Google launches WeatherNext 3, its most accurate AI weather model, trained on real satellite data
geoffwolfe · x · 2026-09-04
Google DeepMind and Google Research introduced WeatherNext 3, their most advanced global AI weather model, generating hourly high-resolution forecasts, precise precipitation predictions, and clean-energy variables.
The key differentiator: most AI weather models train on NWP model outputs with a six-hour lag, but WeatherNext 3 trains on real-world satellite observations, bypassing that constraint. It now powers forecasts in Search, the Gemini app, and Google Maps, and joins Brightband's Operational WeatherBench leaderboard.
Related event: Google DeepMind Unveils WeatherNext 3, Hourly-Updated Global Weather AI(11 posts)→
More from Models
- Simple Bench: Qwen3 27B Nearly Matches GPT-5 Pro on Common Sense Reasoning — Healthy-Nebula-3603 · 2026-09-04
- Qwen Launches QwenCloud Platform, Reveals 2.4T-Parameter Qwen3.8-Max Flagship — Alibaba_Qwen · 2026-09-04
- Apodex 1.1 hits the web with file uploads; API free for two weeks, 35B mini on HF — rohanpaul_ai · 2026-09-04
- IFM open-sources K2 Horizon fleet: six LLMs from 0.9B to a 375B MoE — tw_killian · 2026-09-04
- Apodex 1.1 Released: Training Agents to Deliver Verifiable Complete Work — rohanpaul_ai · 2026-09-04
- Apodex 1.1 trains AI agents to deliver verifiable completed work, not polished answers — rohanpaul_ai · 2026-09-04