Skip to content
RichseenAtlas← AtlasSign in

GenCast is published with a like-for-like comparison against an operational ensemble

node

DeepMind published GenCast in Nature, reporting that it outperformed the ECMWF ensemble on 97.2% of 1,320 evaluation targets while producing a fifteen-day global forecast in about eight minutes on a single accelerator, against hours of supercomputer time. The comparison was against an operational system's own output on that system's own measures, which is a far stronger evidential position than a self-selected benchmark.

A node is not a place. Drawing it on a map would assert something about the world that no stored fact supports.

Read in · 1

Evidence · 1
Timeline

No dated observations are stored for this object. Atlas shows what was observed and when — it does not infer a history.

Connections · 2
Assembled narrative · 1

Assembled from 22 blocks · 1 evidence · 33 related

  1. Story
  2. DeepMind published GenCast in Nature, reporting that it outperformed the ECMWF ensemble on 97.2% of 1,320 evaluation targets while producing a fifteen-day global forecast in about eight minutes on a single accelerator, against hours of supercomputer time. The comparison was against an operational system's own output on that system's own measures, which is a far stronger evidential position than a self-selected benchmark.
  3. Knowledge
  4. Machine-learned weather forecasting
  5. Google DeepMind
  6. GenCast is published with a like-for-like comparison against an operational ensemble
  7. Connections
  8. Machine-learned weather forecasting
  9. Google DeepMind
  10. Deep learning
  11. European Centre for Medium-Range Weather Forecasts
  12. GenCast is published with a like-for-like comparison against an operational ensemble
  13. ECMWF makes a machine-learned forecast model operational
  14. AlphaFold
  15. GNoME and the materials-discovery claim
  16. London
  17. AlphaGo defeats Lee Sedol in Seoul
  18. AlphaFold2 is assessed blind at CASP14
  19. GNoME is announced as 2.2 million new crystal structures
  20. GenCast is published with a like-for-like comparison against an operational ensemble
  21. Evidence
  22. ECMWF's Artificial Intelligence Forecasting System became operational on 25 February 2025, outperforming the physics-based system on many measures including tropical cyclone tracks with gains of up to 20%; GenCast, published in Nature in December 2024, is reported to have beaten the ECMWF ensemble on 97.2% of 1,320 evaluation targets and to produce a fifteen-day global forecast in about eight minutes on a single accelerator. V55 verification basis: neither ecmwf.int nor nature.com was fetched. The operational date and the up-to-20% figure were carried in search results attributing them to ECMWF's own news item; the 97.2%, 1,320-target and eight-minute figures were carried with attribution to the Nature paper and to reporting of it.
Close the narrative
Observed changes · 0

No public Signals are attached to this object. Signals show what changed and when it was observed — never a direction or a rank.

Actions

Read the assembled narrativeContinue in StudioOpen TwinTwin does not start a decision from this kind of object.ShareSaveSaved objects are part of the authenticated projection, which is declared and not yet built.

/atlas?object=EVT_GENCAST_NATURE_2024&experience=EVT_GENCAST_NATURE_2024