Google launches WeatherNext 3, an AI weather model up to 5x sharper with hourly global updates
GoogleAI · x · 2026-09-04
Google DeepMind and Google Research have unveiled WeatherNext 3, their most advanced global weather AI model yet.
- Forecasts are up to 5x sharper than WeatherNext 2, capturing fast-evolving rainstorms, local temperature shifts, and even helping wind farms predict power output.
- Unlike traditional physics-based supercomputer simulations that carry a 6-hour forecast lag, WeatherNext 3 ingests live geostationary satellite observations and trains directly on real-world surface and atmospheric data.
- This enables hourly updates of the global forecast, bringing localized forecasting to billions, especially in regions historically underserved due to the high cost of traditional weather modeling.
Related event: Google Launches WeatherNext 3, Its Most Advanced Global Weather AI Model(19 posts)→
More from Models
- Opus 5.5 tops OpenRouter spending in 20 of 29 task categories — mmurph · 2026-10-21
- Meta team builds open-source 30B LLM from scratch in months, hails 'second era' — TimDarcet · 2026-10-21
- DFlash drafter for Muse Glimmer-30B: 5 layers, blockwise 16-token spec decoding — TimDarcet · 2026-10-21
- EvoPress quantization shrinks 30B model from 56GB to 19GB at near-bf16 accuracy — TimDarcet · 2026-10-21
- Radar chart: Muse Glimmer-30B benchmarked against Gemma4-31B and Qwen3.6-27B — TimDarcet · 2026-10-21
- Privacy evals: Muse Glimmer-30B leaks less than Qwen3.6-27B on CIMemories — TimDarcet · 2026-10-21