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
- Reverse-engineering Jev: its architecture, philosophy, and where it falls down — iamrobotbear · 2026-09-21
- Honglak Lee at Nobel Prize Dialogue: AI accelerates science, but skepticism matters more — honglaklee · 2026-09-21
- HF's Merve Noyan shares beginner guides for zero-shot classifiers, says many LLM tasks never needed them — ceciletamura · 2026-09-21
- Two independent results suggest multimodal models still need SSL backbone features — kalomaze · 2026-09-21
- Researchers formally verify the Kubernetes control plane with a compositional CORE spec — tianyin_xu · 2026-09-21
- Astra shows any 3D/4D prior can be distilled into VLMs, a new embodied AI paradigm — mariyaivasileva · 2026-09-21