NVIDIA/earth2mip
Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate researchers and scientists to inter-compare AI models for weather and climate.
This tool helps climate researchers and scientists compare different AI models for weather and climate prediction. You can input various pre-trained AI weather models and historical atmospheric data, then run simulations to see how well each model predicts future weather conditions. It outputs scores and metrics like ACC/RMSE, allowing you to evaluate and understand the strengths and weaknesses of different AI approaches in capturing Earth's atmospheric physics.
254 stars.
Use this if you are a climate researcher or scientist who wants to experiment with and compare various AI models for weather and climate forecasting.
Not ideal if you are looking for a production-ready weather forecasting system or a tool for real-time operational weather prediction.
Stars
254
Forks
54
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIA/earth2mip"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
NVIDIA/earth2studio
Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.
mllam/neural-lam
Research Software for Neural Weather Prediction for Limited Area Modeling
chengtan9907/OpenSTL
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
microsoft/aurora
Implementation of the Aurora model for Earth system forecasting
aditya-grover/climate-learn
Source code for ClimateLearn