GraphCast: Learning skillful medium-range global weather forecasting

By Rémi R. Lam, Alvaro Sanchez-Gonzalez, M. Willson, Peter Wirnsberger, Meire Fortunato, Alexander Pritzel, Suman V. Ravuri, Timo Ewalds, Ferran Alet, Z. Eaton-Rosen and 8 more. arXiv.org, 2022

419 citations recorded by the source corpus.

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 cannot directly use historical weather data to improve the underlying model. We introduce a machine learning-based method called"GraphCast", which can be trained directly from reanalysis data. It predicts hundreds of weather variables, over 10 days at 0.25 degree resolution globally, in under one minute. We show that 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 cyclones, 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.

Subfields: Artificial Intelligence, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/7dff3280beed4cef96265350074498bf142c41e7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Environmental Engineering

Citations in the corpus

ClimaX: A foundation model for weather and climate (2023, neutral): “We include other additional task-specific baselines (Pathak et al., 2022; Bi et al., 2022; Lam et al., 2022) in Appendix F.4.”
The operational medium-range deterministic weather forecasting can be extended beyond a 10-day lead time (2023, neutral): “, 2022) or multiple steps (Lam et al., 2022) powered by elaborate engineering techniques, or training separate models for different steps (Bi et al.”
FourCastNet: Accelerating Global High-Resolution Weather Forecasting Using Adaptive Fourier Neural Operators (2022, result): “Since FourCastNet was released in early 2022, several other works have shown comparable accuracy and resolution [9, 16, 19].”
Geometry-Informed Neural Operator for Large-Scale 3D PDEs (2023, methodology): “To overcome this, prior works propose using multi-pole methods or multi-level graphs [11, 12] to help with global connectivity.”