Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors". Modifications made to the README file, training data files, and Python code scripts in the interest of addressing manuscript reviewer comments.

Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors". Additional Python 3 scripts have been added for the training and usage of random forest ensemble machine learning algorithms to predict a processing space of two axes: one of radio frequency (RF) plasma power level and the other of substrate (growth) temperature as measured by a thermocouple making physical contact with the back side of the substrate mounting block during the growth process. These Python 3 scripts have been updated to add additional explanatory information. This has included renaming the files as well as adding descriptive comments to the scripts themselves in order to distinguish them from the other Python 3 scripts used to generate mapping data for predicting S^2 across a processing space defined by substrate temperature and initial nitrogen pressure axes using a trained random forest algorithm.

Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors". Additional Python 3 scripts have been added for the training and usage of random forest ensemble machine learning algorithms to predict a processing space of two axes: one of radio frequency (RF) plasma power level and the other of substrate (growth) temperature values.

Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors". "Data" directory has been updated with the revision of the "GaN Lattice Disorder.csv" file. Additional information included in the README file.

Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors". "Data" directory has been updated with the revision of the "GaN Lattice Disorder.csv" file.

Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors

Release generated to cite the repository in the manuscript titled "Machine learning–based investigation of optimal synthesis parameters for epitaxially–grown III–nitride semiconductors".