NOAA

US weather service, AI global forecast models

USgovernmentnoaa.gov (opens noaa.gov)Checked 11 Oct

The brief

Analyst view
  • Runs AIGFS, an AI global model built by retraining DeepMind's GraphCast on NOAA's own weather analyses.
  • A 16-day AIGFS forecast uses 0.3% of the computing of the physics GFS and finishes in about 40 minutes.
  • HGEFS blends 31 AI and 31 physics forecasts; NOAA says no other forecaster runs such a hybrid ensemble.

Technical approach

As reported
Base model

Retrain an open AI forecaster

NOAA started from Google DeepMind's GraphCast and fine-tuned it on its own data-assimilation analyses, so it starts well from US initial conditions.

Hybrid

Mix AI and physics runs

The hybrid ensemble pools 31 AI members with 31 physics members; together they beat either set alone on most of NOAA's scores.

Project EAGLE

In-house AI program

The models came from Project EAGLE, a multi-year effort of the Weather Service, NOAA research labs, the modeling center and EPIC.

Primer