FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead

Abstract

We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI). Different from existing data-driven weather forecast methods, FengWu solves the medium-range forecast problem from a multi-modal and multi-task perspective. Specifically, a deep learning architecture equipped with model-specific encoder-decoders and cross-modal fusion Transformer is elaborately designed, which is learned under the supervision of an uncertainty loss to balance the optimization of different predictors in a region-adaptive manner. Besides this, a replay buffer mechanism is introduced to improve medium-range forecast performance. With 39-year data training based on the ERA5 reanalysis, FengWu is able to accurately reproduce the atmospheric dynamics and predict the future land and atmosphere states at 37 vertical levels on a 0.25° latitude-longitude resolution. Hindcasts of 6-hourly weather in 2018 based on ERA5 demonstrate that FengWu performs better than GraphCast in predicting 80\% of the 880 reported predictands, e.g., reducing the root mean square error (RMSE) of 10-day lead global z500 prediction from 733 to 651 $m^2/s^2$. In addition, the inference cost of each iteration is merely 600ms on NVIDIA Tesla A100 hardware. The results suggest that FengWu can significantly improve the forecast skill and extend the skillful global medium-range weather forecast out to 10.75 days lead (with ACC of z500 > 0.6) for the first time.

12 pages

References in corpus (6)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Neural General Circulation Models for Weather and Climate
• The rise of data-driven weather forecasting
• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
• SwinVRNN: A Data-Driven Ensemble Forecasting Model via Learned Distribution Perturbation
• Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers

Cited by in corpus (4)

• FuXi Weather: A data-to-forecast machine learning system for global weather
• Physically Consistent Global Atmospheric Data Assimilation with Machine Learning in Latent Space
• A robust and stable hybrid neural network/finite element method for 2D flows that generalizes to different geometries
• Data-driven global ocean model resolving ocean-atmosphere coupling dynamics