The weather forecast just stopped needing a physics engine to win. google deepmind's gencast beats…
the weather forecast just stopped needing a physics engine to win. google deepmind's gencast beats the european gold standard ecmwf on 97.2 percent of 1,320 forecast targets while producing 15-day outlooks in eight minutes, and the stanford startup windborne claims its weathermesh 6 model already out-forecasts the same agency across all variables from one to ten days.
the next forecast you trust may come from a gpu farm, not a supercomputer.
Context
Verified source: DeepMind's GenCast paper in Nature (Dec 4, 2024) says it has greater skill than ECMWF's ENS ensemble on 97.2% of 1,320 variable, lead time and level combinations. WindBorne's Jun 1, 2026 post says WeatherMesh-6 is more accurate than ECMWF's IFS and AIFS ensembles across every parameter and lead time it evaluated.
The 97.2% of 1,320 targets matches the Nature paper, which compares against ENS, ECMWF's ensemble, and dates from Dec 2024, not recent news. The paper notes the 1,320 targets are not independent forecast tasks. That 15-day forecasts take eight minutes was not seen in the sources read, so unsupported here, not refuted. in the excerpts read. WindBorne's claim is its own and covers the lead times it evaluated; the post's 'one to ten days' was not seen in the sources read, so unsupported here, not refuted. in the post read. 'No physics engine' and 'gpu farm' are the author's framing.
Related work
- WindBorne WeatherMesh-6, AI Weekly ↗Jun 1, 2026.
Watch next
- Check the GenCast post for the forecast generation time per 15-day ensemble member.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 24 September 2026 at 21:08 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →