Google launches WeatherNext 3: AI weather model with real-time satellite data and hourly updates
ymatias · x · 2026-09-04
Google DeepMind and Google Research officially launched WeatherNext 3, their most accurate AI weather model yet. It now learns directly from real-time geostationary satellite observations, bypassing the 6-hour data lag of traditional numerical weather prediction, generating hourly forecasts at up to 5-km resolution. Trained on NASA's IMERG and Google's own satellite-radar-based precipitation reanalysis, it achieves up to 60% CRPS improvement against IMERG, and adds precise precipitation forecasting and clean-energy variables.
Related event: Google Launches WeatherNext 3, Its Most Advanced Global Weather AI Model(19 posts)→
More from Research
- Stanford team launches ScholarCatalyst benchmark for inspiration retrieval — lateinteraction · 2026-10-21
- Holon-S1 predicts gene activity and biomarkers from routine pathology slides — altryne · 2026-10-21
- Three reasons AI is not conscious and may never be, per Nature essay — anilkseth · 2026-10-21
- Aviation tracks every part's provenance — agents can reason over that graph — colinmcnamara · 2026-10-21
- SFT details: instruction/reasoning/code/math mix, synthetic + human traces, no epoching — TimDarcet · 2026-10-21
- Mid-training recipe disclosed: 32k→131k context extension, dropping logit distillation for tokens — TimDarcet · 2026-10-21