This repository contains the code used in the paper: A high-resolution canopy height model of the Earth. Here, we developed a model to estimate canopy top height anywhere on Earth. The model estimates canopy top height for every Sentinel-2 image pixel and was trained using sparse GEDI LIDAR data as a reference.

ICESat-2 ATL03/ATL08 Processing and Analysis

This project uses satellite images on Google Earth Engine to predict canopy height and estimate carbon content in the University of Malaya forest area.

Easy download of NEON LiDAR products in a scalable manner.

Python scripts for extracting GEDI and ICESat-2 data from HDF to shapefiles

A browser-based tool for interactive 3D visualization of canopy height model (CHM) datasets, built entirely in JavaScript. It allows users to load and explore multiple CHM GeoTIFF tiles directly in the browser—no build tools required.

This repository is a fork of https://github.com/langnico/global-canopy-height-model/ and contains the code used to create the results presented in the paper: A high-resolution canopy height model of the Earth. The model estimates canopy top height for Sentinel-2 images

R-based script for processing lidar point cloud data, generating and visualizing Digital Surface Model (DSM) and Digital Terrain Model (DTM), and extracting forest canopy metrics based on the lidR package.

Tutorial for creating DSM from LiDAR data in R

This project automates large-scale lidar processing to create forest structure and change maps. Built using lidR and python libraries, the workflow handles tiling, metric calculation, and differencing, and is parallelized for big data. As part of OpenForest4D, this pipeline enables repeatable, multi-temporal forest metrics to support conservation.

R functions for extracting forest information from lidar-derived Canopy Height Models (CHMs). Based on carlos-alberto-silva/weblidar-treetop, the scripts have been refactored into standalone, modular functions better suited for automated or batch processing.

This project provides an automated workflow for large-scale lidar data processing to map forest structure and change maps. Using lidR, Python libraries, it manages tiling, metric computation, and differencing, and is parallelized to handle big data efficiently. The pipeline enables repeatable multi-temporal forest metrics to support conservation.

This repository...