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

作　　者：卢姝 陈鹤 陈静静 赵琳娜[3] 郭田韵 LU Shu;CHEN He;CHEN Jingjing;ZHAO Linna;GUO Tianyun(Hunan Key Laboratory of Meteorological Disaster Prevention and Reduction,Changsha 410118;Hunan Meteorological Observatory,Changsha 410118;Chinese Academy of Meteorological Sciences,Beijing 100081;Hunan Meteorological Service Center,Changsha 410118)

机构地区：[1]气象防灾减灾湖南省重点实验室,长沙410118 [2]湖南省气象台,长沙410118 [3]中国气象科学研究院,北京100081 [4]湖南省气象服务中心,长沙410118

出　　处：《气象》2025年第4期431-445,共15页Meteorological Monthly

基　　金：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);中国气象科学研究院科技发展基金项目(2023KJ022、2024KJ008)共同资助。

摘　　要：基于欧洲中期天气预报中心高分辨率模式预报产品以及中国气象局陆面数据同化系统逐1 h气温实况,构建了一种改进的长短期记忆网络ED-LSTM-FCNN模型,模型中加入嵌入层模块以处理高维空间、时间特征,并通过全连接神经网络融合不同类型特征实现气温的回归预测,生成0.05°×0.05°格点逐1 h气温预报产品。针对湖南省2022年预报检验表明:ED-LSTM-FCNN模型能显著降低数值模式的预报误差,提高预报稳定性,1~24 h时效预报均方根误差较模式预报与中央气象台指导预报分别降低了25.4%~37.7%和15.8%~40.0%;模型明显改善了数值模式在空间上(尤其是复杂地形)的预报效果,大部分地区气温均方根误差介于1.2~1.6℃;该模型在不同季节2℃误差以内的预报准确率达83.0%以上,明显高于模式预报与中央气象台指导预报,在平稳性极端高温天气中的优势更加明显,可有效应用于智能网格预报业务中。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 forecast 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 improve the forecast performance of ECMWF-IFS forecast,in spatial scale,particularly in regions characterized 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,demonstrating a significant improvement compared to both ECMWF-IFS and SCMOC.The forecasting performance 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 temperature forecasting operations.

关 键 词：网格预报 长短期记忆网络 气温预报 深度学习 

分 类 号：P456[天文地球—大气科学及气象学] TP183[自动化与计算机技术—控制理论与控制工程]