CMA-MESO逐时快速更新同化预报系统及其短临预报效果初步分析  

Hourly Rapid Updating Assimilation Forecast System of CMA-MESO and Preliminary Analysis of Short-term Forecasting Effect

作　　者：庄照荣[1,2,3] 江源[1,2,3] 田伟红[1,2,3] 黄丽萍[1,2,3] 李兴良[1,2,3] 邓莲堂[1,2,3] ZHUANG Zhaorong;JIANG Yuan;TIAN Weihong;HUANG Liping;LI Xingliang;DENG Liantang(Earth System Modeling and Prediction Centre,China Meteorological Administration,Beijing 100081;CMA Key Laboratory of Earth System Modeling and Prediction,Beijing 100081;State Key Laboratory of Severe Weather,Chinese Academy of Meteorological Sciences,Beijing 100081)

机构地区：[1]中国气象局地球系统数值预报中心,北京100081 [2]中国气象局地球系统数值预报重点开放实验室,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

出　　处：《大气科学》2023年第4期925-942,共18页Chinese Journal of Atmospheric Sciences

基　　金：河南省重大科技专项201400210800;国家重点研发计划项目2021YFC3000902。

摘　　要：基于CMA-MESO模式水平3 km分辨率3 h循环的快速更新同化预报系统,本文建立逐小时的分析预报循环系统,并且通过采用5种尺度叠加的高斯相关模型和引入各向异性的水平相关尺度方案来改进背景误差水平相关结构,同时考察引入全球大尺度信息方案对逐小时循环的分析和预报影响。通过对2020年7月19日华东强对流天气过程的数值模拟表明:(1)逐小时循环吸收了更多的高频观测资料和循环中采用更临近的1 h预报场作为背景场,分析和降水短临预报质量整体比3 h循环有所提高;(2)在区域分析中逐时引入全球预报场的大尺度信息会削弱区域观测资料的影响,对预报会有不利影响;(3)改进的五种尺度叠加高斯相关模型和各向异性的水平相关尺度主要使风场背景误差水平相关系数的描述更接近样本的统计结果,因而在逐1 h循环中风场分析更靠近观测,华东强对流过程的组合反射率和降水短临预报更接近实况。Based on the CMA-MESO(China Meteorological Administration MESOscale weather forecast system)horizontal 3 km resolution 3 h cycle rapid update assimilation and forecast system,an hourly cycle analysis and forecast system was established.In this system,the background error correlation structure is improved by adopting a Gaussian correlation model with five-scale superimposition and introducing an anisotropic correlation scale scheme,and the impact of introducing a global large-scale information scheme on the analysis and forecast of the hourly cycle is examined.Numerical simulations of the strong convective case in eastern China on July 19,2020,show that:(1)The hourly cycle absorbs more high-frequency observations and uses the more proximate 1 h forecast field as the background field in the cycle,which improves the quality of analysis and short-range forecasts compared to the 3 h cycle.(2)The introduction of large-scale information from the global forecast field to the hourly cycle regional analysis can weaken the influence of regional observations,which can negatively affect forecasting.(3)The improved five-scale superimposed Gaussian correlation model and the anisotropic horizontal correlation scale make the representation of the background error horizontal correlation coefficients of wind variables closer to the statistical results of the samples.Thus,the analyzed wind fields are closer to the observations in the hourly cycle,and the composite reflectivity and short-term precipitation forecasting of the strong convective process in Eastern China are closer to the real situation.

关 键 词：CMA-MESO 模式 逐时快速更新同化预报 短临预报 强对流 背景误差协方差 

分 类 号：P456.7[天文地球—大气科学及气象学]