降水的统计降尺度预报及其空间相关性和时间连续性重建  

Statistical downscaling forecast and reconstruction of spatial and temporal correlation of the precipitation

作　　者：王姝苏 智协飞[1,3] 俞剑蔚 陈超辉[5] 周红梅 朱寿鹏[1] 赵欢 WANG Shusu;ZHI Xiefei;YU Jianwei;CHEN Chaohui;ZHOU Hongmei;ZHU Shoupeng;ZHAO Huan(Key Laboratory of Meteorological Disaster,Ministry of Education(KLME)/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disaster(CIC-FEMD)/Joint International Research Laboratory of Climate and Environment Change(ILCEC),Nanjing University of Information Science&Technolo;Meteorological Bureau Dafeng District,Yancheng 224100,China;Nanjing Joint Center for Atmospheric Research,Nanjing 210008,China;Weather Observatory of Jiangsu Province,Nanjing 210008,China;College of Meteorology and Oceanography,Defense University of Science and Technology,Nanjing 211101,China;Wuhan Central Meteorological Observatory,Wuhan 430074,China)

机构地区：[1]南京信息工程大学气象灾害教育部重点实验室/气象灾害预报预警与评估协同创新中心/气候与环境变化国际合作联合实验室,江苏南京210044 [2]江苏省盐城市大丰区气象局,江苏盐城224100 [3]南京大气科学联合研究中心,江苏南京210008 [4]江苏省气象台,江苏南京210008 [5]国防科技大学气象海洋学院,江苏南京211101 [6]武汉中心气象台,湖北武汉430074

出　　处：《大气科学学报》2018年第1期36-45,共10页Transactions of Atmospheric Sciences

基　　金：北极阁开放研究基金南京大气科学联合研究中心重点项目(NJCAR2016ZD04);深圳南方强天气研究重点实验室项目;江苏高校优势学科建设工程资助项目(PAPD)

摘　　要：利用欧洲中期天气预报中心(ECMWF)、日本气象厅(JMA)、美国国家环境预报中心(NCEP)以及英国气象局(UKMO)四个中心1~7 d日累计降水量集合预报资料,以中国降水融合产品作为"观测值",对我国地面降水量进行统计降尺度预报,并对预报降水的空间相关性和时间连续性进行重建。对降水量进行分级后,建立各个量级的回归方程进行统计降尺度预报。此外,还利用Schaake Shuffle方法重建丢失的空间相关性和时间连续性。结果表明,分级回归比未分级回归后的预报结果相关系数更高,预报误差更小,更接近观测值。Schaake Shuffle方法可以有效地改进降水预报的空间相关性和时间连续性,使之更接近实况观测,集合成员间的相关性也更好。Based on the ensemble forecasts of 1-7 day daily accumulated precipitation from the European Centre for Medium-Range Weather Forecasts(ECMWF),Japan Meteorological Agency(JMA),National Centers for Environmental Prediction(NCEP)and UK Met Office(UKMO),with the hourly merged precipitation product over China as the observed data,the forecast of daily precipitation in China by means of statistical downscaling and the reconstruction of spatial and temporal correlation of the precipitation forecast were conducted.The statistical downscaling based on different categories of the rainfall was applied to improve the precipitation forecast.The Schaake Shuffle was used to reconstruct the spatial correlation and temporal persistence of the precipitation forecast.The results show that the forecasts after the regression based on the different categories of the rainfall are more accurate than the ones after the regression.Classifying the rainfall into different categories was not considered,due to the fact that the anomaly correlation coefficient becomes larger and the root-mean-square error becomes smaller.The spatial and temporal correlations after the reconstruction are quite close to the observed ones.

关 键 词：降水量预报 统计降尺度 Schaake Shuffle方法 相关性重建 

分 类 号：P457.6[天文地球—大气科学及气象学]