This is a lightweight web-interface for creating and sharing vector annotations over satellite/aerial imagery scenes.

SITS - Satellite Image Time Series toolkit for annotation, classification, and clustering

One line code to get any remote sensing foundation model embeddings for any place and any time

Github Action to setup Spack

Prettier is an opinionated code formatter.

GlobalBuildingAtlas: an open global and complete dataset of building polygons, heights and LoD1 3D models

Democratizing planetary-scale analysis: An ultra-lightweight Earth embedding database for accurate and flexible global land monitoring

Earth Vision Foundation

🛰️ GeoAI.js is a javascript library for use with transformers.js to perform GeoAI on the frontend

Laspy is a pythonic interface for reading/modifying/creating .LAS LIDAR files matching specification 1.0-1.4.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

GoldenEye is a library of geospatial vision-language models -- run any geospatial VLM in three lines of code

A unified PyTorch framework for semantic segmentation of satellite imagery. Supports multi-spectral data, state-of-the-art architectures, and seamless large-scale inference for Earth Observation ap…

Code to reproduce datasets and experiments from SSL4EO-L paper

Code to reproduce experiments in TorchGeo paper

Quickly rewrite git repository history (filter-branch replacement)

A Python package for installing commonly used packages for geospatial analysis and machine learning with only one command.

Expandable Datasets for Earth Observation

Information hub for our project training the largest possible historical LLMs.

A curated list of papers that focus on how to represent Earth data in embedding space — spatial, temporal, or semantic — and how those embeddings behave or are applied.

The code coverage tool for Python

Official code repository of Sen12Landslides

A python package for end-to-end geospatial machine learning using multispectral earth observation data such as NASA HLS and ESA Sentinel-2.

Jeo: Jax model training lib for Earth Observation

Acceptance rates for the major AI conferences

Code for GEO-Bench V2 datasets. Made in collaboration with TUM, IBM and ServiceNow.

Scikit-learn applied to mapping and spatial prediction

A tool for benchmarking and hyper-parameter optimization using TerraTorch. Leverages MLFlow for experiment logging, optuna for hyperparameter optimization and ray for parallelization.