基于机器学习(Machine Learning,ML)的天气预报模型近些年取得了显著进展,展示了优越的预报性能.与欧洲中期天气预报中心(European Centre for Medium-Range Weather Forecasts,ECMWF)的高分辨率预报(High-Resolution Forecasts,HRES)相...基于机器学习(Machine Learning,ML)的天气预报模型近些年取得了显著进展,展示了优越的预报性能.与欧洲中期天气预报中心(European Centre for Medium-Range Weather Forecasts,ECMWF)的高分辨率预报(High-Resolution Forecasts,HRES)相比,FuXi等先进的基于ML的天气预报模型,在统计预报指标上表现出色.然而,这些模型存在着共同的局限性,即随着预报时间步长的增加,预报结果趋于平滑,导致极端天气事件强度的低估.为了解决这一问题,本文研发了FuXi-Extreme模型.该模型采用去噪扩散概率模型(Denoising Diffusion Probabilistic Model,DDPM),增强了FuXi模型在5天预报中的地表预报数据细节.对极端总降水量(Total Precipitation,TP)、10m风速(10-meter Wind Speed,WS10)和2m温度(2-meter Temperature,T2M)的评估表明,FuXi-Extreme在性能上优于FuXi和HRES.此外,基于国际热带气旋最佳路径资料集(International Best Track Archive for Climate Stewardship,IBTrACS)的评估显示,与HRES相比,FuXi和FuXi-Extreme在热带气旋(Tropical Cyclone,TC)路径预报方面表现优异,但在TC强度预报方面仍有不足.展开更多
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 super...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 MediumRange Weather Forecasts(ECMWF).However,a common limitation of these ML models is their tendency to generate increasingly smooth predictions as forecast lead times increase,which often results in the underestimation of intensities of extreme weather events.To address this challenge,we developed the FuXi-Extreme model,which employs a denoising diffusion probabilistic model(DDPM)to enhance finer-scale details in the surface forecast data generated by the FuXi model in 5-day forecasts.An evaluation of extreme total precipitation(TP),10-meter wind speed(WS10),and 2-meter temperature(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 FuXiExtreme shows superior performance in TC track forecasts compared to HRES,but they show inferior performance in TC intensity forecasts in comparison to HRES.展开更多
基金supported by the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20240154)。
文摘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 MediumRange Weather Forecasts(ECMWF).However,a common limitation of these ML models is their tendency to generate increasingly smooth predictions as forecast lead times increase,which often results in the underestimation of intensities of extreme weather events.To address this challenge,we developed the FuXi-Extreme model,which employs a denoising diffusion probabilistic model(DDPM)to enhance finer-scale details in the surface forecast data generated by the FuXi model in 5-day forecasts.An evaluation of extreme total precipitation(TP),10-meter wind speed(WS10),and 2-meter temperature(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 FuXiExtreme shows superior performance in TC track forecasts compared to HRES,but they show inferior performance in TC intensity forecasts in comparison to HRES.
