GRAPES集合卡尔曼滤波资料同化系统Ⅱ:区域分析及集合预报

The GRAPES ensemble Kalman filter data assimilation system.Part Ⅱ:Regional analysis and ensemble prediction

GRAPES集合卡尔曼滤波资料同化方法能够分批同化常规观测资料,GRAPES集合卡尔曼滤波同化系统的设计及其与GRAPES三维变分同化系统的对比试验结果表明,GRAPES集合卡尔曼滤波系统能够得到合理的分析,并且具有实际运行能力。在此基础上,进行集合卡尔曼滤波区域同化分析及集合预报试验,对比区域模式面三维变分同化分析预报结果,研究表明,集合卡尔曼滤波分析比三维变分分析具有一定优势,降水预报更接近实况。考察了预报误差特征随天气形势的变化情况,表明预报误差相关场和均方差的分布随着天气形式不同而变化。

The GRAPES ensemble Kalman filter（EnKF） is able to assimilate the conventional observations in batches.The design and tentative experiment of the EnKF are introduced in part I.The experiment results of assimilating the regional radiosonds show that the reasonable analysis of the GRAPES EnKF is obtained and the system can be practically applied to the operational forecast.In this paper,the regional analysis and ensemble prediction experiments of the GRAPES EnKF are carried out,and the results are compared with the fields of the 3D-Var assimilation system in sigma level.The results indicate that the analysis of the EnKF has the competitive advantage over the 3D-Var analysis and the predicted precipitation of the EnKF is more similar to that of the observational station.The forecasting errors have been examined,which shows that the distribution of error correlation and error variance are flow-dependent.