Skip to content

[GitHub Trending] google-deepmind/weathernext

6.8 relevance
Score Breakdown
technical depth
8
novelty
8
actionability
4
community
7
strategic
7
personal
6

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

DeepMind's weather prediction model, technically deep but not directly aligned with the reader's focus.

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 weather and cyclone forecasting model at 0.25° resolution, alongside its predecessors GraphCast and GenCast. The repository provides pretrained weights for operational and research use, including a lightweight Mini variant for single TPU/GPU inference, and offers forecast data feeds via Google Cloud, WeatherLab, and OpenMeteo. WN2 is fine-tuned on ECMWF HRES data and has been operational during the 2025 Atlantic hurricane season under the FNV3 designation.

Author

google-deepmind