear, a new breakup mechanism not previously reported. Their paper was featured in the news .</description></item><item><title> On Gradient Descent Convergence beyond the Edge of Stability</title><link>https://m2lines.github.io/news/2211bruna/</link><pubDate>Thu, 03 Nov 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2211bruna/</guid><description>Joan Bruna is the senior author in this preprint on Gradient Descent (GD) convergence in unstable conditions. The study examines the conditions for such unstable convergence, focusing on simple, yet representative, learning problems.</description></item><item><title> A year-round satellite sea-ice thickness record from CryoSat-2</title><link>https://m2lines.github.io/news/2210bushuk/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210bushuk/</guid><description>This study , co-authored by Mitch Bushuk, produced the first ever year-round satellite observational record of Arctic sea ice thickness, employing a deep learning model to produce estimates of sea ice freeboard. These data span the period 2010-2020 and will be critical for better monitoring the changing Arctic climate, advancing climate model evaluation, and improving sea ice predictions.</description></item><item><title> Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning</title><link>https://m2lines.github.io/news/2210gentine/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210gentine/</guid><description>High resolution data is overwhelming and this paper , co-authored by Pierre Gentine and Tom Beucler, tries to define an unsupervised machine learning technique to better compare Storm Resolving Climate Models (SRMs). Their analysis found that only six out of nine considered SRMs are dynamically consistent. This split among SRMs highlights the need to further investigate sub-grid parameterization choices.</description></item><item><title> Semi-automatic tuning of coupled climate models with multiple intrinsic timescales</title><link>https://m2lines.github.io/news/2210deshayes/</link><pubDate>Mon, 03 Oct 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2210deshayes/</guid><description>Using the two-scale Lorenz96 model, this article evaluates the potential of History Matching to tune a climate system with multi-scale dynamics. This semi-automatic tuning was more efficient when combined with physical expertise. Julie Deshayes and V Balaji are co-authors on this study.</description></item><item><title> Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</title><link>https://m2lines.github.io/news/2208ross/</link><pubDate>Tue, 02 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208ross/</guid><description>In this work , led by Andrew Ross, with Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda and Laure Zanna, we provide a framework for systematically benchmarking the offline and online performance of physical and ML-based subgrid parameterizations. We find that the choice of filtering operator is critical for performance. To help with interpretability, we also propose a novel equation-discovery approach combining linear regression and genetic programming which generalizes better than physical and neural network parameterizations.</description></item><item><title> Cloud-based framework for inter-comparing submesoscale permitting realistic ocean models</title><link>https://m2lines.github.io/news/2208uchida/</link><pubDate>Mon, 01 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208uchida/</guid><description>This study presents a cloud-based workflow for intercomparing high-resolution ocean models and provides an assessment of one of the most used parameterizations of ocean submesoscales. Julien Le Sommer, Ryan Abernathey, and Aurelie Albert contributed to the research.</description></item><item><title> Non-Linear Dimensionality Reduction with a VED to Understand Convective Processes in Climate Models</title><link>https://m2lines.github.io/news/2208behrens/</link><pubDate>Mon, 01 Aug 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2208behrens/</guid><description>Pierre Gentine and Tom Beucler are co-authors in this article , which demonstrates that Variational Encoder Decoder structures (VED) are capable of learning and accurately reproducing convective processes in an aquaplanet superparameterized climate model simulation, while enabling interpretability and better understanding of sub-grid-scale physical processes.</description></item><item><title> A potential energy analysis of ocean surface mixed layers - Brandon Reichl</title><link>https://m2lines.github.io/news/2207reichl/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207reichl/</guid><description>Analysis of the ocean mixed layer requires one to estimate its vertical extent, for which there are various definitions. In this paper , Brandon Reichl and co-authors, including Alistair Adcroft, show that using the potential energy anomaly to identify the mixed layer depth is practical and it offers conceptual benefits by directly linking to the physics of upper ocean vertical mixing.</description></item><item><title> New preprint led by Adam Subel on transfer learning</title><link>https://m2lines.github.io/news/2207subel/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207subel/</guid><description>Adam Subel is the lead author in this article , which builds a framework to understand and implement transfer learning, a powerful machine learning technique for enabling generalization between datasets from different configurations of a system or of varying quality/quantity, in multiscale physical systems.</description></item><item><title> Subseasonal Earth System Prediction with CESM2 - Judith Berner</title><link>https://m2lines.github.io/news/2207berner/</link><pubDate>Tue, 05 Jul 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/2207berner/</guid><description>Judith Berner is a co-author in this article , which describes the design and prediction skill of two subseasonal prediction systems based on two configurations of the Community Earth System Model, version 2 (CESM2): with the Community Atmosphere Model and with Whole Atmosphere Community Climate Model as its atmospheric component. Both systems are compared to NOAA CFSv2 and ECMWF.</description></item><item><title> Deep Learning for Subgrid-Scale Turbulence Modeling in LES of the Convective Atmospheric Boundary Layer</title><link>https://m2lines.github.io/news/gentine-abernathey/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/gentine-abernathey/</guid><description>This article , co-authored by Pierre Gentine and Ryan Abernathey, replaces the typically used physically based assumptions with deep learning in subgrid-scale modeling, in large eddy simulations of turbulence. They show that the latter performs better in a priori (offline) tests of atmospheric turbulence. The deep neural networks model also captures key statistics of turbulence in a posteriori (online) tests.</description></item><item><title> Lorenzo Zampieri - A machine learning correction model</title><link>https://m2lines.github.io/news/zampieri2022/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/zampieri2022/</guid><description>Lorenzo Zampieri et al. illustrate in this preprint , a novel method based on ML for reducing the surface temperature errors of atmospheric reanalyses in sea-ice-covered regions of the Arctic. The corrected temperature can be employed to support polar research activities, and to better simulate the evolution of the interacting sea ice and ocean systems in numerical models.</description></item><item><title> Will Gregory - Network connectivity article</title><link>https://m2lines.github.io/news/gregory2022/</link><pubDate>Tue, 07 Jun 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/gregory2022/</guid><description>Will Gregory and co-authors hypothesized in this publication that regional biases in sea ice thickness may hinder the ability of CMIP6 models to reproduce an important atmospheric driver of summer sea ice variability, and hence their ability to make reliable sea ice predictions on seasonal to inter-annual time scales.</description></item><item><title> 2022 CESM workshop: Info and submission deadline</title><link>https://m2lines.github.io/news/cesmworkshop2022/</link><pubDate>Mon, 02 May 2022 09:29:16 +1000</pubDate><guid>https://m2lines.github.io/news/cesmworkshop2022/</guid><description>Registration is open for the 2022 CESM Workshop on June 13-16, 2022. Please visit the website to register as well as submit working group session talks and /or posters. The deadline to submit a talk / poster is Monday, May 16th.
 The full workshop agenda can be found here .
diff --git a/news/newsletters/index.html b/news/newsletters/index.html
index c3cc3c11b..4cffbc392 100644
--- a/news/newsletters/index.html
+++ b/news/newsletters/index.html
@@ -9,6 +9,6 @@
 <input type=checkbox id=News><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../news/><span class=menu__text>Our news</span></a></li><li class="menu__item menu__item--active"><a class=menu__link href=../../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
 <span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style=background-image:url(/images/andrew-dunstan-qdUDnCjo7e0-unsplash.jpeg)><div class=container><div class=hero-text><span class=hero-section></span><h1>Newsletters</h1><p></p></div></div></div><div class="container pt-6 pt-md-5"><div class=row><div id=mc_embed_signup><form action="https://github.us1.list-manage.com/subscribe/post?u=c81830f2905baad1c7b2d8c8b&id=5b8c433eb4" method=post id=mc-embedded-subscribe-form name=mc-embedded-subscribe-form class=validate target=_blank novalidate><div id=mc_embed_signup_scroll><h2>Subscribe to our newsletter</h2><div class=indicates-required><span class=asterisk>*</span> indicates required</div><div class=mc-field-group><label for=mce-EMAIL>Email Address <span class=asterisk>*</span></label>
 <input type=email name=EMAIL class="required email" id=mce-EMAIL></div><div class=mc-field-group><label for=mce-NAME>Name (Optional)</label>
-<input type=text name=NAME id=mce-NAME></div><div id=mce-responses class=clear><div class=response id=mce-error-response style=display:none></div><div class=response id=mce-success-response style=display:none></div></div><div style=position:absolute;left:-5000px aria-hidden=true><input type=text name=b_c81830f2905baad1c7b2d8c8b_5b8c433eb4 tabindex=-1></div><div class=clear><input type=submit value=Subscribe name=subscribe id=mc-embedded-subscribe class=button></div></div></form></div></div></div><div class="container pt-3 pt-md-10"><div class=row><div class=col-12><div class=page-intro><p>Links to our past newsletters are below.</p><h3 id=2024>2024</h3><ul><li><p>04/01/2024 - <a href=https://mailchi.mp/e8da3716350c/m2lines-april24-newsletter target=_blank>M²LInES newsletter - April 2024</a></p></li><li><p>02/16/2024 - <a href=https://mailchi.mp/98cf4196cd4a/m2lines-newsletter-osm24 target=_blank>M²LInES newsletter - Special Ocean Sciences Meeting</a></p></li><li><p>02/01/2024 - <a href=https://mailchi.mp/149196c77c09/m2lines-feburary-2024 target=_blank>M²LInES newsletter - Feburary 2024</a></p></li><li><p>01/08/2024 - <a href=https://mailchi.mp/688f6e69dc60/m2lines-january-2024 target=_blank>M²LInES newsletter - January 2024</a></p></li></ul><h3 id=2023>2023</h3><ul><li><p>12/01/2023 - <a href=https://mailchi.mp/7d7642df21e6/m2lines-december-newsletter-agu target=_blank>M²LInES newsletter - December 2023 - Special AGU</a></p></li><li><p>11/02/2023 - <a href=https://mailchi.mp/6be77812991b/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2023</a></p></li><li><p>10/04/2023 - <a href=https://mailchi.mp/09855c01b0d3/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2023</a></p></li><li><p>09/06/2023 - <a href=https://mailchi.mp/77c1eded6eb6/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2023</a></p></li><li><p>08/01/2023 - <a href=https://mailchi.mp/8afe52c0433c/m2lines-august23-newsletter target=_blank>M²LInES newsletter - August 2023</a></p></li><li><p>07/03/2023 - <a href=https://mailchi.mp/7c514e163b6e/m2lines-july23-newsletter target=_blank>M²LInES newsletter - July 2023</a></p></li><li><p>06/13/2023 - <a href=https://mailchi.mp/3e13c2d1b09e/m2lines-june2023-newsletter target=_blank>M²LInES newsletter - June 2023</a></p></li><li><p>05/11/2023 - <a href=https://mailchi.mp/89ec798d18b2/m2lines-may2023-newsletter target=_blank>M²LInES newsletter - May 2023</a></p></li><li><p>01/03/2023 - <a href=https://mailchi.mp/5b801dd5a61a/m2lines-newsletter-january-2023 target=_blank>M²LInES newsletter - January 2023</a></p></li></ul><h3 id=2022>2022</h3><ul><li><p>12/05/2022 - <a href=https://mailchi.mp/169d6f0c61f9/m2lines-december-newsletter-agu-special target=_blank>M²LInES newsletter - December 2022 AGU Special</a></p></li><li><p>11/01/2022 - <a href=https://mailchi.mp/ea5545ba3ad9/m2lines-newsletter-november-2022 target=_blank>M²LInES newsletter - November 2022</a></p></li><li><p>10/03/2022 - <a href=https://mailchi.mp/1b79e3c3f118/m2lines-newsletter-october-2022 target=_blank>M²LInES newsletter - October 2022</a></p></li><li><p>09/16/2022 - <a href=https://mailchi.mp/23f67eb58497/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2022 Research Roundup</a></p></li><li><p>08/01/2022 - <a href=https://mailchi.mp/de41e2fa4f3a/m2lines-august-2022 target=_blank>M²LInES newsletter - August 2022</a></p></li><li><p>07/05/2022 - <a href=https://mailchi.mp/559244aacd7f/m2lines-july-newsletter target=_blank>M²LInES newsletter - July 2022</a></p></li><li><p>06/06/2022 - <a href=https://mailchi.mp/b6ce90c1f066/m2lines-june-2022-newsletter target=_blank>M²LInES newsletter - June 2022</a></p></li><li><p>05/02/2022 - <a href=https://mailchi.mp/f1f185fede51/m2lines-may2022 target=_blank>M²LInES newsletter - May 2022</a></p></li><li><p>04/01/2022 - <a href=https://mailchi.mp/2db4ee09fcf6/m2lines-april-2022-newsletter target=_blank>M²LInES newsletter - April 2022</a></p></li><li><p>02/24/2022 - <a href=https://mailchi.mp/11a5a98d21a3/m2lines-newsletter-osm22 target=_blank>M²LInES newsletter - OSM22 special</a></p></li><li><p>02/01/2022 - <a href=https://mailchi.mp/cb9b5c06b78c/m2lines-february-2022 target=_blank>M²LInES newsletter - February 2022</a></p></li><li><p>01/01/2022 - <a href=https://mailchi.mp/a57b46b053b0/m2lines-january-2022 target=_blank>M²LInES newsletter - January 2022</a></p></li></ul><h3 id=2021>2021</h3><ul><li><p>12/01/2021 - <a href=https://mailchi.mp/29ddfae980e7/m2lines-december-newsletter target=_blank>M²LInES newsletter - December 2021 AGU special</a></p></li><li><p>11/01/2021 - <a href=https://mailchi.mp/5ae317faf7e4/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2021</a></p></li><li><p>10/01/2021 - <a href=https://mailchi.mp/c3af749bf3ea/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2021</a></p></li><li><p>09/01/2021 - <a href=https://mailchi.mp/51a1b976f492/m2lines-newsletter target=_blank>M²LInES newsletter - September 2021</a></p></li><li><p>08/02/2021 - <a href=https://mailchi.mp/6c353c6991e5/m2lines-august-newsletter target=_blank>M²LInES newsletter - August 2021</a></p></li><li><p>06/29/2021 - <a href=https://mailchi.mp/1fabec1cb5be/m2lines target=_blank>M²LInES newsletter - June/July 2021</a></p></li></ul></div></div></div></div><div class="container pb-3 pt-3 pb-md-5 pt-md-5"><div class=row></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+<input type=text name=NAME id=mce-NAME></div><div id=mce-responses class=clear><div class=response id=mce-error-response style=display:none></div><div class=response id=mce-success-response style=display:none></div></div><div style=position:absolute;left:-5000px aria-hidden=true><input type=text name=b_c81830f2905baad1c7b2d8c8b_5b8c433eb4 tabindex=-1></div><div class=clear><input type=submit value=Subscribe name=subscribe id=mc-embedded-subscribe class=button></div></div></form></div></div></div><div class="container pt-3 pt-md-10"><div class=row><div class=col-12><div class=page-intro><p>Links to our past newsletters are below.</p><h3 id=2024>2024</h3><ul><li><p>05/01/2024 - <a href=https://mailchi.mp/04a341e92442/m2lines-may-2024 target=_blank>M²LInES newsletter - May 2024</a></p></li><li><p>04/01/2024 - <a href=https://mailchi.mp/e8da3716350c/m2lines-april24-newsletter target=_blank>M²LInES newsletter - April 2024</a></p></li><li><p>02/16/2024 - <a href=https://mailchi.mp/98cf4196cd4a/m2lines-newsletter-osm24 target=_blank>M²LInES newsletter - Special Ocean Sciences Meeting</a></p></li><li><p>02/01/2024 - <a href=https://mailchi.mp/149196c77c09/m2lines-feburary-2024 target=_blank>M²LInES newsletter - Feburary 2024</a></p></li><li><p>01/08/2024 - <a href=https://mailchi.mp/688f6e69dc60/m2lines-january-2024 target=_blank>M²LInES newsletter - January 2024</a></p></li></ul><h3 id=2023>2023</h3><ul><li><p>12/01/2023 - <a href=https://mailchi.mp/7d7642df21e6/m2lines-december-newsletter-agu target=_blank>M²LInES newsletter - December 2023 - Special AGU</a></p></li><li><p>11/02/2023 - <a href=https://mailchi.mp/6be77812991b/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2023</a></p></li><li><p>10/04/2023 - <a href=https://mailchi.mp/09855c01b0d3/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2023</a></p></li><li><p>09/06/2023 - <a href=https://mailchi.mp/77c1eded6eb6/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2023</a></p></li><li><p>08/01/2023 - <a href=https://mailchi.mp/8afe52c0433c/m2lines-august23-newsletter target=_blank>M²LInES newsletter - August 2023</a></p></li><li><p>07/03/2023 - <a href=https://mailchi.mp/7c514e163b6e/m2lines-july23-newsletter target=_blank>M²LInES newsletter - July 2023</a></p></li><li><p>06/13/2023 - <a href=https://mailchi.mp/3e13c2d1b09e/m2lines-june2023-newsletter target=_blank>M²LInES newsletter - June 2023</a></p></li><li><p>05/11/2023 - <a href=https://mailchi.mp/89ec798d18b2/m2lines-may2023-newsletter target=_blank>M²LInES newsletter - May 2023</a></p></li><li><p>01/03/2023 - <a href=https://mailchi.mp/5b801dd5a61a/m2lines-newsletter-january-2023 target=_blank>M²LInES newsletter - January 2023</a></p></li></ul><h3 id=2022>2022</h3><ul><li><p>12/05/2022 - <a href=https://mailchi.mp/169d6f0c61f9/m2lines-december-newsletter-agu-special target=_blank>M²LInES newsletter - December 2022 AGU Special</a></p></li><li><p>11/01/2022 - <a href=https://mailchi.mp/ea5545ba3ad9/m2lines-newsletter-november-2022 target=_blank>M²LInES newsletter - November 2022</a></p></li><li><p>10/03/2022 - <a href=https://mailchi.mp/1b79e3c3f118/m2lines-newsletter-october-2022 target=_blank>M²LInES newsletter - October 2022</a></p></li><li><p>09/16/2022 - <a href=https://mailchi.mp/23f67eb58497/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2022 Research Roundup</a></p></li><li><p>08/01/2022 - <a href=https://mailchi.mp/de41e2fa4f3a/m2lines-august-2022 target=_blank>M²LInES newsletter - August 2022</a></p></li><li><p>07/05/2022 - <a href=https://mailchi.mp/559244aacd7f/m2lines-july-newsletter target=_blank>M²LInES newsletter - July 2022</a></p></li><li><p>06/06/2022 - <a href=https://mailchi.mp/b6ce90c1f066/m2lines-june-2022-newsletter target=_blank>M²LInES newsletter - June 2022</a></p></li><li><p>05/02/2022 - <a href=https://mailchi.mp/f1f185fede51/m2lines-may2022 target=_blank>M²LInES newsletter - May 2022</a></p></li><li><p>04/01/2022 - <a href=https://mailchi.mp/2db4ee09fcf6/m2lines-april-2022-newsletter target=_blank>M²LInES newsletter - April 2022</a></p></li><li><p>02/24/2022 - <a href=https://mailchi.mp/11a5a98d21a3/m2lines-newsletter-osm22 target=_blank>M²LInES newsletter - OSM22 special</a></p></li><li><p>02/01/2022 - <a href=https://mailchi.mp/cb9b5c06b78c/m2lines-february-2022 target=_blank>M²LInES newsletter - February 2022</a></p></li><li><p>01/01/2022 - <a href=https://mailchi.mp/a57b46b053b0/m2lines-january-2022 target=_blank>M²LInES newsletter - January 2022</a></p></li></ul><h3 id=2021>2021</h3><ul><li><p>12/01/2021 - <a href=https://mailchi.mp/29ddfae980e7/m2lines-december-newsletter target=_blank>M²LInES newsletter - December 2021 AGU special</a></p></li><li><p>11/01/2021 - <a href=https://mailchi.mp/5ae317faf7e4/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2021</a></p></li><li><p>10/01/2021 - <a href=https://mailchi.mp/c3af749bf3ea/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2021</a></p></li><li><p>09/01/2021 - <a href=https://mailchi.mp/51a1b976f492/m2lines-newsletter target=_blank>M²LInES newsletter - September 2021</a></p></li><li><p>08/02/2021 - <a href=https://mailchi.mp/6c353c6991e5/m2lines-august-newsletter target=_blank>M²LInES newsletter - August 2021</a></p></li><li><p>06/29/2021 - <a href=https://mailchi.mp/1fabec1cb5be/m2lines target=_blank>M²LInES newsletter - June/July 2021</a></p></li></ul></div></div></div></div><div class="container pb-3 pt-3 pb-md-5 pt-md-5"><div class=row></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
 <a href=https://twitter.com/M2LInES target=blank><img src=../../images/twitter.svg title=Twitter alt=Twitter></a>
 <a href=https://github.com/m2lines target=blank><img src=../../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/publications/index.html b/publications/index.html
index 806fcf7aa..a7a6ae43c 100644
--- a/publications/index.html
+++ b/publications/index.html
@@ -8,7 +8,7 @@
 <label class=drop-icon for=News>▾</label></a>
 <input type=checkbox id=News><ul class=submenu__list><li class=menu__item><a class=menu__link href=../news/><span class=menu__text>Our news</span></a></li><li class=menu__item><a class=menu__link href=../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
 <span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div id=hero class="hero-image hero-image-setheight" style=background-image:url(/images/susan-q-yin-2JIvboGLeho-unsplash.jpg)><div class=container><div class=hero-text><span class=hero-section></span><h1>Publications</h1><p>Research work and relevant papers by our team</p></div></div></div><div class="container pt-6 pt-md-10"><div class=row><div class=col-12><div class=page-intro><h2 id=mlines-research-publications>M²LInES research publications</h2><p>If you are interested in understanding how M²LInES is using machine learning to improve climate models, we have developed an educational JupyterBook <a href=https://m2lines.github.io/L96_demo target=_blank>Learning Machine Learning for Climate modeling with Lorenz 96</a>
-. This JupyterBook describes the key research themes in M²LInES, through the use of a simple climate model and machine learning algorithms. You can run the notebooks yourself, contribute to the development of the JupyterBook or let us know what you think on GitHub <a href=https://github.com/m2lines/L96_demo>https://github.com/m2lines/L96_demo</a>.</p><h3 id=2024>2024</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/al_24.png style=width:100px;height:100px></div><p><strong>Adam Subel, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Building Ocean Climate Emulators</strong></a><br><i>ICLR 2024 Workshop: Tackling Climate Change with Machine Learning.</i> <strong>DOI</strong>: 10.48550/arXiv.2402.04342</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/wmy_24.png style=width:100px;height:100px></div><p><strong>William Gregory, Mitchell Bushuk, Yongfei Zhang, Alistair Adcroft, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Machine Learning for Online Sea Ice Bias Correction Within Global Ice-Ocean Simulations</strong></a><br><i>Geophysical Research Letters 2024.</i> <strong>DOI</strong>: 10.1029/2023GL106776</p></div><h3 id=2023>2023</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pca_24.png style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2311.02517><strong>Implementation of a data-driven equation-discovery mesoscale parameterization into an ocean mode</strong></a><br><i>James 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2311.02517</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/bdst_23.png style=width:100px;height:100px></div><p><strong>Will Chapman and Judith Berner</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</strong></a><br><i>ArXiv 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2308.15295</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/rcts_23.png style=width:100px;height:100px></div><p><strong>Christian Pedersen, Laure Zanna, Joan Bruna, Pavel Perezhogin</strong><br><a href=https://arxiv.org/abs/2307.13144><strong>Reliable coarse-grained turbulent simulations through combined offline learning and neural emulation</strong></a><br><i>ICML 2023 Workshop on Synergy of Scientific and Machine Learning Modeling</i> <strong>DOI</strong>: 10.48550/arXiv.2307.13144</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/bpdc_23.png style=width:100px;height:100px></div><p><strong>Emily Newsom, Laure Zanna, Jonathan Gregory</strong><br><a href=https://arxiv.org/abs/2307.11902><strong>Background Pycnocline depth constrains Future Ocean Heat Uptake Efficiency</strong></a><br><i>AGU Geophysical Research Letters 2023.</i> <strong>DOI</strong>: 10.1029/2023GL105673</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/cisc_23.png style=width:100px;height:100px></div><p><strong>Fabrizio Falasca, Pavel Perezhogin, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2306.14433><strong>A data-driven framework for dimensionality reduction and causal inference in climate fields</strong></a><br><i>ArXiv 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2306.14433</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/labl_23.png style=width:100px;height:100px></div><p><strong>Sara Shamekh and Pierre Gentine</strong><br><a href=https://essopenarchive.org/doi/full/10.22541/essoar.168748456.60017486><strong>Learning Atmospheric Boundary Layer Turbulence</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.22541/essoar.168748456.60017486/v1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pvmc_23.png style=width:100px;height:100px></div><p><strong>Aakash Sane, Brandon G. Reichl, Alistair Adcroft, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003890><strong>Parameterizing vertical mixing coefficients in the Ocean
-Surface Boundary Layer using Neural Networks</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003890</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/climsim_23.png style=width:100px;height:100px></div><p><strong>Sungduk Yu, ..., Michael S. Pritchard<br></strong><a href=https://doi.org/10.48550/arXiv.2306.08754><strong>ClimSim: An open large-scale dataset for training high-resolution physics emulators in hybrid<br>multi-scale climate simulators</strong></a><br><i>ArXiv 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2306.08754</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/lces_23.png style=width:100px;height:100px></div><p><strong>Karan Jakhar, Yifei Guan, Rambod Mojgani, Ashesh Chattopadhyay, Pedram Hassanzadeh, Laure Zanna</strong><br><a href=https://doi.org/10.22541/essoar.168677212.21341231/v1><strong>Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges.</strong></a><br><i>ESS Open Archive. 2023.</i> <strong>DOI</strong>: 10.22541/essoar.168677212.21341231/v1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dcre_23.png style=width:100px;height:100px></div><p><strong>Gustau Camps-Valls, Andreas Gerhardus, Urmi Ninad, Gherardo Varando, Georg Martius,<br>Emili Balaguer-Ballester, Ricardo Vinuesa, Emiliano Diaz, Laure Zanna, Jakob Runge</strong><br><a href=https://doi.org/10.1016/j.physrep.2023.10.005><strong>Discovering Causal Relations and Equations from Data.</strong></a><br><i>Physics Reports 2023.</i> <strong>DOI</strong>: 10.1016/j.physrep.2023.10.005</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/hwnh_23.png style=width:100px;height:100px></div><p><strong>Rei Chemke and Janni Yuval</strong><br><a href=https://www.nature.com/articles/s41586-023-05903-1><strong>Human-induced weakening of the Northern Hemisphere tropical circulation</strong></a><br><i>Nature. 2023.</i> <strong>DOI</strong>: 10.1038/s41586-023-05903-1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Gregory_et_al.2023.png style=width:100px;height:100px></div><p><strong>William Gregory, Mitchell Bushuk, Alistair Adcroft, Yongfei Zhang, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003757><strong>Deep learning of systematic sea ice model errors from data assimilation increments</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003757</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/nnps_23.png style=width:100px;height:100px></div><p><strong>Janni Yuval and Paul A. O’Gorman</strong><br><a href=https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2023MS003606><strong>Neural-Network Parameterization of Subgrid Momentum Transport in the Atmosphere</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003606</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dmms_23.png style=width:100px;height:100px></div><p><strong>Karl Otness, Laure Zanna, Joan Bruna</strong><br><a href=https://www.climatechange.ai/papers/iclr2023/60><strong>Data-driven multiscale modeling of subgrid parameterizations in climate models</strong></a><br><i>arXiv:2303.17496. Preprint submitted to ICLR Workshop on Climate Change AI. 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2303.17496</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/encs_23.png style=width:100px;height:100px></div><p><strong>Fabrizio Falasca, Andrew Brettin, Laure Zanna, Stephen M. Griffies, Jianjun Yin, Ming Zhao</strong><br><a href=https://arxiv.org/abs/2211.04608><strong>Exploring the non-stationarity of coastal sea level probability distributions</strong></a><br><i>arxiv.org:2211.04608. Preprint submitted to EDS. 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2211.04608</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Perezhogin_eddy.gif style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Laure Zanna, Carlos Fernandez-Granda</strong><br><a href=https://doi.org/10.1029/2023MS003681><strong>Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003681</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Perezhogin_eddy.gif style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Andrey Glazunov</strong><br><a href=https://doi.org/10.1029/2023MS003771><strong>Subgrid Parameterizations of Ocean Mesoscale Eddies Based on Germano Decomposition</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003771</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2208-Ross.png style=width:100px;height:100px></div><p><strong>Andrew Ross, Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2022MS003258><strong>Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2022MS003258</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/0523-Chengetal.png style=width:100px;height:100px></div><p><strong>Cheng Zhang, Pavel Perezhogin, Cem Gultekin, Alistair Adcroft, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003697><strong>Implementation and Evaluation of a Machine Learned Mesoscale Eddy Parameterization into a<br>Numerical Ocean Circulation Model</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003697</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/rsks_23.png style=width:100px;height:100px></div><p><strong>Qiyu Xiao, Dhruv Balwada, C. Spencer Jones, Mario Herrero-Gonzalez, K. Shafer Smith, Ryan Abernathey</strong><br><a href=https://essopenarchive.org/users/595672/articles/629531-reconstruction-of-surface-kinematics-from-sea-surface-height-using-neural-networks)><strong>Reconstruction of Surface Kinematics from Sea Surface Height Using Neural Networks</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2022MS003258</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Uchida2023.jpg style=width:100px;height:100px></div><p><strong>Takaya Uchida, Dhruv Balwada, Quentin Jamet, William K. Dewar, Bruno Deremble,<br>Thierry Penduff, Julien Le Sommer</strong><br><a href=https://www.sciencedirect.com/science/article/abs/pii/S1463500323000136?via%3Dihub)><strong>Cautionary tales from the mesoscale eddy transport tensor</strong></a><br><i>ScienceDirect 2023.</i> <strong>DOI</strong>: 10.1016/j.ocemod.2023.102172</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2207-Subel.png style=width:100px;height:100px></div><p><strong>Adam Subel, Yifei Guan, Ashesh Chattopadhyay, Pedram Hassanzadeh</strong><br><a href=https://academic.oup.com/pnasnexus/article/2/3/pgad015/6998042)><strong>Explaining the physics of transfer learning in data-driven turbulence modeling</strong></a><br><i>PNAS NEXUS 2023.</i> <strong>DOI</strong>: 10.1093/pnasnexus/pgad015</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/0623-Zampieri.jpg style=width:100px;height:100px></div><p><strong>Lorenzo Zampieri, Gabriele Arduini, Marika Holland, Sarah Keeley, Kristian S. Mogensen,<br>Matthew D. Shupe, Steffen Tietsche</strong><br><a href=https://doi.org/10.1002/essoar.10511269.1><strong>A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses</strong></a><br><i>AMS Journals, Monthy Weather Review: volume151, issue6</i> <strong>DOI</strong>: 10.1175/MWR-D-22-0130.1</p></div><br><h3 id=2022>2022</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2204-Bruna.png style=width:100px;height:100px></div><p><strong>Joan Bruna, Benjamin Peherstorfer, Eric Vanden-Eijnden</strong><br><a href=https://doi.org/10.1016/j.jcp.2023.112588><strong>Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations</strong></a><br><i>Journal of Computational Physics</i> <strong>DOI</strong>: 10.1016/j.jcp.2023.112588</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/npas_23.png style=width:100px;height:100px></div><p><strong>Peidong Wang, Janni Yuval, Paul A. O'Gorman</strong><br><a href=https://doi.org/10.1029/2022MS002984><strong>Non-local parameterization of atmospheric subgrid processes with neural networks</strong></a><br><i>JAMES 2022.</i> <strong>DOI</strong>: 10.1029/2022MS002984</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2211Shamekh.png style=width:100px;height:100px></div><p><strong>Sara Shamekh, Kara D Lamb, Yu Huang, Pierre Gentine</strong><br><a href=https://doi.org/10.1002/essoar.10512517.1><strong>Implicit learning of convective organization explains precipitation stochasticity</strong></a><br><i>In review. 2022.</i> <strong>DOI</strong>: 10.1002/essoar.10512517.1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pwcm_22.png style=width:100px;height:100px></div><p><strong>Hannah Christensen and Laure Zanna</strong><br><a href=https://doi.org/10.1093/acrefore/9780190228620.013.826><strong>Parametrization in Weather and Climate Models</strong></a><br><i>Oxford Research Encyclopedia of Climate Science. 2022.</i> <strong>DOI</strong>: 10.1093/acrefore/9780190228620.013.826</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dpe_22.png style=width:100px;height:100px></div><p><strong>Sheng Liu, Aakash Kaku, Haoxiang Huang, Laure Zanna, Weicheng Zhu, Narges Razavian,<br>Matan Leibovich, Sreyas Mohan, Boyang Yu, Jonathan Niles-Weed, Carlos Fernandez-Granda</strong><br><a href=https://proceedings.mlr.press/v162/liu22f/liu22f.pdf><strong>Deep Probability Estimation</strong></a><br><i>Proceedings of the 39th International Conference on Machine Learning, PMLR 162:13746-13781, 2022.</i><br><strong>DOI</strong>: 10.48550/arXiv.2111.10734</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/GCMfilters.png style=width:100px;height:100px></div><p><strong>Nora Loose, Ryan Abernathey, Ian Grooms, Julius Busecke, Arthur Guillaumin,<br>Elizabeth Yankovsky, Gustavo Marques, Jacob Steinberg, Andrew Slavin Ross, Hemant Khatri,<br>Scott Bachman, Laure Zanna, Paige Martin</strong><br><a href=https://doi.org/10.21105/joss.03947><strong>GCM-Filters: A Python Package for Diffusion-based Spatial Filtering of Gridded Data</strong></a><br><i>Journal of Open Source Software 7(70), p.3947. 2022.</i> <strong>DOI</strong>: 10.21105/joss.03947</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/aplq_22.png style=width:100px;height:100px></div><p><strong>Hugo Frezat, Julien Le Sommer, Ronan Fablet, Guillaume Balarac, Redouane Lguensat</strong><br><a href=https://doi.org/10.1029/2022MS003124><strong>A posteriori learning for quasi-geostrophic turbulence parametrization</strong></a><br><i>JAMES. 2022.</i> <strong>DOI</strong>: 10.1029/2022MS003124</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/ogdc_22.png style=width:100px;height:100px></div><p><strong>Lei Chen and Joan Bruna</strong><br><a href=https://doi.org/10.48550/arXiv.2206.04172><strong>On Gradient Descent Convergence beyond the Edge of Stability</strong></a><br><i>ArXiv 2022</i> <strong>DOI</strong>: 10.48550/arXiv.2206.04172</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/hbcs_22.png style=width:100px;height:100px></div><p><strong>Mohamed Aziz Bhouri and Pierre Gentine</strong><br><a href=https://arxiv.org/abs/2210.14488><strong>History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96</strong></a><br><i>ArXiv 2022.</i> <strong>DOI</strong>: 10.48550/arXiv.2210.14488</p></div></div></div></div></div><div class="container pb-6 pt-6 pb-md-10 pt-md-10"><div class=row><div class="col-12 col-md-6 mb-2"><div class="work work-summary"><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/publications/archive/>Publications Archive</a></h2><h3 id=2021-->2021 -</h3><ul><li><p>Guillaumin, A. P., & Zanna, L. <strong><a href=https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021MS002534 target=_blank>Stochastic-Deep Learning Parameterization of Ocean Momentum Forcing</a></strong> JAMES...</p></li></ul></div></div></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+. This JupyterBook describes the key research themes in M²LInES, through the use of a simple climate model and machine learning algorithms. You can run the notebooks yourself, contribute to the development of the JupyterBook or let us know what you think on GitHub <a href=https://github.com/m2lines/L96_demo>https://github.com/m2lines/L96_demo</a>.</p><h3 id=2024>2024</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/al_24.png style=width:100px;height:100px></div><p><strong>Adam Subel, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Building Ocean Climate Emulators</strong></a><br><i>ICLR 2024 Workshop: Tackling Climate Change with Machine Learning.</i> <strong>DOI</strong>: 10.48550/arXiv.2402.04342</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/wmy_24.png style=width:100px;height:100px></div><p><strong>William Gregory, Mitchell Bushuk, Yongfei Zhang, Alistair Adcroft, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Machine Learning for Online Sea Ice Bias Correction Within Global Ice-Ocean Simulations</strong></a><br><i>Geophysical Research Letters 2024.</i> <strong>DOI</strong>: 10.1029/2023GL106776</p></div><h3 id=2023>2023</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pca_24.png style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Cheng Zhang, Alistair Adcroft, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2311.02517><strong>Implementation of a data-driven equation-discovery mesoscale parameterization into an ocean mode</strong></a><br><i>James 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003697</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/bdst_23.png style=width:100px;height:100px></div><p><strong>Will Chapman and Judith Berner</strong><br><a href=https://arxiv.org/abs/2308.15295><strong>Benefits of Deterministic and Stochastic Tendency Adjustments in a Climate Model</strong></a><br><i>ArXiv 2023.</i> <strong>DOI</strong>: 10.1002/qj.4652</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/rcts_23.png style=width:100px;height:100px></div><p><strong>Christian Pedersen, Laure Zanna, Joan Bruna, Pavel Perezhogin</strong><br><a href=https://arxiv.org/abs/2307.13144><strong>Reliable coarse-grained turbulent simulations through combined offline learning and neural emulation</strong></a><br><i>ICML 2023 Workshop on Synergy of Scientific and Machine Learning Modeling</i> <strong>DOI</strong>: 10.48550/arXiv.2307.13144</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/bpdc_23.png style=width:100px;height:100px></div><p><strong>Emily Newsom, Laure Zanna, Jonathan Gregory</strong><br><a href=https://arxiv.org/abs/2307.11902><strong>Background Pycnocline depth constrains Future Ocean Heat Uptake Efficiency</strong></a><br><i>AGU Geophysical Research Letters 2023.</i> <strong>DOI</strong>: 10.1029/2023GL105673</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/cisc_23.png style=width:100px;height:100px></div><p><strong>Fabrizio Falasca, Pavel Perezhogin, Laure Zanna</strong><br><a href=https://arxiv.org/abs/2306.14433><strong>Data-driven framework for dimensionality reduction and causal inference in climate fields</strong></a><br><i>APS Physics Review E 2024</i> <strong>DOI</strong>: 10.1103/PhysRevE.109.044202</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/labl_23.png style=width:100px;height:100px></div><p><strong>Sara Shamekh and Pierre Gentine</strong><br><a href=https://essopenarchive.org/doi/full/10.22541/essoar.168748456.60017486><strong>Learning Atmospheric Boundary Layer Turbulence</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.22541/essoar.168748456.60017486/v1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pvmc_23.png style=width:100px;height:100px></div><p><strong>Aakash Sane, Brandon G. Reichl, Alistair Adcroft, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003890><strong>Parameterizing vertical mixing coefficients in the Ocean
+Surface Boundary Layer using Neural Networks</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003890</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/climsim_23.png style=width:100px;height:100px></div><p><strong>Sungduk Yu, ..., Michael S. Pritchard<br></strong><a href=https://doi.org/10.48550/arXiv.2306.08754><strong>ClimSim: An open large-scale dataset for training high-resolution physics emulators in hybrid<br>multi-scale climate simulators</strong></a><br><i>ArXiv 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2306.08754</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/lces_23.png style=width:100px;height:100px></div><p><strong>Karan Jakhar, Yifei Guan, Rambod Mojgani, Ashesh Chattopadhyay, Pedram Hassanzadeh, Laure Zanna</strong><br><a href=https://doi.org/10.22541/essoar.168677212.21341231/v1><strong>Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges.</strong></a><br><i>ESS Open Archive. 2023.</i> <strong>DOI</strong>: 10.22541/essoar.168677212.21341231/v1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dcre_23.png style=width:100px;height:100px></div><p><strong>Gustau Camps-Valls, Andreas Gerhardus, Urmi Ninad, Gherardo Varando, Georg Martius,<br>Emili Balaguer-Ballester, Ricardo Vinuesa, Emiliano Diaz, Laure Zanna, Jakob Runge</strong><br><a href=https://doi.org/10.1016/j.physrep.2023.10.005><strong>Discovering Causal Relations and Equations from Data.</strong></a><br><i>Physics Reports 2023.</i> <strong>DOI</strong>: 10.1016/j.physrep.2023.10.005</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/hwnh_23.png style=width:100px;height:100px></div><p><strong>Rei Chemke and Janni Yuval</strong><br><a href=https://www.nature.com/articles/s41586-023-05903-1><strong>Human-induced weakening of the Northern Hemisphere tropical circulation</strong></a><br><i>Nature. 2023.</i> <strong>DOI</strong>: 10.1038/s41586-023-05903-1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Gregory_et_al.2023.png style=width:100px;height:100px></div><p><strong>William Gregory, Mitchell Bushuk, Alistair Adcroft, Yongfei Zhang, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003757><strong>Deep learning of systematic sea ice model errors from data assimilation increments</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003757</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/nnps_23.png style=width:100px;height:100px></div><p><strong>Janni Yuval and Paul A. O’Gorman</strong><br><a href=https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2023MS003606><strong>Neural-Network Parameterization of Subgrid Momentum Transport in the Atmosphere</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003606</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dmms_23.png style=width:100px;height:100px></div><p><strong>Karl Otness, Laure Zanna, Joan Bruna</strong><br><a href=https://www.climatechange.ai/papers/iclr2023/60><strong>Data-driven multiscale modeling of subgrid parameterizations in climate models</strong></a><br><i>arXiv:2303.17496. Preprint submitted to ICLR Workshop on Climate Change AI. 2023.</i> <strong>DOI</strong>: 10.48550/arXiv.2303.17496</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/encs_23.png style=width:100px;height:100px></div><p><strong>Fabrizio Falasca, Andrew Brettin, Laure Zanna, Stephen M. Griffies, Jianjun Yin, Ming Zhao</strong><br><a href=https://arxiv.org/abs/2211.04608><strong>Exploring the non-stationarity of coastal sea level probability distributions</strong></a><br><i>EDS. volume 2 2023.</i> <strong>DOI</strong>: 10.1017/eds.2023.10</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Perezhogin_eddy.gif style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Laure Zanna, Carlos Fernandez-Granda</strong><br><a href=https://doi.org/10.1029/2023MS003681><strong>Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003681</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Perezhogin_eddy.gif style=width:100px;height:100px></div><p><strong>Pavel Perezhogin, Andrey Glazunov</strong><br><a href=https://doi.org/10.1029/2023MS003771><strong>Subgrid Parameterizations of Ocean Mesoscale Eddies Based on Germano Decomposition</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003771</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2208-Ross.png style=width:100px;height:100px></div><p><strong>Andrew Ross, Ziwei Li, Pavel Perezhogin, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2022MS003258><strong>Benchmarking of machine learning ocean subgrid parameterizations in an idealized model</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2022MS003258</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/0523-Chengetal.png style=width:100px;height:100px></div><p><strong>Cheng Zhang, Pavel Perezhogin, Cem Gultekin, Alistair Adcroft, Carlos Fernandez-Granda, Laure Zanna</strong><br><a href=https://doi.org/10.1029/2023MS003697><strong>Implementation and Evaluation of a Machine Learned Mesoscale Eddy Parameterization into a<br>Numerical Ocean Circulation Model</strong></a><br><i>JAMES 2023.</i> <strong>DOI</strong>: 10.1029/2023MS003697</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/rsks_23.png style=width:100px;height:100px></div><p><strong>Qiyu Xiao, Dhruv Balwada, C. Spencer Jones, Mario Herrero-Gonzalez, K. Shafer Smith, Ryan Abernathey</strong><br><a href=https://essopenarchive.org/users/595672/articles/629531-reconstruction-of-surface-kinematics-from-sea-surface-height-using-neural-networks)><strong>Reconstruction of Surface Kinematics from Sea Surface Height Using Neural Networks</strong></a><br><i>JAMES. 2023.</i> <strong>DOI</strong>: 10.1029/2022MS003258</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/Uchida2023.jpg style=width:100px;height:100px></div><p><strong>Takaya Uchida, Dhruv Balwada, Quentin Jamet, William K. Dewar, Bruno Deremble,<br>Thierry Penduff, Julien Le Sommer</strong><br><a href=https://www.sciencedirect.com/science/article/abs/pii/S1463500323000136?via%3Dihub)><strong>Cautionary tales from the mesoscale eddy transport tensor</strong></a><br><i>ScienceDirect 2023.</i> <strong>DOI</strong>: 10.1016/j.ocemod.2023.102172</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2207-Subel.png style=width:100px;height:100px></div><p><strong>Adam Subel, Yifei Guan, Ashesh Chattopadhyay, Pedram Hassanzadeh</strong><br><a href=https://academic.oup.com/pnasnexus/article/2/3/pgad015/6998042)><strong>Explaining the physics of transfer learning in data-driven turbulence modeling</strong></a><br><i>PNAS NEXUS 2023.</i> <strong>DOI</strong>: 10.1093/pnasnexus/pgad015</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/0623-Zampieri.jpg style=width:100px;height:100px></div><p><strong>Lorenzo Zampieri, Gabriele Arduini, Marika Holland, Sarah Keeley, Kristian S. Mogensen,<br>Matthew D. Shupe, Steffen Tietsche</strong><br><a href=https://doi.org/10.1002/essoar.10511269.1><strong>A Machine Learning Correction Model of the Winter Clear-Sky Temperature Bias over the Arctic Sea Ice in Atmospheric Reanalyses</strong></a><br><i>AMS Journals, Monthy Weather Review: volume151, issue6</i> <strong>DOI</strong>: 10.1175/MWR-D-22-0130.1</p></div><br><h3 id=2022>2022</h3><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2204-Bruna.png style=width:100px;height:100px></div><p><strong>Joan Bruna, Benjamin Peherstorfer, Eric Vanden-Eijnden</strong><br><a href=https://doi.org/10.1016/j.jcp.2023.112588><strong>Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations</strong></a><br><i>Journal of Computational Physics</i> <strong>DOI</strong>: 10.1016/j.jcp.2023.112588</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/npas_23.png style=width:100px;height:100px></div><p><strong>Peidong Wang, Janni Yuval, Paul A. O'Gorman</strong><br><a href=https://doi.org/10.1029/2022MS002984><strong>Non-local parameterization of atmospheric subgrid processes with neural networks</strong></a><br><i>JAMES 2022.</i> <strong>DOI</strong>: 10.1029/2022MS002984</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/2211Shamekh.png style=width:100px;height:100px></div><p><strong>Sara Shamekh, Kara D Lamb, Yu Huang, Pierre Gentine</strong><br><a href=https://doi.org/10.1002/essoar.10512517.1><strong>Implicit learning of convective organization explains precipitation stochasticity</strong></a><br><i>In review. 2022.</i> <strong>DOI</strong>: 10.1002/essoar.10512517.1</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/pwcm_22.png style=width:100px;height:100px></div><p><strong>Hannah Christensen and Laure Zanna</strong><br><a href=https://doi.org/10.1093/acrefore/9780190228620.013.826><strong>Parametrization in Weather and Climate Models</strong></a><br><i>Oxford Research Encyclopedia of Climate Science. 2022.</i> <strong>DOI</strong>: 10.1093/acrefore/9780190228620.013.826</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/dpe_22.png style=width:100px;height:100px></div><p><strong>Sheng Liu, Aakash Kaku, Haoxiang Huang, Laure Zanna, Weicheng Zhu, Narges Razavian,<br>Matan Leibovich, Sreyas Mohan, Boyang Yu, Jonathan Niles-Weed, Carlos Fernandez-Granda</strong><br><a href=https://proceedings.mlr.press/v162/liu22f/liu22f.pdf><strong>Deep Probability Estimation</strong></a><br><i>Proceedings of the 39th International Conference on Machine Learning, PMLR 162:13746-13781, 2022.</i><br><strong>DOI</strong>: 10.48550/arXiv.2111.10734</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/news/GCMfilters.png style=width:100px;height:100px></div><p><strong>Nora Loose, Ryan Abernathey, Ian Grooms, Julius Busecke, Arthur Guillaumin,<br>Elizabeth Yankovsky, Gustavo Marques, Jacob Steinberg, Andrew Slavin Ross, Hemant Khatri,<br>Scott Bachman, Laure Zanna, Paige Martin</strong><br><a href=https://doi.org/10.21105/joss.03947><strong>GCM-Filters: A Python Package for Diffusion-based Spatial Filtering of Gridded Data</strong></a><br><i>Journal of Open Source Software 7(70), p.3947. 2022.</i> <strong>DOI</strong>: 10.21105/joss.03947</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/aplq_22.png style=width:100px;height:100px></div><p><strong>Hugo Frezat, Julien Le Sommer, Ronan Fablet, Guillaume Balarac, Redouane Lguensat</strong><br><a href=https://doi.org/10.1029/2022MS003124><strong>A posteriori learning for quasi-geostrophic turbulence parametrization</strong></a><br><i>JAMES. 2022.</i> <strong>DOI</strong>: 10.1029/2022MS003124</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/ogdc_22.png style=width:100px;height:100px></div><p><strong>Lei Chen and Joan Bruna</strong><br><a href=https://doi.org/10.48550/arXiv.2206.04172><strong>On Gradient Descent Convergence beyond the Edge of Stability</strong></a><br><i>ArXiv 2022</i> <strong>DOI</strong>: 10.48550/arXiv.2206.04172</p></div><div style=display:flex;align-items:center><div style=width:100px;height:100px;overflow:hidden;margin-right:10px><img src=../images/publications/hbcs_22.png style=width:100px;height:100px></div><p><strong>Mohamed Aziz Bhouri and Pierre Gentine</strong><br><a href=https://arxiv.org/abs/2210.14488><strong>History-Based, Bayesian, Closure for Stochastic Parameterization: Application to Lorenz '96</strong></a><br><i>ArXiv 2022.</i> <strong>DOI</strong>: 10.48550/arXiv.2210.14488</p></div></div></div></div></div><div class="container pb-6 pt-6 pb-md-10 pt-md-10"><div class=row><div class="col-12 col-md-6 mb-2"><div class="work work-summary"><div class=work-content><h2 class=work-title><a href=https://m2lines.github.io/publications/archive/>Publications Archive</a></h2><h3 id=2021-->2021 -</h3><ul><li><p>Guillaumin, A. P., & Zanna, L. <strong><a href=https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2021MS002534 target=_blank>Stochastic-Deep Learning Parameterization of Ocean Momentum Forcing</a></strong> JAMES...</p></li></ul></div></div></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
 <a href=https://twitter.com/M2LInES target=blank><img src=../images/twitter.svg title=Twitter alt=Twitter></a>
 <a href=https://github.com/m2lines target=blank><img src=../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/sitemap.xml b/sitemap.xml
index aa1952443..cc8bab19d 100644
--- a/sitemap.xml
+++ b/sitemap.xml
@@ -1 +1 @@
-<?xml version="1.0" encoding="utf-8" standalone="yes"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url><loc>https://m2lines.github.io/team/laure-zanna/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/research/research1/</loc></url><url><loc>https://m2lines.github.io/team/johannagoldman/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/research/research5/</loc></url><url><loc>https://m2lines.github.io/research/research2/</loc></url><url><loc>https://m2lines.github.io/research/research4/</loc></url><url><loc>https://m2lines.github.io/team/former/ziweili/</loc></url><url><loc>https://m2lines.github.io/team/alistairadcroft/</loc></url><url><loc>https://m2lines.github.io/research/research3/</loc></url><url><loc>https://m2lines.github.io/team/carlosferndandezgranda/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/joan-bruna/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/ryanabernathy/</loc></url><url><loc>https://m2lines.github.io/team/brandonreichl/</loc></url><url><loc>https://m2lines.github.io/team/feiyulu/</loc></url><url><loc>https://m2lines.github.io/team/judithberner/</loc></url><url><loc>https://m2lines.github.io/team/marikaholland/</loc></url><url><loc>https://m2lines.github.io/team/mitchbushuk/</loc></url><url><loc>https://m2lines.github.io/team/pierregentine/</loc></url><url><loc>https://m2lines.github.io/team/paulogorman/</loc></url><url><loc>https://m2lines.github.io/team/juliedeshayes/</loc></url><url><loc>https://m2lines.github.io/team/julienlesommer/</loc></url><url><loc>https://m2lines.github.io/team/arthurguillaumin/</loc></url><url><loc>https://m2lines.github.io/team/janniyuval/</loc></url><url><loc>https://m2lines.github.io/team/alexconnolly/</loc></url><url><loc>https://m2lines.github.io/team/juliusbusecke/</loc></url><url><loc>https://m2lines.github.io/team/aakashsane/</loc></url><url><loc>https://m2lines.github.io/team/former/andrewross/</loc></url><url><loc>https://m2lines.github.io/team/lorenzozampieri/</loc></url><url><loc>https://m2lines.github.io/team/cemgultekin/</loc></url><url><loc>https://m2lines.github.io/team/tarunverma/</loc></url><url><loc>https://m2lines.github.io/team/dhruvbalwada/</loc></url><url><loc>https://m2lines.github.io/team/chengzhang/</loc></url><url><loc>https://m2lines.github.io/team/former/anastasiiagorbunova/</loc></url><url><loc>https://m2lines.github.io/team/pavelperezhogin/</loc></url><url><loc>https://m2lines.github.io/team/willchapman/</loc></url><url><loc>https://m2lines.github.io/team/willgregory/</loc></url><url><loc>https://m2lines.github.io/team/abigailbodner/</loc></url><url><loc>https://m2lines.github.io/team/andrewbrettin/</loc></url><url><loc>https://m2lines.github.io/team/former/marioherrerogonzalez/</loc></url><url><loc>https://m2lines.github.io/team/karlotness/</loc></url><url><loc>https://m2lines.github.io/team/azizbhouri/</loc></url><url><loc>https://m2lines.github.io/team/former/hugofrezat/</loc></url><url><loc>https://m2lines.github.io/team/former/adrienburq/</loc></url><url><loc>https://m2lines.github.io/team/fabriziofalasca/</loc></url><url><loc>https://m2lines.github.io/team/adamsubel/</loc></url><url><loc>https://m2lines.github.io/team/alexisbarge/</loc></url><url><loc>https://m2lines.github.io/team/maudtissot/</loc></url><url><loc>https://m2lines.github.io/team/former/elizabethyankovsky/</loc></url><url><loc>https://m2lines.github.io/team/sarashamekh/</loc></url><url><loc>https://m2lines.github.io/team/former/chrisdupuis/</loc></url><url><loc>https://m2lines.github.io/team/former/jemanjohnson/</loc></url><url><loc>https://m2lines.github.io/team/chrispedersen/</loc></url><url><loc>https://m2lines.github.io/team/emilynewsom/</loc></url><url><loc>https://m2lines.github.io/team/etiennemeunier/</loc></url><url><loc>https://m2lines.github.io/team/former/mariapratcolomer/</loc></url><url><loc>https://m2lines.github.io/team/noraloose/</loc></url><url><loc>https://m2lines.github.io/team/davidkamm/</loc></url><url><loc>https://m2lines.github.io/team/patricialuc/</loc></url><url><loc>https://m2lines.github.io/team/kelseyeverard/</loc></url><url><loc>https://m2lines.github.io/team/former/matiasortiz/</loc></url><url><loc>https://m2lines.github.io/team/shubham/</loc></url><url><loc>https://m2lines.github.io/team/suryadheeshjith/</loc></url><url><loc>https://m2lines.github.io/team/former/leoliu/</loc></url><url><loc>https://m2lines.github.io/team/former/shantanu/</loc></url><url><loc>https://m2lines.github.io/team/griffinmooers/</loc></url><url><loc>https://m2lines.github.io/team/former/friedrichginnold/</loc></url><url><loc>https://m2lines.github.io/team/praninalluri/</loc></url><url><loc>https://m2lines.github.io/team/renaudfalga/</loc></url><url><loc>https://m2lines.github.io/team/jisuhan/</loc></url><url><loc>https://m2lines.github.io/team/juliasimpson/</loc></url><url><loc>https://m2lines.github.io/team/jiarongwu/</loc></url><url><loc>https://m2lines.github.io/team/yongquanqu-/</loc></url><url><loc>https://m2lines.github.io/news/</loc><lastmod>2024-04-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404zampieri/</loc><lastmod>2024-04-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404qu/</loc><lastmod>2024-04-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404adam/</loc><lastmod>2024-04-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402bhouri/</loc><lastmod>2024-02-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402joan/</loc><lastmod>2024-02-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402noora/</loc><lastmod>2024-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2401pavel/</loc><lastmod>2024-01-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2401l96/</loc><lastmod>2024-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2312climsim/</loc><lastmod>2023-12-12T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2312willgfeature/</loc><lastmod>2023-12-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2311johnson/</loc><lastmod>2023-11-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310lu/</loc><lastmod>2023-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310bhouri/</loc><lastmod>2023-10-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310chapman/</loc><lastmod>2023-10-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309blogpost/</loc><lastmod>2023-09-11T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309holland/</loc><lastmod>2023-09-04T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309mooers/</loc><lastmod>2023-09-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309pederson/</loc><lastmod>2023-09-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308newsom/</loc><lastmod>2023-08-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308bhouri/</loc><lastmod>2023-08-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308shamekh/</loc><lastmod>2023-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2307sane/</loc><lastmod>2023-07-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2306zampieri/</loc><lastmod>2023-06-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2305otness/</loc><lastmod>2023-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2301gentine/</loc><lastmod>2023-01-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2212agu22/</loc><lastmod>2022-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211balwada/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211shamekh/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211adcroft/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211bruna/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210bushuk/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210gentine/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210deshayes/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208ross/</loc><lastmod>2022-08-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208uchida/</loc><lastmod>2022-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208behrens/</loc><lastmod>2022-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207reichl/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207subel/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207berner/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gentine-abernathey/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampieri2022/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gregory2022/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/cesmworkshop2022/</loc><lastmod>2022-05-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gorbunova2021/</loc><lastmod>2022-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gcmfilter/</loc><lastmod>2022-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/holland2022/</loc><lastmod>2022-05-01T08:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balaji2022/</loc><lastmod>2022-05-01T07:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401subel/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401bruna/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401bushuk/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balwadazanna22/</loc><lastmod>2022-03-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/m2linesmovie/</loc><lastmod>2022-02-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/sanepaper2022/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/abernatheychapter/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/beuclerpreprint/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/fernandezgranda21/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/frezatpreprint/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/ziweili21/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/agupresentation/</loc><lastmod>2021-12-08T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/kickoffoct/</loc><lastmod>2021-10-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/hollandetal/</loc><lastmod>2021-10-28T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/chapmanetal/</loc><lastmod>2021-10-14T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampierietal21/</loc><lastmod>2021-10-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/aiforgood/</loc><lastmod>2021-08-25T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/fernandezgranda/</loc><lastmod>2021-07-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampierijames/</loc><lastmod>2021-07-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balwada-article/</loc><lastmod>2021-07-28T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/abernatheypaper/</loc><lastmod>2021-07-27T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/bushukarticle/</loc><lastmod>2021-07-27T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/ziweiliarticle/</loc><lastmod>2021-07-26T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/articleyuval/</loc><lastmod>2021-07-19T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/articlejamescall/</loc><lastmod>2021-07-14T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/oneworld/</loc><lastmod>2021-07-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/willgregorypaper/</loc><lastmod>2021-07-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/s2schallenge/</loc><lastmod>2021-06-29T10:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/kitpconference/</loc><lastmod>2021-06-07T10:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/cesmworkshop/</loc><lastmod>2021-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/5jamescall/</loc><lastmod>2021-06-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/3gentinepaper1/</loc><lastmod>2021-04-23T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/4gentinepaper2/</loc><lastmod>2021-03-21T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/1guillauminpaper/</loc><lastmod>2021-03-08T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2jlesommerpaper/</loc><lastmod>2021-02-22T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/about/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/pages/code-of-conduct/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/pages/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe1/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe2/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe3/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/climate/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/deep-learning/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/machine-learning/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/ocean/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/project-management/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/sciences-communication/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/signal-processing/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/</loc><lastmod>2018-02-12T15:37:57+07:00</lastmod></url><url><loc>https://m2lines.github.io/404/</loc><lastmod>2018-02-10T10:52:03+07:00</lastmod></url><url><loc>https://m2lines.github.io/research/</loc></url><url><loc>https://m2lines.github.io/sitevisit/</loc><priority>0</priority></url><url><loc>https://m2lines.github.io/team/former/</loc></url><url><loc>https://m2lines.github.io/blog/</loc></url><url><loc>https://m2lines.github.io/code/</loc></url><url><loc>https://m2lines.github.io/tags/air-sea-fluxes/</loc></url><url><loc>https://m2lines.github.io/tags/air-sea-interactions/</loc></url><url><loc>https://m2lines.github.io/research/talks/archive/</loc></url><url><loc>https://m2lines.github.io/tags/arctic-dynamics/</loc></url><url><loc>https://m2lines.github.io/tags/atmoshpere/</loc></url><url><loc>https://m2lines.github.io/tags/atmosphere/</loc></url><url><loc>https://m2lines.github.io/tags/atmospheric-boundary-layer/</loc></url><url><loc>https://m2lines.github.io/code/corrected_era5/</loc></url><url><loc>https://m2lines.github.io/tags/boundary-layer/</loc></url><url><loc>https://m2lines.github.io/tags/boundary-layer-turbulence/</loc></url><url><loc>https://m2lines.github.io/categories/</loc></url><url><loc>https://m2lines.github.io/tags/climate-data/</loc></url><url><loc>https://m2lines.github.io/tags/climate-model-development/</loc></url><url><loc>https://m2lines.github.io/tags/climate-physics/</loc></url><url><loc>https://m2lines.github.io/code/cm26/</loc></url><url><loc>https://m2lines.github.io/tags/complex-systems/</loc></url><url><loc>https://m2lines.github.io/tags/computational-fluid-mechanics/</loc></url><url><loc>https://m2lines.github.io/tags/computer-vision/</loc></url><url><loc>https://m2lines.github.io/tags/coupled-physics/</loc></url><url><loc>https://m2lines.github.io/tags/coupling/</loc></url><url><loc>https://m2lines.github.io/tags/data/</loc></url><url><loc>https://m2lines.github.io/tags/data-analysis/</loc></url><url><loc>https://m2lines.github.io/tags/data-assimilation/</loc></url><url><loc>https://m2lines.github.io/tags/data-engineering/</loc></url><url><loc>https://m2lines.github.io/tags/data-mining/</loc></url><url><loc>https://m2lines.github.io/code/icemodelerrors/</loc></url><url><loc>https://m2lines.github.io/tags/diagnostics/</loc></url><url><loc>https://m2lines.github.io/code/diffqg_jax/</loc></url><url><loc>https://m2lines.github.io/code/diffqg_pytorch/</loc></url><url><loc>https://m2lines.github.io/tags/dynamical-systems/</loc></url><url><loc>https://m2lines.github.io/tags/eddy-parameterizations/</loc></url><url><loc>https://m2lines.github.io/code/equationdiscovery/</loc></url><url><loc>https://m2lines.github.io/code/gcm/</loc></url><url><loc>https://m2lines.github.io/code/datadrivenparam/</loc></url><url><loc>https://m2lines.github.io/code/geotrainflow/</loc></url><url><loc>https://m2lines.github.io/tags/hr-data-and-observations/</loc></url><url><loc>https://m2lines.github.io/code/mom6/</loc></url><url><loc>https://m2lines.github.io/code/parampyqg/</loc></url><url><loc>https://m2lines.github.io/code/parammom6/</loc></url><url><loc>https://m2lines.github.io/tags/interpretability/</loc></url><url><loc>https://m2lines.github.io/jobs/</loc></url><url><loc>https://m2lines.github.io/code/lorenz96/</loc></url><url><loc>https://m2lines.github.io/tags/macro-turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/mesoscale-eddy-parameterisation/</loc></url><url><loc>https://m2lines.github.io/tags/mesoscale-eddy-parameterizations/</loc></url><url><loc>https://m2lines.github.io/tags/modelling-and-predictability/</loc></url><url><loc>https://m2lines.github.io/tags/moist-convection/</loc></url><url><loc>https://m2lines.github.io/code/verticalmix/</loc></url><url><loc>https://m2lines.github.io/code/subgridatmosphere/</loc></url><url><loc>https://m2lines.github.io/code/transportatmosphere/</loc></url><url><loc>https://m2lines.github.io/tags/newsletters/</loc></url><url><loc>https://m2lines.github.io/news/newsletters/</loc></url><url><loc>https://m2lines.github.io/tags/ocean-mesoscale-and-submesoscale-turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/ocean-surface/</loc></url><url><loc>https://m2lines.github.io/tags/open-source-software/</loc></url><url><loc>https://m2lines.github.io/tags/predictability/</loc></url><url><loc>https://m2lines.github.io/publications/</loc></url><url><loc>https://m2lines.github.io/publications/archive/</loc></url><url><loc>https://m2lines.github.io/code/pyqg/</loc></url><url><loc>https://m2lines.github.io/code/randomforest/</loc></url><url><loc>https://m2lines.github.io/tags/sea-ice/</loc></url><url><loc>https://m2lines.github.io/tags/simulation/</loc></url><url><loc>https://m2lines.github.io/tags/software-architecture/</loc></url><url><loc>https://m2lines.github.io/tags/speech-recognition/</loc></url><url><loc>https://m2lines.github.io/code/shallowwater/</loc></url><url><loc>https://m2lines.github.io/tags/statistics/</loc></url><url><loc>https://m2lines.github.io/code/momentumforcing/</loc></url><url><loc>https://m2lines.github.io/tags/subgrid-parametrizations/</loc></url><url><loc>https://m2lines.github.io/tags/subgrid-scale-parametrization/</loc></url><url><loc>https://m2lines.github.io/research/talks/</loc></url><url><loc>https://m2lines.github.io/tags/talks/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence-paramezizations/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence-statistics/</loc></url><url><loc>https://m2lines.github.io/code/xgcm/</loc></url></urlset>
\ No newline at end of file
+<?xml version="1.0" encoding="utf-8" standalone="yes"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url><loc>https://m2lines.github.io/team/laure-zanna/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/research/research1/</loc></url><url><loc>https://m2lines.github.io/team/johannagoldman/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/research/research5/</loc></url><url><loc>https://m2lines.github.io/research/research2/</loc></url><url><loc>https://m2lines.github.io/research/research4/</loc></url><url><loc>https://m2lines.github.io/team/former/ziweili/</loc></url><url><loc>https://m2lines.github.io/team/alistairadcroft/</loc></url><url><loc>https://m2lines.github.io/research/research3/</loc></url><url><loc>https://m2lines.github.io/team/carlosferndandezgranda/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/joan-bruna/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/ryanabernathy/</loc></url><url><loc>https://m2lines.github.io/team/brandonreichl/</loc></url><url><loc>https://m2lines.github.io/team/feiyulu/</loc></url><url><loc>https://m2lines.github.io/team/judithberner/</loc></url><url><loc>https://m2lines.github.io/team/marikaholland/</loc></url><url><loc>https://m2lines.github.io/team/mitchbushuk/</loc></url><url><loc>https://m2lines.github.io/team/pierregentine/</loc></url><url><loc>https://m2lines.github.io/team/paulogorman/</loc></url><url><loc>https://m2lines.github.io/team/juliedeshayes/</loc></url><url><loc>https://m2lines.github.io/team/julienlesommer/</loc></url><url><loc>https://m2lines.github.io/team/arthurguillaumin/</loc></url><url><loc>https://m2lines.github.io/team/janniyuval/</loc></url><url><loc>https://m2lines.github.io/team/alexconnolly/</loc></url><url><loc>https://m2lines.github.io/team/juliusbusecke/</loc></url><url><loc>https://m2lines.github.io/team/aakashsane/</loc></url><url><loc>https://m2lines.github.io/team/former/andrewross/</loc></url><url><loc>https://m2lines.github.io/team/lorenzozampieri/</loc></url><url><loc>https://m2lines.github.io/team/cemgultekin/</loc></url><url><loc>https://m2lines.github.io/team/tarunverma/</loc></url><url><loc>https://m2lines.github.io/team/dhruvbalwada/</loc></url><url><loc>https://m2lines.github.io/team/chengzhang/</loc></url><url><loc>https://m2lines.github.io/team/former/anastasiiagorbunova/</loc></url><url><loc>https://m2lines.github.io/team/pavelperezhogin/</loc></url><url><loc>https://m2lines.github.io/team/willchapman/</loc></url><url><loc>https://m2lines.github.io/team/willgregory/</loc></url><url><loc>https://m2lines.github.io/team/abigailbodner/</loc></url><url><loc>https://m2lines.github.io/team/andrewbrettin/</loc></url><url><loc>https://m2lines.github.io/team/former/marioherrerogonzalez/</loc></url><url><loc>https://m2lines.github.io/team/karlotness/</loc></url><url><loc>https://m2lines.github.io/team/azizbhouri/</loc></url><url><loc>https://m2lines.github.io/team/former/hugofrezat/</loc></url><url><loc>https://m2lines.github.io/team/former/adrienburq/</loc></url><url><loc>https://m2lines.github.io/team/fabriziofalasca/</loc></url><url><loc>https://m2lines.github.io/team/adamsubel/</loc></url><url><loc>https://m2lines.github.io/team/alexisbarge/</loc></url><url><loc>https://m2lines.github.io/team/maudtissot/</loc></url><url><loc>https://m2lines.github.io/team/former/elizabethyankovsky/</loc></url><url><loc>https://m2lines.github.io/team/sarashamekh/</loc></url><url><loc>https://m2lines.github.io/team/former/chrisdupuis/</loc></url><url><loc>https://m2lines.github.io/team/former/jemanjohnson/</loc></url><url><loc>https://m2lines.github.io/team/chrispedersen/</loc></url><url><loc>https://m2lines.github.io/team/emilynewsom/</loc></url><url><loc>https://m2lines.github.io/team/etiennemeunier/</loc></url><url><loc>https://m2lines.github.io/team/former/mariapratcolomer/</loc></url><url><loc>https://m2lines.github.io/team/noraloose/</loc></url><url><loc>https://m2lines.github.io/team/davidkamm/</loc></url><url><loc>https://m2lines.github.io/team/patricialuc/</loc></url><url><loc>https://m2lines.github.io/team/kelseyeverard/</loc></url><url><loc>https://m2lines.github.io/team/former/matiasortiz/</loc></url><url><loc>https://m2lines.github.io/team/shubham/</loc></url><url><loc>https://m2lines.github.io/team/suryadheeshjith/</loc></url><url><loc>https://m2lines.github.io/team/former/leoliu/</loc></url><url><loc>https://m2lines.github.io/team/former/shantanu/</loc></url><url><loc>https://m2lines.github.io/team/griffinmooers/</loc></url><url><loc>https://m2lines.github.io/team/former/friedrichginnold/</loc></url><url><loc>https://m2lines.github.io/team/praninalluri/</loc></url><url><loc>https://m2lines.github.io/team/renaudfalga/</loc></url><url><loc>https://m2lines.github.io/team/jisuhan/</loc></url><url><loc>https://m2lines.github.io/team/juliasimpson/</loc></url><url><loc>https://m2lines.github.io/team/jiarongwu/</loc></url><url><loc>https://m2lines.github.io/team/yongquanqu-/</loc></url><url><loc>https://m2lines.github.io/news/</loc><lastmod>2024-05-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2405chapman/</loc><lastmod>2024-05-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2405bushuk/</loc><lastmod>2024-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404zampieri/</loc><lastmod>2024-04-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404qu/</loc><lastmod>2024-04-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2404adam/</loc><lastmod>2024-04-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402bhouri/</loc><lastmod>2024-02-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402joan/</loc><lastmod>2024-02-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2402noora/</loc><lastmod>2024-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2401pavel/</loc><lastmod>2024-01-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2401l96/</loc><lastmod>2024-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2312climsim/</loc><lastmod>2023-12-12T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2312willgfeature/</loc><lastmod>2023-12-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2311johnson/</loc><lastmod>2023-11-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310lu/</loc><lastmod>2023-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310bhouri/</loc><lastmod>2023-10-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2310chapman/</loc><lastmod>2023-10-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309blogpost/</loc><lastmod>2023-09-11T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309holland/</loc><lastmod>2023-09-04T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309mooers/</loc><lastmod>2023-09-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2309pederson/</loc><lastmod>2023-09-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308newsom/</loc><lastmod>2023-08-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308bhouri/</loc><lastmod>2023-08-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2308shamekh/</loc><lastmod>2023-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2307sane/</loc><lastmod>2023-07-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2306zampieri/</loc><lastmod>2023-06-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2305otness/</loc><lastmod>2023-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2301gentine/</loc><lastmod>2023-01-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2212agu22/</loc><lastmod>2022-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211balwada/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211shamekh/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211adcroft/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2211bruna/</loc><lastmod>2022-11-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210bushuk/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210gentine/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2210deshayes/</loc><lastmod>2022-10-03T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208ross/</loc><lastmod>2022-08-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208uchida/</loc><lastmod>2022-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2208behrens/</loc><lastmod>2022-08-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207reichl/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207subel/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2207berner/</loc><lastmod>2022-07-05T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gentine-abernathey/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampieri2022/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gregory2022/</loc><lastmod>2022-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/cesmworkshop2022/</loc><lastmod>2022-05-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gorbunova2021/</loc><lastmod>2022-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/gcmfilter/</loc><lastmod>2022-05-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/holland2022/</loc><lastmod>2022-05-01T08:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balaji2022/</loc><lastmod>2022-05-01T07:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401subel/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401bruna/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/220401bushuk/</loc><lastmod>2022-03-31T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balwadazanna22/</loc><lastmod>2022-03-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/m2linesmovie/</loc><lastmod>2022-02-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/sanepaper2022/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/abernatheychapter/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/beuclerpreprint/</loc><lastmod>2022-02-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/fernandezgranda21/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/frezatpreprint/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/ziweili21/</loc><lastmod>2022-01-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/agupresentation/</loc><lastmod>2021-12-08T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/kickoffoct/</loc><lastmod>2021-10-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/hollandetal/</loc><lastmod>2021-10-28T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/chapmanetal/</loc><lastmod>2021-10-14T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampierietal21/</loc><lastmod>2021-10-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/aiforgood/</loc><lastmod>2021-08-25T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/fernandezgranda/</loc><lastmod>2021-07-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/zampierijames/</loc><lastmod>2021-07-29T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/balwada-article/</loc><lastmod>2021-07-28T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/abernatheypaper/</loc><lastmod>2021-07-27T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/bushukarticle/</loc><lastmod>2021-07-27T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/ziweiliarticle/</loc><lastmod>2021-07-26T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/articleyuval/</loc><lastmod>2021-07-19T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/articlejamescall/</loc><lastmod>2021-07-14T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/oneworld/</loc><lastmod>2021-07-02T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/willgregorypaper/</loc><lastmod>2021-07-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/s2schallenge/</loc><lastmod>2021-06-29T10:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/kitpconference/</loc><lastmod>2021-06-07T10:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/cesmworkshop/</loc><lastmod>2021-06-07T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/5jamescall/</loc><lastmod>2021-06-01T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/3gentinepaper1/</loc><lastmod>2021-04-23T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/4gentinepaper2/</loc><lastmod>2021-03-21T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/1guillauminpaper/</loc><lastmod>2021-03-08T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/news/2jlesommerpaper/</loc><lastmod>2021-02-22T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/about/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/pages/code-of-conduct/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/pages/</loc><lastmod>2018-12-06T09:29:16+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe1/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe2/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/axe3/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/services/</loc><lastmod>2018-11-28T15:15:34+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/climate/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/deep-learning/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/machine-learning/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/ocean/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/project-management/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/sciences-communication/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/signal-processing/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/tags/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/team/</loc><lastmod>2018-11-19T10:47:58+10:00</lastmod></url><url><loc>https://m2lines.github.io/</loc><lastmod>2018-02-12T15:37:57+07:00</lastmod></url><url><loc>https://m2lines.github.io/404/</loc><lastmod>2018-02-10T10:52:03+07:00</lastmod></url><url><loc>https://m2lines.github.io/research/</loc></url><url><loc>https://m2lines.github.io/sitevisit/</loc><priority>0</priority></url><url><loc>https://m2lines.github.io/team/former/</loc></url><url><loc>https://m2lines.github.io/blog/</loc></url><url><loc>https://m2lines.github.io/code/</loc></url><url><loc>https://m2lines.github.io/tags/air-sea-fluxes/</loc></url><url><loc>https://m2lines.github.io/tags/air-sea-interactions/</loc></url><url><loc>https://m2lines.github.io/research/talks/archive/</loc></url><url><loc>https://m2lines.github.io/tags/arctic-dynamics/</loc></url><url><loc>https://m2lines.github.io/tags/atmoshpere/</loc></url><url><loc>https://m2lines.github.io/tags/atmosphere/</loc></url><url><loc>https://m2lines.github.io/tags/atmospheric-boundary-layer/</loc></url><url><loc>https://m2lines.github.io/code/corrected_era5/</loc></url><url><loc>https://m2lines.github.io/tags/boundary-layer/</loc></url><url><loc>https://m2lines.github.io/tags/boundary-layer-turbulence/</loc></url><url><loc>https://m2lines.github.io/categories/</loc></url><url><loc>https://m2lines.github.io/tags/climate-data/</loc></url><url><loc>https://m2lines.github.io/tags/climate-model-development/</loc></url><url><loc>https://m2lines.github.io/tags/climate-physics/</loc></url><url><loc>https://m2lines.github.io/code/cm26/</loc></url><url><loc>https://m2lines.github.io/tags/complex-systems/</loc></url><url><loc>https://m2lines.github.io/tags/computational-fluid-mechanics/</loc></url><url><loc>https://m2lines.github.io/tags/computer-vision/</loc></url><url><loc>https://m2lines.github.io/tags/coupled-physics/</loc></url><url><loc>https://m2lines.github.io/tags/coupling/</loc></url><url><loc>https://m2lines.github.io/tags/data/</loc></url><url><loc>https://m2lines.github.io/tags/data-analysis/</loc></url><url><loc>https://m2lines.github.io/tags/data-assimilation/</loc></url><url><loc>https://m2lines.github.io/tags/data-engineering/</loc></url><url><loc>https://m2lines.github.io/tags/data-mining/</loc></url><url><loc>https://m2lines.github.io/code/icemodelerrors/</loc></url><url><loc>https://m2lines.github.io/tags/diagnostics/</loc></url><url><loc>https://m2lines.github.io/code/diffqg_jax/</loc></url><url><loc>https://m2lines.github.io/code/diffqg_pytorch/</loc></url><url><loc>https://m2lines.github.io/tags/dynamical-systems/</loc></url><url><loc>https://m2lines.github.io/tags/eddy-parameterizations/</loc></url><url><loc>https://m2lines.github.io/code/equationdiscovery/</loc></url><url><loc>https://m2lines.github.io/code/gcm/</loc></url><url><loc>https://m2lines.github.io/code/datadrivenparam/</loc></url><url><loc>https://m2lines.github.io/code/geotrainflow/</loc></url><url><loc>https://m2lines.github.io/tags/hr-data-and-observations/</loc></url><url><loc>https://m2lines.github.io/code/mom6/</loc></url><url><loc>https://m2lines.github.io/code/parampyqg/</loc></url><url><loc>https://m2lines.github.io/code/parammom6/</loc></url><url><loc>https://m2lines.github.io/tags/interpretability/</loc></url><url><loc>https://m2lines.github.io/jobs/</loc></url><url><loc>https://m2lines.github.io/code/lorenz96/</loc></url><url><loc>https://m2lines.github.io/tags/macro-turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/mesoscale-eddy-parameterisation/</loc></url><url><loc>https://m2lines.github.io/tags/mesoscale-eddy-parameterizations/</loc></url><url><loc>https://m2lines.github.io/tags/modelling-and-predictability/</loc></url><url><loc>https://m2lines.github.io/tags/moist-convection/</loc></url><url><loc>https://m2lines.github.io/code/verticalmix/</loc></url><url><loc>https://m2lines.github.io/code/subgridatmosphere/</loc></url><url><loc>https://m2lines.github.io/code/transportatmosphere/</loc></url><url><loc>https://m2lines.github.io/tags/newsletters/</loc></url><url><loc>https://m2lines.github.io/news/newsletters/</loc></url><url><loc>https://m2lines.github.io/tags/ocean-mesoscale-and-submesoscale-turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/ocean-surface/</loc></url><url><loc>https://m2lines.github.io/tags/open-source-software/</loc></url><url><loc>https://m2lines.github.io/tags/predictability/</loc></url><url><loc>https://m2lines.github.io/publications/</loc></url><url><loc>https://m2lines.github.io/publications/archive/</loc></url><url><loc>https://m2lines.github.io/code/pyqg/</loc></url><url><loc>https://m2lines.github.io/code/randomforest/</loc></url><url><loc>https://m2lines.github.io/tags/sea-ice/</loc></url><url><loc>https://m2lines.github.io/tags/simulation/</loc></url><url><loc>https://m2lines.github.io/tags/software-architecture/</loc></url><url><loc>https://m2lines.github.io/tags/speech-recognition/</loc></url><url><loc>https://m2lines.github.io/code/shallowwater/</loc></url><url><loc>https://m2lines.github.io/tags/statistics/</loc></url><url><loc>https://m2lines.github.io/code/momentumforcing/</loc></url><url><loc>https://m2lines.github.io/tags/subgrid-parametrizations/</loc></url><url><loc>https://m2lines.github.io/tags/subgrid-scale-parametrization/</loc></url><url><loc>https://m2lines.github.io/research/talks/</loc></url><url><loc>https://m2lines.github.io/tags/talks/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence-paramezizations/</loc></url><url><loc>https://m2lines.github.io/tags/turbulence-statistics/</loc></url><url><loc>https://m2lines.github.io/code/xgcm/</loc></url></urlset>
\ No newline at end of file
diff --git a/tags/newsletters/index.html b/tags/newsletters/index.html
index 934217ef9..5b5756745 100644
--- a/tags/newsletters/index.html
+++ b/tags/newsletters/index.html
@@ -7,6 +7,6 @@
 <input type=checkbox id=Publications><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../publications/><span class=menu__text>Latest</span></a></li><li class=menu__item><a class=menu__link href=../../publications/archive><span class=menu__text>Archive</span></a></li></ul></li><li class="menu__item menu__dropdown"><a class=menu__link href><span class=menu__text>News</span>
 <label class=drop-icon for=News>▾</label></a>
 <input type=checkbox id=News><ul class=submenu__list><li class=menu__item><a class=menu__link href=../../news/><span class=menu__text>Our news</span></a></li><li class=menu__item><a class=menu__link href=../../news/newsletters/><span class=menu__text>Newsletters</span></a></li></ul></li></ul></nav><button id=toggle-main-menu-mobile class="hamburger hamburger--slider" type=button>
-<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div class="container pt-10 pb-6"><div class=row><div class=col-12><h1 class="title-1 black">Newsletters</h1></div></div></div><div class="container pb-6"><div class=row><div class="col-12 col-md-6 mb-2"><p>Links to our past newsletters are below.</p><h3 id=2024>2024</h3><ul><li><p>04/01/2024 - <a href=https://mailchi.mp/e8da3716350c/m2lines-april24-newsletter target=_blank>M²LInES newsletter - April 2024</a></p></li><li><p>02/16/2024 - <a href=https://mailchi.mp/98cf4196cd4a/m2lines-newsletter-osm24 target=_blank>M²LInES newsletter - Special Ocean Sciences Meeting</a></p></li><li><p>02/01/2024 - <a href=https://mailchi.mp/149196c77c09/m2lines-feburary-2024 target=_blank>M²LInES newsletter - Feburary 2024</a></p></li><li><p>01/08/2024 - <a href=https://mailchi.mp/688f6e69dc60/m2lines-january-2024 target=_blank>M²LInES newsletter - January 2024</a></p></li></ul><h3 id=2023>2023</h3><ul><li><p>12/01/2023 - <a href=https://mailchi.mp/7d7642df21e6/m2lines-december-newsletter-agu target=_blank>M²LInES newsletter - December 2023 - Special AGU</a></p></li><li><p>11/02/2023 - <a href=https://mailchi.mp/6be77812991b/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2023</a></p></li><li><p>10/04/2023 - <a href=https://mailchi.mp/09855c01b0d3/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2023</a></p></li><li><p>09/06/2023 - <a href=https://mailchi.mp/77c1eded6eb6/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2023</a></p></li><li><p>08/01/2023 - <a href=https://mailchi.mp/8afe52c0433c/m2lines-august23-newsletter target=_blank>M²LInES newsletter - August 2023</a></p></li><li><p>07/03/2023 - <a href=https://mailchi.mp/7c514e163b6e/m2lines-july23-newsletter target=_blank>M²LInES newsletter - July 2023</a></p></li><li><p>06/13/2023 - <a href=https://mailchi.mp/3e13c2d1b09e/m2lines-june2023-newsletter target=_blank>M²LInES newsletter - June 2023</a></p></li><li><p>05/11/2023 - <a href=https://mailchi.mp/89ec798d18b2/m2lines-may2023-newsletter target=_blank>M²LInES newsletter - May 2023</a></p></li><li><p>01/03/2023 - <a href=https://mailchi.mp/5b801dd5a61a/m2lines-newsletter-january-2023 target=_blank>M²LInES newsletter - January 2023</a></p></li></ul><h3 id=2022>2022</h3><ul><li><p>12/05/2022 - <a href=https://mailchi.mp/169d6f0c61f9/m2lines-december-newsletter-agu-special target=_blank>M²LInES newsletter - December 2022 AGU Special</a></p></li><li><p>11/01/2022 - <a href=https://mailchi.mp/ea5545ba3ad9/m2lines-newsletter-november-2022 target=_blank>M²LInES newsletter - November 2022</a></p></li><li><p>10/03/2022 - <a href=https://mailchi.mp/1b79e3c3f118/m2lines-newsletter-october-2022 target=_blank>M²LInES newsletter - October 2022</a></p></li><li><p>09/16/2022 - <a href=https://mailchi.mp/23f67eb58497/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2022 Research Roundup</a></p></li><li><p>08/01/2022 - <a href=https://mailchi.mp/de41e2fa4f3a/m2lines-august-2022 target=_blank>M²LInES newsletter - August 2022</a></p></li><li><p>07/05/2022 - <a href=https://mailchi.mp/559244aacd7f/m2lines-july-newsletter target=_blank>M²LInES newsletter - July 2022</a></p></li><li><p>06/06/2022 - <a href=https://mailchi.mp/b6ce90c1f066/m2lines-june-2022-newsletter target=_blank>M²LInES newsletter - June 2022</a></p></li><li><p>05/02/2022 - <a href=https://mailchi.mp/f1f185fede51/m2lines-may2022 target=_blank>M²LInES newsletter - May 2022</a></p></li><li><p>04/01/2022 - <a href=https://mailchi.mp/2db4ee09fcf6/m2lines-april-2022-newsletter target=_blank>M²LInES newsletter - April 2022</a></p></li><li><p>02/24/2022 - <a href=https://mailchi.mp/11a5a98d21a3/m2lines-newsletter-osm22 target=_blank>M²LInES newsletter - OSM22 special</a></p></li><li><p>02/01/2022 - <a href=https://mailchi.mp/cb9b5c06b78c/m2lines-february-2022 target=_blank>M²LInES newsletter - February 2022</a></p></li><li><p>01/01/2022 - <a href=https://mailchi.mp/a57b46b053b0/m2lines-january-2022 target=_blank>M²LInES newsletter - January 2022</a></p></li></ul><h3 id=2021>2021</h3><ul><li><p>12/01/2021 - <a href=https://mailchi.mp/29ddfae980e7/m2lines-december-newsletter target=_blank>M²LInES newsletter - December 2021 AGU special</a></p></li><li><p>11/01/2021 - <a href=https://mailchi.mp/5ae317faf7e4/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2021</a></p></li><li><p>10/01/2021 - <a href=https://mailchi.mp/c3af749bf3ea/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2021</a></p></li><li><p>09/01/2021 - <a href=https://mailchi.mp/51a1b976f492/m2lines-newsletter target=_blank>M²LInES newsletter - September 2021</a></p></li><li><p>08/02/2021 - <a href=https://mailchi.mp/6c353c6991e5/m2lines-august-newsletter target=_blank>M²LInES newsletter - August 2021</a></p></li><li><p>06/29/2021 - <a href=https://mailchi.mp/1fabec1cb5be/m2lines target=_blank>M²LInES newsletter - June/July 2021</a></p></li></ul></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
+<span class=hamburger-box><span class=hamburger-inner></span></span></button></div></div><div class="container pt-10 pb-6"><div class=row><div class=col-12><h1 class="title-1 black">Newsletters</h1></div></div></div><div class="container pb-6"><div class=row><div class="col-12 col-md-6 mb-2"><p>Links to our past newsletters are below.</p><h3 id=2024>2024</h3><ul><li><p>05/01/2024 - <a href=https://mailchi.mp/04a341e92442/m2lines-may-2024 target=_blank>M²LInES newsletter - May 2024</a></p></li><li><p>04/01/2024 - <a href=https://mailchi.mp/e8da3716350c/m2lines-april24-newsletter target=_blank>M²LInES newsletter - April 2024</a></p></li><li><p>02/16/2024 - <a href=https://mailchi.mp/98cf4196cd4a/m2lines-newsletter-osm24 target=_blank>M²LInES newsletter - Special Ocean Sciences Meeting</a></p></li><li><p>02/01/2024 - <a href=https://mailchi.mp/149196c77c09/m2lines-feburary-2024 target=_blank>M²LInES newsletter - Feburary 2024</a></p></li><li><p>01/08/2024 - <a href=https://mailchi.mp/688f6e69dc60/m2lines-january-2024 target=_blank>M²LInES newsletter - January 2024</a></p></li></ul><h3 id=2023>2023</h3><ul><li><p>12/01/2023 - <a href=https://mailchi.mp/7d7642df21e6/m2lines-december-newsletter-agu target=_blank>M²LInES newsletter - December 2023 - Special AGU</a></p></li><li><p>11/02/2023 - <a href=https://mailchi.mp/6be77812991b/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2023</a></p></li><li><p>10/04/2023 - <a href=https://mailchi.mp/09855c01b0d3/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2023</a></p></li><li><p>09/06/2023 - <a href=https://mailchi.mp/77c1eded6eb6/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2023</a></p></li><li><p>08/01/2023 - <a href=https://mailchi.mp/8afe52c0433c/m2lines-august23-newsletter target=_blank>M²LInES newsletter - August 2023</a></p></li><li><p>07/03/2023 - <a href=https://mailchi.mp/7c514e163b6e/m2lines-july23-newsletter target=_blank>M²LInES newsletter - July 2023</a></p></li><li><p>06/13/2023 - <a href=https://mailchi.mp/3e13c2d1b09e/m2lines-june2023-newsletter target=_blank>M²LInES newsletter - June 2023</a></p></li><li><p>05/11/2023 - <a href=https://mailchi.mp/89ec798d18b2/m2lines-may2023-newsletter target=_blank>M²LInES newsletter - May 2023</a></p></li><li><p>01/03/2023 - <a href=https://mailchi.mp/5b801dd5a61a/m2lines-newsletter-january-2023 target=_blank>M²LInES newsletter - January 2023</a></p></li></ul><h3 id=2022>2022</h3><ul><li><p>12/05/2022 - <a href=https://mailchi.mp/169d6f0c61f9/m2lines-december-newsletter-agu-special target=_blank>M²LInES newsletter - December 2022 AGU Special</a></p></li><li><p>11/01/2022 - <a href=https://mailchi.mp/ea5545ba3ad9/m2lines-newsletter-november-2022 target=_blank>M²LInES newsletter - November 2022</a></p></li><li><p>10/03/2022 - <a href=https://mailchi.mp/1b79e3c3f118/m2lines-newsletter-october-2022 target=_blank>M²LInES newsletter - October 2022</a></p></li><li><p>09/16/2022 - <a href=https://mailchi.mp/23f67eb58497/m2lines-september-newsletter target=_blank>M²LInES newsletter - September 2022 Research Roundup</a></p></li><li><p>08/01/2022 - <a href=https://mailchi.mp/de41e2fa4f3a/m2lines-august-2022 target=_blank>M²LInES newsletter - August 2022</a></p></li><li><p>07/05/2022 - <a href=https://mailchi.mp/559244aacd7f/m2lines-july-newsletter target=_blank>M²LInES newsletter - July 2022</a></p></li><li><p>06/06/2022 - <a href=https://mailchi.mp/b6ce90c1f066/m2lines-june-2022-newsletter target=_blank>M²LInES newsletter - June 2022</a></p></li><li><p>05/02/2022 - <a href=https://mailchi.mp/f1f185fede51/m2lines-may2022 target=_blank>M²LInES newsletter - May 2022</a></p></li><li><p>04/01/2022 - <a href=https://mailchi.mp/2db4ee09fcf6/m2lines-april-2022-newsletter target=_blank>M²LInES newsletter - April 2022</a></p></li><li><p>02/24/2022 - <a href=https://mailchi.mp/11a5a98d21a3/m2lines-newsletter-osm22 target=_blank>M²LInES newsletter - OSM22 special</a></p></li><li><p>02/01/2022 - <a href=https://mailchi.mp/cb9b5c06b78c/m2lines-february-2022 target=_blank>M²LInES newsletter - February 2022</a></p></li><li><p>01/01/2022 - <a href=https://mailchi.mp/a57b46b053b0/m2lines-january-2022 target=_blank>M²LInES newsletter - January 2022</a></p></li></ul><h3 id=2021>2021</h3><ul><li><p>12/01/2021 - <a href=https://mailchi.mp/29ddfae980e7/m2lines-december-newsletter target=_blank>M²LInES newsletter - December 2021 AGU special</a></p></li><li><p>11/01/2021 - <a href=https://mailchi.mp/5ae317faf7e4/m2lines-november-newsletter target=_blank>M²LInES newsletter - November 2021</a></p></li><li><p>10/01/2021 - <a href=https://mailchi.mp/c3af749bf3ea/m2lines-october-newsletter target=_blank>M²LInES newsletter - October 2021</a></p></li><li><p>09/01/2021 - <a href=https://mailchi.mp/51a1b976f492/m2lines-newsletter target=_blank>M²LInES newsletter - September 2021</a></p></li><li><p>08/02/2021 - <a href=https://mailchi.mp/6c353c6991e5/m2lines-august-newsletter target=_blank>M²LInES newsletter - August 2021</a></p></li><li><p>06/29/2021 - <a href=https://mailchi.mp/1fabec1cb5be/m2lines target=_blank>M²LInES newsletter - June/July 2021</a></p></li></ul></div></div></div></div><div class=footer><div class=container><div class=row><div class=col-12><div class=footer-inner><ul><li class=logof><a href=https://schmidtfutures.com/ target=blank><img src=https://m2lines.github.io/images/Schmidt-Futures-Logo-small.jpg></a></li><li class=copyright>This project is supported by Schmidt Futures, a philanthropic initiative founded by Eric and Wendy Schmidt that bets early on exceptional people making the world better, particularly through innovative breakthroughs in science and technology.</li></ul></div></div></div></div></div><div class=sub-footer><div class=container><div class=row><div class=col-12><div class=sub-footer-inner><div class=social><a href=mailto:m2lines@nyu.edu target=blank><img src=../../images/PICOL_icon_Mailw.png title=Email alt=Email></a>
 <a href=https://twitter.com/M2LInES target=blank><img src=../../images/twitter.svg title=Twitter alt=Twitter></a>
 <a href=https://github.com/m2lines target=blank><img src=../../images/GitHub-Mark-Light-64px.png title=Github alt=Github></a></div><ul><li class=copyright>© 2024 M²LInES</li><li class=zerostatic><a href=https://www.zerostatic.io>www.zerostatic.io</a></li></ul></div></div></div></div></div><script type=text/javascript src=../../js/scripts.min.bf1e1f7ae8e03db5f012356e825843facdff51c0a559cb0d27fe2bbe1db405c2.js></script></body></html>
\ No newline at end of file
diff --git a/tags/newsletters/index.xml b/tags/newsletters/index.xml
index d7304e8b0..0041b3d4c 100644
--- a/tags/newsletters/index.xml
+++ b/tags/newsletters/index.xml
@@ -1,2 +1,2 @@
 <?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Newsletters on M²LInES</title><link>https://m2lines.github.io/tags/newsletters/</link><description>Recent content in Newsletters on M²LInES</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><atom:link href="https://m2lines.github.io/tags/newsletters/index.xml" rel="self" type="application/rss+xml"/><item><title>Newsletters</title><link>https://m2lines.github.io/news/newsletters/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://m2lines.github.io/news/newsletters/</guid><description>Links to our past newsletters are below.
-2024 04/01/2024 - M²LInES newsletter - April 2024 02/16/2024 - M²LInES newsletter - Special Ocean Sciences Meeting 02/01/2024 - M²LInES newsletter - Feburary 2024 01/08/2024 - M²LInES newsletter - January 2024 2023 12/01/2023 - M²LInES newsletter - December 2023 - Special AGU 11/02/2023 - M²LInES newsletter - November 2023 10/04/2023 - M²LInES newsletter - October 2023 09/06/2023 - M²LInES newsletter - September 2023 08/01/2023 - M²LInES newsletter - August 2023 07/03/2023 - M²LInES newsletter - July 2023 06/13/2023 - M²LInES newsletter - June 2023 05/11/2023 - M²LInES newsletter - May 2023 01/03/2023 - M²LInES newsletter - January 2023 2022 12/05/2022 - M²LInES newsletter - December 2022 AGU Special 11/01/2022 - M²LInES newsletter - November 2022 10/03/2022 - M²LInES newsletter - October 2022 09/16/2022 - M²LInES newsletter - September 2022 Research Roundup 08/01/2022 - M²LInES newsletter - August 2022 07/05/2022 - M²LInES newsletter - July 2022 06/06/2022 - M²LInES newsletter - June 2022 05/02/2022 - M²LInES newsletter - May 2022 04/01/2022 - M²LInES newsletter - April 2022 02/24/2022 - M²LInES newsletter - OSM22 special 02/01/2022 - M²LInES newsletter - February 2022 01/01/2022 - M²LInES newsletter - January 2022 2021 12/01/2021 - M²LInES newsletter - December 2021 AGU special 11/01/2021 - M²LInES newsletter - November 2021 10/01/2021 - M²LInES newsletter - October 2021 09/01/2021 - M²LInES newsletter - September 2021 08/02/2021 - M²LInES newsletter - August 2021 06/29/2021 - M²LInES newsletter - June/July 2021</description></item></channel></rss>
\ No newline at end of file
+2024 05/01/2024 - M²LInES newsletter - May 2024 04/01/2024 - M²LInES newsletter - April 2024 02/16/2024 - M²LInES newsletter - Special Ocean Sciences Meeting 02/01/2024 - M²LInES newsletter - Feburary 2024 01/08/2024 - M²LInES newsletter - January 2024 2023 12/01/2023 - M²LInES newsletter - December 2023 - Special AGU 11/02/2023 - M²LInES newsletter - November 2023 10/04/2023 - M²LInES newsletter - October 2023 09/06/2023 - M²LInES newsletter - September 2023 08/01/2023 - M²LInES newsletter - August 2023 07/03/2023 - M²LInES newsletter - July 2023 06/13/2023 - M²LInES newsletter - June 2023 05/11/2023 - M²LInES newsletter - May 2023 01/03/2023 - M²LInES newsletter - January 2023 2022 12/05/2022 - M²LInES newsletter - December 2022 AGU Special 11/01/2022 - M²LInES newsletter - November 2022 10/03/2022 - M²LInES newsletter - October 2022 09/16/2022 - M²LInES newsletter - September 2022 Research Roundup 08/01/2022 - M²LInES newsletter - August 2022 07/05/2022 - M²LInES newsletter - July 2022 06/06/2022 - M²LInES newsletter - June 2022 05/02/2022 - M²LInES newsletter - May 2022 04/01/2022 - M²LInES newsletter - April 2022 02/24/2022 - M²LInES newsletter - OSM22 special 02/01/2022 - M²LInES newsletter - February 2022 01/01/2022 - M²LInES newsletter - January 2022 2021 12/01/2021 - M²LInES newsletter - December 2021 AGU special 11/01/2021 - M²LInES newsletter - November 2021 10/01/2021 - M²LInES newsletter - October 2021 09/01/2021 - M²LInES newsletter - September 2021 08/02/2021 - M²LInES newsletter - August 2021 06/29/2021 - M²LInES newsletter - June/July 2021</description></item></channel></rss>
\ No newline at end of file