DeepMind's weather model ingests raw satellite radiances hourly, ending the 6-12h analysis lag
burny_tech · x · 2026-09-21
Most AI weather models 'cheat' by forecasting from physics analyses that lag reality by 6-12 hours.
Google DeepMind has collapsed data assimilation and forecasting into a single model that ingests raw satellite radiances directly and updates every hour — eliminating the dependence on stale analysis fields and marking a substantive engineering leap for AI weather prediction.
More from Research
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Gait dataset labeled by encounter, spanning pre-op to 3 months post-TKA — zawthet · 2026-11-12
- Walking alignment measured 2.5-3.1° more neutral than X-ray, iPad gait study finds — zawthet · 2026-11-12
- MIT's Tegmark coins 'formal-washing': Signal protocol proof is far from complete — tegmark · 2026-11-12
- Signal formal verification hits 80%, Tegmark says Wired overstated completion — tegmark · 2026-11-12
- Category-theoretic framework asks: when does a physical system actually compute? — neurovium · 2026-11-12