Accurate Medium-Range Global Weather Forecasting with 3D Deep Neural Networks
DescriptionWeather forecasting is important for science and society. Currently, the most accurate forecast system is the numerical weather prediction (NWP) method, which represents atmospheric states as discretized grids and numerically solves partial differential equations (PDEs) that describe the transition between those states. However, this procedure is computationally expensive. Recently, AI-based weather forecasting methods have shown potential in accelerating weather forecasting by orders of magnitudes, but the forecast accuracy is still significantly lower than that of NWP methods. In this paper, we introduce an AI-based method for accurate, medium-range global weather forecasting. We show that 3D deep networks equipped with Earth-specific priors are effective at dealing with complex patterns in weather data, and that a hierarchical temporal aggregation strategy reduces accumulation errors in medium-range forecasting. Trained on 39 years of global data, our program, Pangu-Weather, is the first to obtain stronger deterministic forecast results on reanalysis data in all tested variables, when compared with the world’s best NWP system, the operational integrated forecasting system (IFS) of the European Centre for Medium-Range Weather Forecasts (ECMWF). Our method also works well with extreme weather forecasts and ensemble forecasts. When initialized with reanalysis data, the accuracy of tracking tropical cyclones is higher than ECMWF-HRES.
TimeTuesday, June 2717:30 - 18:00 CEST
Climate, Weather and Earth Sciences