气象2025，Vol.51Issue(4)：431-445,15.DOI:10.7519/j.issn.1000-0526.2024.022003
基于改进长短期记忆网络的湖南网格气温预报模型
Gridded Temperature Forecast Model in Hunan Based on Improved Long Short-Term Memory Networks
摘要
Abstract
Based on forecast products of the European Centre for Medium-Range Weather Forecasts-Integrated Forecasting System(ECMWF-IFS)and hourly temperature observation data from the CMA Land Data Assimilation System(CLDAS),an enhanced model named ED-LSTM-FCNN is constructed,with an embedding layer module incorporated to handle high-dimensional spatial and temporal features.A fully connected neural network is utilized to integrate various feature types,achieve regression prediction of temperature,and generate gridded hourly temperature forecast products with a resolution of 0.05°× 0.05°.Verification for the forecast products in Hunan Province in 2022 shows that this model exhibits a notable capacity to mitigate forecast errors inherent in the numerical model,and can enhance the overall fore-cast stability.The root mean square errors(RMSEs)of forecasts with lead time ranging from 1 to 24 hours exhibit a reduction of 25.4％-37.7％when compared to ECMWF-IFS and a decrease of 15.8％-40.0％relative to the National Meteorological Centre forecast(SCMOC).The model can significantly im-prove the forecast performance of ECMWF-IFS forecast,in spatial scale,particularly in regions character-ized by intricate terrain.The RMSEs across most areas vary within the range of 1.2-1.6℃.The forecast accuracy of the model,with an error margin of±2℃,surpasses 83.0％across various seasons,demon-strating a significant improvement compared to both ECMWF-IFS and SCMOC.The forecasting perform-ance is notably superior,particularly in stable extreme high-temperature weather conditions compared to alternative products.In conclusion,this model has proved to be effective in the high-resolution tempera-ture forecasting operations.关键词
网格预报/长短期记忆网络/气温预报/深度学习Key words
gridded forecast/long short-term memory network/temperature forecast/deep learning分类
天文与地球科学引用本文复制引用
卢姝,陈鹤,陈静静,赵琳娜,郭田韵..基于改进长短期记忆网络的湖南网格气温预报模型[J].气象,2025,51(4):431-445,15.基金项目
国家重点研发计划(2023YFC3007800)、湖南省气象局创新发展专项(青年专项)(CXFZ2024-QNZX23)、国家自然科学基金项目(U2342219)、中国气象科学研究院基本科研业务费专项(2023Z022、2023Z013)和中国气象科学研究院科技发展基金项目(2023KJ022、2024KJ008)共同资助 （2023YFC3007800）
