Learning skillful medium-range global weather forecasting

TLDR

Global medium‑range weather forecasting is vital for many sectors, yet traditional numerical methods rely mainly on increased compute rather than historical data to improve accuracy. The study introduces GraphCast, a machine‑learning method trained directly from reanalysis data. GraphCast predicts hundreds of weather variables for the next ten days at 0.25° global resolution in under a minute. GraphCast outperforms leading deterministic systems on 90 % of 1,380 verification targets, improving severe event prediction such as tropical cyclones, atmospheric rivers, and extreme temperatures, marking a key advance in accurate and efficient weather forecasting.

Abstract

Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy but does not directly use historical weather data to improve the underlying model. Here, we introduce GraphCast, a machine learning-based method trained directly from reanalysis data. It predicts hundreds of weather variables for the next 10 days at 0.25° resolution globally in under 1 minute. GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclone tracking, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting and helps realize the promise of machine learning for modeling complex dynamical systems.