Post-Cutoff.com
  1. Home
  2. Timeline
  3. 2023
  4. GraphCast: ML weather model beats the world's best…

GraphCast: ML weather model beats the world's best physics-based 10-day forecast on 90% of targets

★★★★scienceGoogle DeepMindconfidence: high

GraphCast (Science, Nov 2023), a graph neural network trained on ECMWF reanalysis data, produced 10-day global forecasts in under a minute on one TPU. It beat ECMWF's HRES, the leading deterministic physics model, on 90.3% of 1,380 verification targets. It later became the basis of NOAA's operational AIGFS.

Key facts

Science result

Field
climate-weather / medium-range weather forecasting
Problem
Global medium-range weather prediction
Result
Learned model outperforming the top operational physics-based deterministic forecast on most variables and lead times.
AI system
GraphCast
Human role
Human-designed model; forecasts automated
Verification
Peer-reviewed in Science; operational adoption
Status
confirmed
Why surprising
A model trained on 39 years of reanalysis beat decades of numerical weather prediction engineering on most metrics at a fraction of the compute.

What happened

DeepMind showed that a learned simulator could beat physics-based weather prediction on standard skill scores.

Why it matters

It triggered the rapid move of AI weather models into operational forecasting worldwide.

Changelog

  • 2026-09-29: created

Related events

  1. GenCast: diffusion-based ensemble forecast beats ECMWF's ENS on 97% of targets ★★★
  2. AI weather forecasting goes operational: ECMWF's AIFS (Feb 2025), then NOAA's AI models (Dec 2025) ★★★★
  3. DeepMind open-sources WeatherNext 2 and WeatherNext Cyclones with a Nature paper showing ~1 extra day of hurricane warning ★★★
  4. NeuralGCM: Google's hybrid physics-ML atmosphere model matches top weather forecasts and runs decades-long climate simulations ★★★

Sources (3)

id: 2023-11-14-graphcast-weather · updated 2026-09-29 · open in the interactive timeline