# NVIDIA/earth2studio

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

Repository: https://github.com/NVIDIA/earth2studio
Canonical: https://ross.abutalabs.com/products/earth2studio
Homepage: https://nvidia.github.io/earth2studio/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, climate-science, deep-learning, weather
Last push: 2026-09-02T22:49:45+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 100, release rhythm 88, longevity 62
- inputs: {"age_days": 880, "days_push": 0, "days_rel": 2, "gap_med": 34, "n_releases_24m": 18}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1112, forks 253 (observed 2026-09-03T02:15:06.819668+00:00)

## What it is
Earth2Studio is a Python deep-learning framework from NVIDIA for building, exploring, and deploying AI-driven weather and climate workflows. It provides ready-to-use AI weather models (e.g., FourCastNet3), data sources, and inference pipelines runnable in a few lines of code.

## Use cases
- run AI weather forecast with FourCastNet
- build deep learning weather prediction workflows
- fetch ERA5 or GFS data for climate research
- deploy AI climate models for inference
- compare AI weather models on GPU
- generate deterministic forecasts from GFS data

## When to choose
- you want to run or experiment with AI weather/climate models in Python
- you need GPU-accelerated forecast inference with pluggable models and data sources
- you are doing research on AI-driven earth system modeling

## When to avoid
- you need traditional numerical weather prediction (NWP) solvers
- you need a general-purpose climate data analysis or visualization tool without AI models
- you cannot use GPU resources

## Facets
- artifact type: library
- maturity: active
- function: deep-learning, machine-learning, data-science, sdk
- domain: weather, artificial-intelligence, deep-learning, data-science
- platform: python, cloud
- tags: weather-forecasting, climate-modeling, ai-weather-models, earth-system-science, inference-workflows, nvidia, climate-science, linux, gpu

## Member repositories
- NVIDIA/earth2studio (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.819668+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:46:38.471530+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/earth2studio (fetched 2026-09-03T02:15:06.819668+00:00, sha 3000c96e5edf)
  - homepage: https://nvidia.github.io/earth2studio/ (fetched 2026-08-29T12:50:07.681746+00:00, sha 99ef38696945)
  - registry_pypi: https://pypi.org/pypi/earth2studio/json (fetched 2026-08-29T12:50:07.684856+00:00, sha 45d2db4d1d25)
- Data as of 2026-08-30T08:39:29.467469+00:00.