Google DeepMind launches WeatherNext 3 with up to 50% more accurate precipitation forecasts
PeterWBattaglia · x · 2026-09-03
Google DeepMind unveiled WeatherNext 3, its most powerful AI weather forecasting model yet: hourly high-resolution forecasts, training on new data sources including live satellites, and state-of-the-art skill per independent evaluations by Brightband. Its standout feature is precipitation forecasting—up to 50% more accurate, with the biggest gains in historically under-served regions—plus new variables for renewable energy forecasting like turbine-height wind speed.
More from Research
- New arXiv paper quantifies CoT necessity via opaque serial depth amid OpenAI architecture rumors — ArthurConmy · 2026-09-04
- Tabular Deep Learning for Trading: Cross-Regime Bayesian Optimisation for Equity Signals — PtrPomorski · 2026-09-04
- Nature Human Behaviour: short funding cycles and productivity metrics stifle creative science — S_OhEigeartaigh · 2026-09-03
- A huge 176-digit integer is claimed to divide RSA-260, unverified — CatAstro_Piyush · 2026-09-03
- Kimi K3 Draft Collection released: EAGLE-3, DFlash2 and DSpark draft models trained on GB200 — hongyangzh · 2026-09-03
- Nature Biotech paper: reference materials as common calibrator to make multiomics data AI-ready — kshameer · 2026-09-03