大气科学学报2025，Vol.48Issue(4)：603-617,15.DOI:10.13878/j.cnki.dqkxxb.20241011004
基于卷积神经网络的湖南盛夏高温过程延伸期智能预报
Extended-range intelligent forecasting of regional heat wave events in Hu-nan Province during midsummer(July-August)using convolutional neural networks
摘要
Abstract
Hunan Province,located in central China,features a terrain dominated by mountains and hills,with plains enclosed by mountains on three sides.The region experiences a subtropical monsoon climate,with frequent high-temperature events during summer,particularly in the peak summer months of July and August.Research in-dicates that a rising trend in extreme heat events in Hunan,with the southeastern region experiencing the highest occurrence.Accurate fine-scale temperature forecasting remains a key challenge in regional weather prediction,while effective forecasting and timely warnings of severe weather are essential for disaster prevention and mitiga-tion.Unlike short-term weather forecasts,extended-range forecasts(10-30 days)provide a longer decision-mak-ing window,allowing government authorities to implement proactive measures to enhance public safety and reduce disaster losses.However,current temperature forecasting studies in Hunan primarily focus on nowcasting and short-term model corrections,with limited research on extended-range forecasting.Furthermore,existing ex-tended-range high-temperature forecasts in Hunan largely rely on sub-seasonal to seasonal(S2S)models,which often exhibit insufficient accuracy.There fore,developing a dedicated forecasting model for extended-range high-temperature forecasting is crucial.The study aims to develop an extended-range forecasting model for heat wave e-vents in Hunan Province during the peak summer period(July-August).The model integrates physical predictors derived from S2S model temperature forecasts and their corrections with a convolutional neural network(CNN)approach to enhance forecasting skill.Daily maximum temperature data from 97 meteorological stations in Hunan Province(1999-2022)and S2S model outputs from ECMWF and NCEP are utilized.Physical forecast factors are extracted from temperature and circulation forecast products using singular value decomposition(SVD)and the spatiotemporal projection model(STPM).These factors are then integrated into a CNN-based high-temperature prediction model(HTPM).Additionally,the maximum temperature forecasts from the S2S models undergo bias correction,and the corrected forecasts are combined with predictions from the HTPM to create an ensemble forecasting scheme.This approach aims to enhance the stability and accuracy of regional high-tempera-ture forecasts.Results indicate that while the original S2S model forecasts exhibit low predictive skill,bias correc-tion significantly improves their performance,though false alarm rates remain high.The CNN-based high-tempera-ture forecasting model trained on ECMWF S2S data(HTPM-ECS2S)and NCEP S2S data(HTPM-NCEPS2S)effectively capture high-temperature events,demonstrating improved forecasting skill.The ensemble scheme suc-cessfully integrates multiple model outputs,further enhancing forecast accuracy and reliability.关键词
高温过程/延伸期预报/卷积神经网络/集成预报Key words
heat wave events/extended-range forecasting/convolutional neural network/ensemble forecasting引用本文复制引用
张祎,谭桂容,赵辉,曾玲玲,黄超,费琪铭..基于卷积神经网络的湖南盛夏高温过程延伸期智能预报[J].大气科学学报,2025,48(4):603-617,15.基金项目
湖南省气象局创新发展专项(CXFZ2024-FZZX36) （CXFZ2024-FZZX36）
国家自然科学基金项目(42175034 （）
42175035) （）
