software · Global

Earth2Studio

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

Claim this listing

Represent Earth2Studio? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.

Data offered docs-verified: AI weather/climate model inference (e.g. FourCastNet3, ECMWF AIFS, GraphCast) · Input data sources (e.g. GFS, IFS, ERA5) · Forecast output to Zarr stores · Statistical operations and pipeline composition
Coverage llm-inferred: Depends on model/data source: several global models (e.g. FourCastNet3, GraphCast); CorrDiff ERA5-HRRR covers the contiguous United States
Formats docs-verified: Python package · Zarr (via ZarrBackend)
Access docs-verified: Free and open source under Apache-2.0. Underlying model checkpoints and datasets are licensed by their providers and must be checked individually.

Use cases llm-inferred: Pull ERA5 surface winds for a historical event as meteorological context for an environmental or civils assessment · Run a short deterministic forecast (e.g. FourCastNet3) to inform short-range weather-risk planning for site works · Bulk-fetch GFS or IFS fields into Zarr as preprocessing for hydrological or drainage model inputs · Prototype AI downscaling (e.g. CorrDiff ERA5-HRRR) for US-based comparison studies
Audience llm-inferred: Hydrologists · Climate and meteorological scientists · Python developers · GIS analysts

Constraints llm-inferred: Model-specific installation steps are required · Python 3.11 to 3.14 per the badge in the README · Third-party model and dataset licences apply and must be checked per asset · Framework only; no UK-specific datasets or regional coverage are described in the docs · Requires a Python environment; not a plug-and-play MCP server

Auto-extracted, unverified fields: tools, install, auth. Check upstream documentation.

Verified via GitHub API (2026-10-15). Tools/install/auth auto-extracted from README.

Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Chris sources (NVIDIA Earth-2))