google-deepmind/jeo

Jeo: Jax model training lib for Earth Observation

47
/ 100
Emerging

This project helps Earth observation scientists and geospatial analysts train machine learning models for remote sensing tasks. It takes large-scale satellite imagery and other geospatial datasets as input and produces trained models capable of making predictions or classifications related to land use, deforestation, or environmental changes. It's designed for researchers and practitioners working on environmental monitoring and sustainability.

158 stars.

Use this if you need to develop and train machine learning models using satellite imagery and geospatial data to understand changes on Earth.

Not ideal if you are not working with large-scale geospatial datasets or if you prefer not to use the JAX and TensorFlow ecosystem for model training.

earth-observation remote-sensing deforestation-monitoring land-cover-mapping environmental-science
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

158

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Nov 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/google-deepmind/jeo"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.