2021年“7·20”郑州暴雨极端雨强对流尺度集合预报试验  

Convective-Scale Ensemble Forecast Experiment of Extreme Rainfall Intensity for“7·20”Severe Torrential Rain in Zhengzhou,2021

作　　者：吴卓亨 陈静[2,3] 张涵斌 江源[2] 刘昕 马雅楠 王秋萍 陈法敬[2] 韩雨盟 吴筱雯 WU Zhuoheng;CHEN Jing;ZHANG Hanbin;JIANG Yuan;LIU Xin;MA Yanan;WANG Qiuping;CHEN Fajing;HAN Yumeng;WU Xiaowen(Chengdu University of Information Technology,Chengdu 610225;Center for Earth System Modeling and Prediction of China Meteorological Administration,Beijing 100081;State Key Laboratory of Severe Weather,Chinese Academy of Meteorological Sciences,Beijing 100081;Beijing Institute of Urban Meteorology,China Meteorological Administration,Beijing 100089;China Meteorological Administration Xiong’an Atmospheric Boundary Layer Key Laboratory,Xiong’an New Area 071799;Nanjing University of Information Science and Technology,Nanjing 210044)

机构地区：[1]成都信息工程大学,成都610225 [2]中国气象局地球系统数值预报中心,北京100081 [3]中国气象科学研究院灾害天气国家重点实验室,北京100081 [4]北京城市气象研究院,北京100089 [5]中国气象局雄安大气边界层重点开放实验室,雄安新区071799 [6]南京信息工程大学,南京210044

出　　处：《大气科学》2024年第6期2389-2404,共16页Chinese Journal of Atmospheric Sciences

基　　金：国家重点研发计划项目2021YFC3000902。

摘　　要：2021年7月20日郑州市特大暴雨过程给人民的生命财产造成了巨大损失。然而,此次暴雨降水量极端性强,数值预报不确定性极大。为提高中国气象局(CMA)数值模式对此类暴雨极端雨强预报不确定性的描述能力,利用CMA自主研发的3 km水平分辨率的对流尺度数值预报系统(China Meteorological Administration Mesoscale model,简称CMA-Meso),通过设计集合同化观测扰动方案与云分析雷达反射率滤波阈值调整方案,实现对常规观测资料和雷达反射率的微小扰动,构建对流尺度集合预报初始扰动场,开展集合预报试验,评估对流尺度集合预报的极端雨强预报不确定性特征,并与CMA全球集合预报和区域集合预报进行对比分析。结果表明:(1)基于3 km水平分辨率的对流尺度集合预报对此次极端降水的预报仍存在一定的落区偏差,但不同集合预报成员的极端雨强值具有较好的发散度,且个别成员预报的极端雨强值接近实况的624.1 mm,较好地代表了极端降水的预报不确定性。(2)通过对比CMA不同分辨率集合预报的极端雨强值、离散度及累积降水邻域分数技巧评分,发现极端雨强值及离散度与模式水平分辨率密切相关,分辨率越高,极端雨强概率预报技巧越高,表明对流尺度集合预报能够更好描述极端雨强预报的不确定性及其极端性。(3)同时扰动常规观测资料及雷达资料的对流尺度集合预报,能够在较短的预报时效内对模式水汽场及环流形势产生影响,促使降水集合预报离散度在较短的预报时效内增长起来,有效提升了极端雨强概率预报能力。总体而言,通过扰动常规观测资料和雷达资料的对流尺度集合预报有助于提高模式对极端雨强概率预报技巧。The devastating rainstorm that hit Zhengzhou on July 20,2021,resulted in substantial losses of life and property.This storm was extraordinarily intense and presented considerable challenges in numerical prediction owing to its inherent uncertainty.To improve the ability of the China Meteorological Administration’s(CMA)numerical model to predict such rainfall intensity,we used a convective-scale numerical forecast system which is called CMA-Meso with a 3-km horizontal resolution.We designed an ensemble assimilation observation disturbance scheme and adjusted the cloud analysis radar reflectivity filtering threshold.This allowed us to conduct convective-scale ensemble forecast experiments.Then,we evaluated the uncertainty characteristics of extreme rainfall intensity forecasts from the convective-scale ensemble forecast.These characteristics were compared to those obtained from the CMA global ensemble forecast and regional ensemble forecast.The following are the results obtained from this study.(1)While CMA-Meso 3km still exhibited some deviation in predicting extreme precipitation,there was a good spread in the extreme rainfall intensity values among different ensemble forecast members.Some values of individual members were close to the actual 24-hour cumulative precipitation of 624.1 mm,providing a better representation of the forecast uncertainty of extreme precipitation.(2)Further comparison of the CMA ensemble forecasts at different resolutions showed a strong correlation among the intensity of extreme rainfall,dispersion,and the skill scores derived from assessing the fraction of cumulative precipitation as well as the model’s horizontal resolution.The higher the resolution,the higher the ability to accurately predict extreme rainfall intensity.This indicates that the convective-scale ensemble forecast can effectively describe the uncertainty and extremeness of extreme rainfall intensity forecasts.(3)When the convective-scale ensemble forecast simultaneously disturbed the conventional observation and rada

关 键 词：郑州极端暴雨 极端雨强 对流尺度 集合预报 集合资料同化 

分 类 号：P456.7[天文地球—大气科学及气象学]