Data

Tools

Indexes

Applications

Experiments

Open Sustainable Technology

Earth2Studio

A Python-based package designed to get users up and running with AI weather and climate models fast. Our mission is to enable everyone to build, research and explore AI driven meteorology.
https://github.com/nvidia/earth2studio

Category: Climate Change
Sub Category: Earth and Climate Modeling

Keywords

ai climate-science deep-learning weather

Keywords from Contributors

transformer compose measur archiving observation conversion animals products projection threads

Last synced: about 14 hours ago
JSON representation

Repository metadata

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

README.md

Earth2Studio Banner

python version
license
coverage
mypy
format
ruff
uv

Earth2Studio is a Python-based package designed to get users up and running
with AI weather and climate models fast.
Our mission is to enable everyone to build, research and explore AI driven meteorology.

- Earth2Studio Documentation -

Install | User-Guide |
Examples | API

Earth2Studio Banner

Quick start

Install Earth2Studio:

pip install earth2studio[dlwp]

Run a deterministic weather prediction in just a few lines of code:

from earth2studio.models.px import DLWP
from earth2studio.data import GFS
from earth2studio.io import NetCDF4Backend
from earth2studio.run import deterministic as run

model = DLWP.load_model(DLWP.load_default_package())
ds = GFS()
io = NetCDF4Backend("output.nc")

run(["2024-01-01"], 10, model, ds, io)

Features

Earth2Studio provides access to pre-trained AI weather models and inference
features through an easy to use and extendable Python interface.
This package focuses on supplying users the tools to build their own
workflows, pipelines, APIs, packages, etc. via modular components including:

  • Collection of pre-trained weather/climate prediction models
  • Collection of pre-trained diagnostic weather models
  • Variety of online and on-prem data sources for initialization, scoring, analysis, etc.
  • IO utilities for exporting predicted data to user friendly formats
  • Suite of perturbation methods for building ensemble predictions
  • Sample workflows and examples for common tasks / use cases
  • Seamless integration into other Nvidia packages including PhysicsNeMo

For a more complete list of feature set, be sure to view the documentation.
Don't see what you need?
Great news, extension and customization are at the heart of our design.

Contributors

Check out the Contributing document for details about the technical
requirements and the userguide for higher level philosophy, structure, and design.

License

Earth2Studio is provided under the Apache License 2.0, please see
LICENSE file for full license text.

Citation (CITATION.cff)

cff-version: 1.2.0
message: If you use this software, please cite it as below.
title: NVIDIA Earth2Studio
authors:
  - family-names: Geneva
    given-names: Nicholas
    orcid: https://orcid.org/0000-0003-4562-459X
  - family-names: Foster
    given-names: Dallas
    orcid: https://orcid.org/0000-0001-8459-9767
url: https://github.com/NVIDIA/earth2studio
repository-code: https://github.com/NVIDIA/earth2studio
date-released: 2024-04-22

Owner metadata

GitHub Events

Total
Last Year

Committers metadata

Last synced: 11 days ago

Total Commits: 215
Total Committers: 18
Avg Commits per committer: 11.944
Development Distribution Score (DDS): 0.298

Commits in past year: 163
Committers in past year: 18
Avg Commits per committer in past year: 9.056
Development Distribution Score (DDS) in past year: 0.27

Name Email Commits
Nicholas Geneva 5****a 151
Dallas Foster d****f@n****m 28
Marius 2****s 7
Peter Harrington 4****n 5
Oliver Hennigh l****1@g****m 4
dependabot[bot] 4****] 4
Akshay Subramaniam 6****r 2
Sai Krishnan Chandrasekar 1****v 2
Jussi Leinonen j****n@n****m 2
Stefan Weissenberger s****v@g****m 2
Emmanuel Ferdman e****n@g****m 1
Kaustubh Tangsali 7****i 1
Luke Conibear 1****r 1
Manas Sahni s****s@g****m 1
Rodrigo Almeida r****4@o****t 1
Sean Lee 1****e 1
gertln g****l@n****m 1
ivanauyeung 1****g 1

Committer domains:

Issue and Pull Request metadata

Last synced: 1 day ago

Total issues: 143
Total pull requests: 306
Average time to close issues: 16 days
Average time to close pull requests: 2 days
Total issue authors: 30
Total pull request authors: 18
Average comments per issue: 0.84
Average comments per pull request: 3.17
Merged pull request: 284
Bot issues: 0
Bot pull requests: 6

Past year issues: 113
Past year pull requests: 205
Past year average time to close issues: 18 days
Past year average time to close pull requests: 3 days
Past year issue authors: 30
Past year pull request authors: 18
Past year average comments per issue: 1.03
Past year average comments per pull request: 3.11
Past year merged pull request: 183
Past year bot issues: 0
Past year bot pull requests: 6

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/nvidia/earth2studio

Top Issue Authors

  • NickGeneva (80)
  • swbg (13)
  • mariusaurus (8)
  • jleinonen (5)
  • dallasfoster (4)
  • rodrigoalmeida94 (3)
  • gertln (3)
  • luke-conibear (3)
  • david5010 (2)
  • hauke-dttl (2)
  • ShihengDuan (1)
  • bfouquet (1)
  • mike-scchen (1)
  • awesomemfg (1)
  • juliusberner (1)

Top Pull Request Authors

  • NickGeneva (202)
  • dallasfoster (43)
  • loliverhennigh (11)
  • mariusaurus (10)
  • pzharrington (9)
  • dependabot[bot] (6)
  • gertln (6)
  • jleinonen (5)
  • akshaysubr (2)
  • saikrishnanc-nv (2)
  • swbg (2)
  • rodrigoalmeida94 (2)
  • SeanSBLee (1)
  • sahnimanas (1)
  • ivanauyeung (1)

Top Issue Labels

  • bug (79)
  • enhancement (45)
  • documentation (24)
  • 2 - In Progress (15)
  • 1 - On Deck (15)
  • question (8)
  • 0 - Backlog (7)
  • ? - Needs Triage (7)
  • 0 - Blocked (1)
  • wontfix (1)

Top Pull Request Labels

  • 4 - In Review (15)
  • 2 - In Progress (13)
  • 3 - Ready for Review (11)
  • dependencies (6)
  • python (6)
  • 1 - On Deck (5)
  • ! - Release (4)
  • 5 - DO NOT MERGE (2)
  • bug (1)
  • enhancement (1)

Package metadata

pypi.org: earth2studio

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

  • Homepage: https://github.com/NVIDIA/earth2studio
  • Documentation: https://nvidia.github.io/earth2studio
  • Licenses: Apache Software License
  • Latest release: 0.7.0 (published 18 days ago)
  • Last Synced: 2025-06-06T15:02:13.717Z (1 day ago)
  • Versions: 7
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 1,070 Last month
  • Rankings:
    • Dependent packages count: 9.459%
    • Average: 35.931%
    • Dependent repos count: 62.403%
  • Maintainers (1)

Dependencies

.github/workflows/blossom-ci.yml actions
  • NVIDIA/blossom-action main composite
  • actions/checkout v2 composite
pyproject.toml pypi
  • boto3 >=1.34.50
  • cdsapi >= 0.6.1
  • cfgrib >= 0.9.10.3
  • cftime *
  • eccodes >=1.4.0
  • ecmwf-opendata >=0.2.0
  • ecmwflibs >=0.5.2
  • fsspec >=2023.1.0
  • gcsfs *
  • h5netcdf >=1.0.0
  • h5py >=3.2.0
  • herbie-data *
  • huggingface-hub >=0.4.0
  • importlib_metadata *
  • loguru *
  • netCDF4 >=1.6.4
  • numpy *
  • nvidia-modulus >= 0.4.0
  • python-dotenv *
  • s3fs >=2023.5.0
  • setuptools >=67.6.0
  • torch >=2.0.0
  • torch_harmonics >=0.5.0
  • tqdm >=4.65.0
  • xarray >=2023.1.0
  • zarr >=2.14.2
setup.py pypi

Score: 15.174987525745118