Skip to content

[GitHub Trending] google-deepmind/weathernext

7.7 relevance
Score Breakdown
technical depth
9
novelty
9
actionability
4
community
9
strategic
9
personal
6

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Google DeepMind weather model, high technical depth and strategic impact.

Open Source github.com
Contribute to google-deepmind/weathernext development by creating an account on GitHub.
Summary

Google DeepMind open-sourced WeatherNext 2 (WN2), a global medium-range atmospheric and cyclone forecasting model, alongside its predecessors GraphCast and GenCast. The repository provides pretrained weights at 0.25° resolution, including operational checkpoints fine-tuned on ECMWF HRES data, and a lightweight 1° Mini variant for local testing on single TPUs or GPUs. Forecast data feeds are accessible via Google Cloud (Earth Engine, BigQuery, Vertex AI), WeatherLab, and OpenMeteo, with cyclone-specific models that ran live during the 2025 Atlantic hurricane season.

Author

google-deepmind