夏季不同源地水汽对我国西北区降水影响的数值模拟(Ⅰ)：模拟试验方案及对照试验结果

Simulation on Impact of Water Vapor in Various Source Areas on NWC Precipitation Summer(Ⅰ):Experiment Schemes and Contrast Run Results

为客观地检验夏季不同源区水汽对我国西北区降水影响的相对重要性,在本文中我们划分了东南沿海、孟加拉湾、青藏高原及西风带等水汽源区,选择了西北区全区性湿月1979年7月,利用NCAR MM5中尺度模式和NCEP再分析值资料作初、侧边界条件,对该月分别执行了检验模式性能的对照试验及检验减、增各源区水汽影响的敏感性试验等共13个试验。文章上篇的主要结果如下:(1)两对照试验为传统的仅月初给定初始场,连续积分全月的连续积分试验(CONA)及每5天更新初始场,分6段接力式完成全月积分的分段积分试验(CONB)。(2)两对照试验虽都较好地再现了该月亚洲中、高纬度较平直的月平均西风环流,但CONB试验更好地再现了该月淮河—川西半环状多雨带及江南、华南、以及西北区少雨的降水分布格局,还令人鼓舞地捕捉了该月西北区东南部的各次降水过程,即MM5模式对该月形势和降水的模拟性能较好,因而其下篇分别减、增不同源区水汽影响的敏感性试验结果也是可信的。(3)对某天气气候事件的事后较长时间的模拟,采用分段积分模拟方案,可部分提高模式的模拟效果。

To objectively test the relative importance of water vapor in various source areas in summer precipitation over Northwest China （hereafter NWC）, in these companion papers, first, a typically wet month over nearly NWC around July, 1979 was chosen; then the likely water vapor source areas of NWC such as Off the Southeast Coast of China（SE）, The Bay of Bengal（BB）, Qinghai-Xizang Plateau（QXP） and Westerly Zone（WZ） were drawn; and again then, a set of thirteen numerical experi ments totally, including two contrast ones testing MM5 modeling performance and eleven sensitive ones changing respectively water vapor over each source area, have been designed and integrated for whole July of 1979, utilizing the PSU/NCAR MM5V3.7 model and the NCEP reanalyzed values data as the initial and lateral boundary conditions. The main conclusions of the Part I of the papers are as follows. （1） Two contrast runs are both the traditionally continually integration one（CONA） which was only given the initial field at 00.-00 GMT on July 1, 1979 and then integrated continually 31 days and the pentad by pentad integration run（CONB） which was updated the initial field in each five days and finished the 31 day integration in relay race ways. （2） Both the CONA and CONB runs simulate the circulation and precipitation weather of the month quite well, especially the latter one. I e, the MM5 model has again been proved to be of good performance, thus the subsequent simulation results of the sensitive runs in Part H of the papers are also convinced. （3） As a post-event and long-integrated modeling, using the pentad-bypentad integration scheme may partly improve the modeling behavior.