摘要
为进一步描述GRAPES(Global/Regional Assimilation and Prediction System)区域集合预报系统(GRAPES Me—soscale Ensemble Prediction System,GRAPES—MEPS)中GRAPES—Meso模式的不确定性特征,本研究在GRAPES—MEPS系统中引人了模式物理参数化倾向随机扰动方案(Stochastically Perturbed Parameterization Tendencies,SPPT),随机扰动型的产生是基于-阶马尔科夫链,其具有时间相关性特征,并服从正态分布,另外经过谱展开随机场具有空间结构特征,在水平结构上较平滑和连续。本文开展了基于SPPT方案的GRAPES—MEPS集合预报试验,针对SPPT方案中随机场的扰动幅度和时间相关尺度参数开展了一系列敏感性试验,并对试验结果进行了较全面的集合预报客观检验,此外,针对一次强降水过程,分析了SPPT方案对降水预报的影响。试验结果表明,引入SPPT方案能在一定程度上提高GRAPES—MEPS系统的预报技巧,降低系统的漏报率;且能显著改进预报后期大雨量级降水的预报技巧。通过敏感性试验发现,对于GRAPES—MEPS系统,SPPT方案的效果与随机扰动场幅度的范围,及扰动场的时间相关尺度选择相关,需经过敏感性试验确定出较适合的参数。
In order to describe the model uncertainly of the GRAPES_MEPS （Global/Regional Assimilation and Prediction System, Mesoscale Ensemble Prediction System）, we used Stochastically Perturbed Param- eterization Tendencies （SPPT） scheme in this system. The random field which is described with first order Markov chain has a time-related characteristics and Gaussian distribution, and also has a continuous and smooth horizontal structure since it is a combination through the spectral transform. This paper presents experiments on GRAPES_MEPS ensemble forecasts based on SPPT scheme, with a series of sensitivity tests on random perturbation amplitude and timescale correlation coefficient carried out. Verification on ensemble forecasts is also implemented, and the impact of SPPT scheme on precipitation prediction is ana- lyzed. The experimental results indicate that SPPT scheme can improve forecasting skills of GRAPES_MEPS system and reduce the false negative rate to a certain extent, and improve the prediction of heavy rain fore- cast skill significantly. Through the sensitivity tests we found that the effect of SPPT scheme for GRAPES _MEPS system is related to the amplitude of the random perturbation field and time correlation scale, more suitable parameters should be determined through sensitivity experiments.
作者
袁月
李晓莉
陈静
夏宇
YUAN Yue LI Xiaoli CHEN Jing XIA Yu(Chengdu University of Information Technology, Chengdu 610025 Numerical Weather Prediction Centre, CMA, Beijing 100081)
出处
《气象》
CSCD
北大核心
2016年第10期1161-1175,共15页
Meteorological Monthly
基金
公益性行业(气象)科研专项(GYHY201506005和GYHY201006015)
国家自然科学基金项目(41075035)
国家重点基础研究发展计划(973计划)(2012CB417204)
国家科技支撑计划项目(2015BAC03B01)共同资助
关键词
集合预报
随机扰动参数化倾向方案
扰动范围
时间尺度
ensemble forecast, stochastically perturbed parameterization tendency （SPPT）, random field, time scale
