Google's WeatherNext 3 AI weather model adds satellite data to cut forecast lag
Ars Technica AI · rss · 2026-09-09
Google released version 3 of its WeatherNext AI weather model, whose biggest change is ingesting satellite weather data to shorten the lag between observed conditions and new forecasts.
AI weather models match traditional numerical forecast performance while needing far less compute, so they can run more often. The update is detailed in a white paper, covering techniques like reanalysis—fusing diverse weather data into a consistent global atmospheric snapshot with estimates for unmeasured regions.
More from Research
- Researchers identify "Forking": train loss falls while validation loss turns up — ZimingLiu11 · 2026-10-26
- Google DeepMind pilots world's first double-blind evaluations for frontier models — scychan_brains · 2026-10-26
- Rewriting scaling law study: optimal synthetic data share rises from 10% to 32% with compute — heghbalz · 2026-10-26
- FLASH: GPU-native deformable sim learns cloth folding in minutes on one RTX 5090 — ChongZzZhang · 2026-10-26
- LEMON: zero-shot LLM misbehavior monitor flags hallucinations from attention maps — yoavartzi · 2026-10-26
- Behind the EMNLP keynote: LMs as simulated learners to generate child language acquisition hypotheses — najoungkim · 2026-10-26