Scientific AI & Physics ML

Open-source deep learning framework for physics-informed machine learning (Physics-ML). Build, train, and fine-tune models for AI4science and engineering applications using state-of-the-art SciML methods. Apache 2.0 licensed.

PyTorch domain library for geospatial data. Datasets, samplers, transforms, and pre-trained models for multispectral satellite imagery and remote sensing. First library with pre-trained models for Sentinel-2 bands. MIT licensed.

Core library for astronomy and astrophysics in Python. Comprehensive tools for celestial coordinates, FITS I/O, cosmological calculations, and data analysis for professional astronomy. BSD-3-Clause licensed.