← Discover
Discover · GitHub · Weathernext↑ +86 today

Fast weather forecast with artificial intelligence

WeatherNext, developed by Google DeepMind, is a model that uses generative artificial intelligence (generative AI) for weather forecasts. It aims to make faster and higher resolution atmospheric predictions compared to traditional physical simulations.

Updates

  • August 10, 2026: Stars 7,148 → 7,149, latest release v0.3.0 (August 6, 2026).

What you get

  • Makes medium-term atmospheric weather forecasts.
  • Performs hurricane tracking and analysis.
  • It offers high resolution data processing capacity.

Installation

Library installation
pip install git+https://github.com/google-deepmind/weathernext.git@v0.3.0

If you don't write code

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

I need to make a medium-term weather forecast for a specific region using the WeatherNext model. How can I load model weights via Google Cloud Bucket and start the forecast cycle by processing weather data (like temperature, wind speed)? Can you specifically explain the steps required for hurricane tracking?

Related dictionary terms

Google CloudGenerative AIArtificial Intelligence
Who it is forIt is suitable for researchers working with meteorological data and data scientists who want to develop high-resolution atmospheric forecast models.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-10: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.