Skip to content
RichseenAtlasAtlasSign in

ECMWF makes a machine-learned forecast model operational

node

The European Centre for Medium-Range Weather Forecasts brought its Artificial Intelligence Forecasting System into operational service, reporting gains of up to 20% over the physics-based system on several measures including tropical cyclone track error. An intergovernmental agency whose forecasts are used for aviation, shipping and emergency planning thereby accepted operational accountability for learned-model output. It did not switch the physics-based system off: the numerical model still produces the reanalysis the learned model is trained on, so the two are complements and the learned model cannot outrun its own training source.

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 17 blocks · 1 evidence · 9 related

  1. Story
  2. The European Centre for Medium-Range Weather Forecasts brought its Artificial Intelligence Forecasting System into operational service, reporting gains of up to 20% over the physics-based system on several measures including tropical cyclone track error. An intergovernmental agency whose forecasts are used for aviation, shipping and emergency planning thereby accepted operational accountability for learned-model output. It did not switch the physics-based system off: the numerical model still produces the reanalysis the learned model is trained on, so the two are complements and the learned model cannot outrun its own training source.
  3. Knowledge
  4. Machine-learned weather forecasting
  5. European Centre for Medium-Range Weather Forecasts
  6. ECMWF makes a machine-learned forecast model operational
  7. Connections
  8. European Centre for Medium-Range Weather Forecasts
  9. Machine-learned weather forecasting
  10. Machine-learned weather forecasting
  11. ECMWF makes a machine-learned forecast model operational
  12. Deep learning
  13. European Centre for Medium-Range Weather Forecasts
  14. GenCast is published with a like-for-like comparison against an operational ensemble
  15. ECMWF makes a machine-learned forecast model operational
  16. Evidence
  17. 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_ECMWF_AIFS_OPERATIONAL_2025&experience=EVT_ECMWF_AIFS_OPERATIONAL_2025