English

FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model

Machine Learning 2023-11-01 v1 Atmospheric and Oceanic Physics Applications

Abstract

Significant advancements in the development of machine learning (ML) models for weather forecasting have produced remarkable results. State-of-the-art ML-based weather forecast models, such as FuXi, have demonstrated superior statistical forecast performance in comparison to the high-resolution forecasts (HRES) of the European Centre for Medium-Range Weather Forecasts (ECMWF). However, ML models face a common challenge: as forecast lead times increase, they tend to generate increasingly smooth predictions, leading to an underestimation of the intensity of extreme weather events. To address this challenge, we developed the FuXi-Extreme model, which employs a denoising diffusion probabilistic model (DDPM) to restore finer-scale details in the surface forecast data generated by the FuXi model in 5-day forecasts. An evaluation of extreme total precipitation (TP\textrm{TP}), 10-meter wind speed (WS10\textrm{WS10}), and 2-meter temperature (T2M\textrm{T2M}) illustrates the superior performance of FuXi-Extreme over both FuXi and HRES. Moreover, when evaluating tropical cyclone (TC) forecasts based on International Best Track Archive for Climate Stewardship (IBTrACS) dataset, both FuXi and FuXi-Extreme shows superior performance in TC track forecasts compared to HRES, but they show inferior performance in TC intensity forecasts in comparison to HRES.

Keywords

Cite

@article{arxiv.2310.19822,
  title  = {FuXi-Extreme: Improving extreme rainfall and wind forecasts with diffusion model},
  author = {Xiaohui Zhong and Lei Chen and Jun Liu and Chensen Lin and Yuan Qi and Hao Li},
  journal= {arXiv preprint arXiv:2310.19822},
  year   = {2023}
}
R2 v1 2026-06-28T13:06:24.758Z