microsoft/aurora

Implementation of the Aurora model for Earth system forecasting

48
/ 100
Emerging

# Technical Summary A foundation model pretrained on diverse Earth system datasets (ERA5, CMIP6, CAMS) that adapts to specialized forecasting tasks including medium/high-resolution weather, air pollution, and ocean wave prediction. Built as a neural network that processes surface variables, atmospheric levels, and static geographic data through a unified architecture. Provides pip/conda installation with pretrained checkpoints and integrates with standard PyTorch workflows for atmospheric variable prediction from ERA5-formatted inputs.

847 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 23 / 25

How are scores calculated?

Stars

847

Forks

140

Language

Python

License

Last pushed

Nov 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/microsoft/aurora"

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