NVIDIA/earth2studio
Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.
Provides a unified interface to multiple state-of-the-art AI weather models (GraphCast, Pangu, Aurora, AIFS, StormCast) with pluggable data sources (GFS, IFS, satellite observations) and output backends, enabling composition of complex multi-model pipelines. Built as a modular inference toolkit supporting prognostic models for time-series forecasting, diagnostic models for derived quantities, and data assimilation workflows, all sharing a consistent API across different underlying frameworks.
694 stars and 7,638 monthly downloads. Actively maintained with 47 commits in the last 30 days. Available on PyPI.
Stars
694
Forks
155
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Monthly downloads
7,638
Commits (30d)
47
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/earth2studio"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
mllam/neural-lam
Research Software for Neural Weather Prediction for Limited Area Modeling
chengtan9907/OpenSTL
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
aditya-grover/climate-learn
Source code for ClimateLearn
NVIDIA/earth2mip
Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate...
microsoft/aurora
Implementation of the Aurora model for Earth system forecasting