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

TL;DR

Pangu-Weather is a deep learning system that achieves fast, high-resolution, and more accurate global weather forecasts than traditional numerical methods, using a novel 3D transformer architecture and hierarchical temporal strategies.

Contribution

The paper introduces a new AI-based weather forecasting model that outperforms state-of-the-art NWP methods in accuracy and speed, with a novel 3D transformer architecture and hierarchical temporal aggregation.

Findings

AI-based method surpasses traditional NWP in accuracy across all factors.

Model achieves 0.25° spatial resolution comparable to ECMWF IFS.

Supports real-time extreme weather and ensemble forecasting.

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 $0.25^\circ\times0.25^\circ$, 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.