Forecasting Global Weather with Graph Neural Networks
This addresses weather prediction for meteorologists and climate scientists, offering a data-driven alternative that is incremental over prior data-driven methods.
The paper tackles global weather forecasting by using graph neural networks to step forward atmospheric states, achieving performance comparable to operational physical models on metrics like Z500 and T850 at 1-degree scales.
We present a data-driven approach for forecasting global weather using graph neural networks. The system learns to step forward the current 3D atmospheric state by six hours, and multiple steps are chained together to produce skillful forecasts going out several days into the future. The underlying model is trained on reanalysis data from ERA5 or forecast data from GFS. Test performance on metrics such as Z500 (geopotential height) and T850 (temperature) improves upon previous data-driven approaches and is comparable to operational, full-resolution, physical models from GFS and ECMWF, at least when evaluated on 1-degree scales and when using reanalysis initial conditions. We also show results from connecting this data-driven model to live, operational forecasts from GFS.