Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast

Abstract

In this paper, we present Pangu-Weather, a deep learning based system for fast and accurate global weather forecast. For this purpose, we establish a data-driven environment by downloading $43$ years of hourly global weather data from the 5th generation of ECMWF reanalysis (ERA5) data and train a few deep neural networks with about $256$ million parameters in total. The spatial resolution of forecast is $0.25^{\circ }\times 0.25^{\circ }$, comparable to the ECMWF Integrated Forecast Systems (IFS). More importantly, for the first time, an AI-based method outperforms state-of-the-art numerical weather prediction (NWP) methods in terms of accuracy (latitude-weighted RMSE and ACC) of all factors (e.g., geopotential, specific humidity, wind speed, temperature, etc.) and in all time ranges (from one hour to one week). There are two key strategies to improve the prediction accuracy: (i) designing a 3D Earth Specific Transformer (3DEST) architecture that formulates the height (pressure level) information into cubic data, and (ii) applying a hierarchical temporal aggregation algorithm to alleviate cumulative forecast errors. In deterministic forecast, Pangu-Weather shows great advantages for short to medium-range forecast (i.e., forecast time ranges from one hour to one week). Pangu-Weather supports a wide range of downstream forecast scenarios, including extreme weather forecast (e.g., tropical cyclone tracking) and large-member ensemble forecast in real-time. Pangu-Weather not only ends the debate on whether AI-based methods can surpass conventional NWP methods, but also reveals novel directions for improving deep learning weather forecast systems.

19 pages, 13 figures: the first ever AI-based method that outperforms traditional numerical weather prediction methods

Cited by in corpus (6)

• Deep learning of systematic sea ice model errors from data assimilation increments
• A Machine Learning Tutorial for Operational Meteorology, Part II: Neural Networks and Deep Learning
• DNN-MG: A Hybrid Neural Network/Finite Element Method with Applications to 3D Simulations of the Navier-Stokes Equations
• Leveraging data-driven weather models for improving numerical weather prediction skill through large-scale spectral nudging
• Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
• A Spatiotemporal Radar-Based Precipitation Model for Water Level Prediction and Flood Forecasting