Skip to content

About

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

Resources

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

 
 

Latest commit

 

History

904 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Important

1.0.0: This is a major release with breaking changes from pre-1.0 releases. See the migration guide if you need help transitioning, or point your agent to it. To install the legacy version, please refer to the 0.20.0 installation instructions.

NVIDIA Earth2Studio

Next-generation AI weather and climate modeling.

python version license Maturity: L3 Strategic coverage uv

Install | User Guide | Examples | API | Skills

Access a leading collection of weather and climate AI models, production-ready data sources, composable inference APIs, and GPU-accelerated workflows in one Python package.

Earth2Studio hero

Get Started

Paste this into your coding agent (Claude, Codex, OpenCode, Cursor, etc.):

Help me get started with Earth2Studio.
https://github.com/NVIDIA/earth2studio

AGENTS.md routes usage and development tasks to the relevant documentation and skills. Learn more, install, and start forecasting with just a few prompts:

# Learn about the latest release
Summarize new models and features in the latest Earth2Studio release.
Include the version, release date, and links to the release notes.

# Create a forecasting pipeline
Create a 10-day AI forecasting pipeline starting from the latest GFS analysis.

# Set up a Python environment for a specific model
Set up my environment for FourCastNet3 inference.

# Find a model for your forecast and hardware
Recommend the best model for a 2-week global forecast on one GPU.

# Explore models that predict a specific product
What models do you have that support predicting precipitation?

# Download weather data
Fetch ERA5 surface winds for March 2024 and save them to Zarr.

To keep the skills installed, add them from this repository:

npx skills add NVIDIA/earth2studio --skill earth2studio-install
npx skills add NVIDIA/earth2studio --skill earth2studio-discover

Installation and Examples

Each model has different dependencies; the install guide provides the exact commands for your setup.

Resource What's there
Install Environments, model-specific extras, hardware
Examples Deterministic, ensemble, diagnostic and coupled workflows
User Guide Components, design philosophy and extending the package
API Every prognostic, diagnostic and data source

Main Features

  • Forecast with global and regional prognostic AI models.
  • Diagnose derived fields such as precipitation, wind speed and downscaled output.
  • Assimilate sparse observations into global and regional analyses.
  • Fetch analysis, forecast and observation data from public sources.
  • Compose ensembles and coupled multi-model workflows.
  • Store results to Zarr, NetCDF and more.

Documentation

Everything else (model zoo, data sources, news, tutorials) lives on the documentation site. See the changelog for what is new, CONTRIBUTING to get involved, and Earth-2 Open Models for NVIDIA's open weights and PhysicsNeMo for training recipes. For deploying workflows as an inference service, see PhysicsNeMo Serve.

Warning

NOTICE AND DISCLAIMER: This software automatically retrieves, accesses or interacts with external materials. Those retrieved materials are not distributed with this software and are governed solely by separate terms, conditions and licenses. You are solely responsible for finding, reviewing and complying with all applicable terms, conditions, and licenses, and for verifying the security, integrity and suitability of any retrieved materials for your specific use case. This software is provided "AS IS", without warranty of any kind. The author makes no representations or warranties regarding any retrieved materials, and assumes no liability for any losses, damages, liabilities or legal consequences from your use or inability to use this software or any retrieved materials. Use this software and the retrieved materials at your own risk.

License

Apache License 2.0, see the LICENSE file.

About

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

Resources

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages