Popular GitHub Repositories for Earth Observation

?? List of satellite image training datasets with annotations for computer vision and deep learning

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

The Clay Foundation Model - An open source AI model and interface for Earth

a Python toolkit for fine-tuning Geospatial Foundation Models (GFMs). https://ibm.github.io/terratorch/

Lightning-UQ-Box: Uncertainty Quantification for Neural Networks with PyTorch and Lightning

Code for Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities

This includes short and minimalistic few examples covering fundamentals of Deep Learning for Satellite Image Analysis (Remote Sensing).

Using StableDiffusion and ControlNet to generate synthetic aerial images

Official PyTorch implementation and benchmark dataset for IGARSS 2024 ORAL paper: "Composed Image Retrieval for Remote Sensing"

This repository contains code to download data for the preprint "MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning"

Semantic segmentation from aerial imagery (baseline of the FLAIR #1 challenge)

Code repository for "Parameter Efficient Self-supervised Geospatial Domain Adaptation", CVPR 2024

Course materials for the IGARSS 2023 Tutorial "Efficient Deep Learning for Earth Observation"

ODEON is a task-agnostic framework for deep learning applied to remote sensing

Official repo for 'Generating Physically-Consistent Satellite Imagery for Climate Visualizations'

EuroCropsML is a ready-to-use benchmark dataset for few-shot crop type classification using Sentinel-2 imagery.

"Evaluating Digital Agriculture Recommendations with Causal Inference". It was accepted and presented in the special track on Artificial Intelligence for Social Impact, AAAI-23

[IEEE T-GRS 2025] The official repository of "Spatioformer: A Geo-encoded Transformer for Large-Scale Plant Species Richness Prediction"

:earth_africa: An Earth Observation toolkit written in Rust for use in Python. Python is a popular language for Earth Observation; however, it is so slow for any pixel-wise operations over large areas! This Python packages aims to speed this all up.

Using Computer Vision, ML, ESRGAN, and Image Processing to find the best sunsets across the ocean.