Deep Learning for Seasonal Precipitation Prediction over China

作     者：Weixin JIN Yong LUO Tongwen WU Xiaomeng HUANG Wei XUE Chaoqing YU Weixin JIN;Yong LUO;Tongwen WU;Xiaomeng HUANG;Wei XUE;Chaoqing YU

作者机构：Department of Earth System ScienceMinistry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084 Beijing Climate CenterChina Meteorological AdministrationBeijing 100081 AI for Earth Labthe Joint Laboratory of Cross-Strait Tsinghua Research InstituteXiamen 361006 

出 版 物：《Journal of Meteorological Research》 (气象学报（英文版）)

年 卷 期：2022年第36卷第2期

页      面：271-281页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 070601[理学-气象学] 081104[工学-模式识别与智能系统] 08[工学] 0706[理学-大气科学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Supported by the National Key Research and Development Program of China(2016YFA0602103) National Climate Center’s Project on Precipitation Prediction Method in Flood Season in China based on CMA–CPS(Climate Prediction System) Machine Learning,GEIGC(Global Energy Interconnection Group Co.,Ltd.)Science and Technology Project(SGGEIG00JYJS2000053) 

主　　题：seasonal precipitation seasonal prediction statistical downscaling deep learning 

摘      要：Despite significant progress having been made in recent years,the forecast skill for seasonal precipitation over China remains *** this study,a deep-learning-based statistical prediction model for seasonal precipitation over China was *** model was trained to learn the distribution of the seasonal precipitation using simultaneous general circulation ***,it was pre-trained with the hindcasts of several general circulation models(GCMs),and evaluation of the test set suggested that the pre-trained model could basically reproduce the GCM-predicted precipitation,with the anomaly pattern correlation coefficients(PCCs)greater than ***,transfer learning was applied by using ECMWF Reanalysis v5(ERA5)data and gridded precipitation observational data over China,to further correct the systemic errors in the *** a result,using general circulation fields from reanalysis as the input,this hybrid model performed reasonably well in simulating the seasonal precipitation over China,with the PCC reaching *** addition,the results using the circulation fields predicted by GCMs as the input were also *** general,the proposed model improves the PCC over China by 0.10-0.13,as compared to the raw GCM outputs,for lead times of 1-4 *** deep learning model has been used at the National Climate Center of China Meteorological Administration for the past two years to provide guidance for summer precipitation prediction over China and has performed extremely well.