Increasing shared understanding of our world by expanding access to geospatial data and machine learning models.

Our initiatives

Radiant MLHub

Radiant MLHub is the world’s first cloud-based open library dedicated to Earth observation training data for use with machine learning algorithms.

Access open datasets and machine learning models from NASA, Planet, University of Maryland and others at


The SpatioTemporal Asset Catalogs (STAC) metadata specification is a common language to describe geospatial information to make it more accessible and interoperable.

Learn more about STAC at

Machine Learning Challenges

We help organize challenges to create capacity building opportunities and accelerate development of machine learning models to interpret Earth observation data.

Learn about our current challenge to detect field boundaries in Rwanda.

Our blog