基于CMIP5模式对四川盆地湿季降水与极端降水的研究  

Study on Precipitation and Extreme Precipitation in the Wet Season in Sichuan Basin based on CMIP5 Models

作　　者：于灏 周筠珺 李倩[3] 姜琪 邱威腾 吴笛 崔雪锋 YU Hao;ZHOU Yunjun;LI Qian;JIANG Qi;QIU Weiteng;WU Di;CUI Xuefeng(School of Systems Science,Beijing Normal University,Beijing 100875,China;Department of Atmospheric Sciences,Chengdu University of Information Technology,Chengdu 610225,Sichuan,China;Key Laboratory of Middle Atmosphere and Global Environment Observation,Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing 100029,China;State Key Laboratory of Earth Surface Processes and Resource Ecology,Beijing Normal University,Beijing 100087,China;Northwest Institute of Ecological and Environmental Resources,Chinese Academy of Sciences,Lanzhou 730000,Gansu,China)

机构地区：[1]北京师范大学系统科学学院,北京100875 [2]成都信息工程大学大气科学学院高原大气与环境四川省重点实验室,四川成都610225 [3]中国科学院大气物理研究所中层大气与全球环境探测重点实验室,北京100029 [4]北京师范大学地表过程与资源生态国家重点实验室,北京100875 [5]中国科学院西北生态环境资源研究院,甘肃兰州730000

出　　处：《高原气象》2020年第1期68-79,共12页Plateau Meteorology

基　　金：国家自然科学基金项目(91637104,41661144006);成都市科技惠民技术研发项目(2016-HM01-00038-SF);成都市科技专项(2018-ZM01-00038-SN)

摘　　要：四川盆地是中国重要的农业和经济中心,湿季降水尤其极端降水情况显得尤为重要。基于“国际耦合模式比较计划第五阶段”(CMIP5)的多个模式结果评估未来湿季降水和极端降水的可能变化。首先,利用CRU数据检验了模式对1971-2000年5-9月四川盆地降水的模拟能力。结果显示,31个模式中有17个模式的模拟能力较好,通过99%的空间相关性信度检验,重现了“东多西少”的空间形态。有21个模式与观测值的标准差之比小于2.5,所有模式的平均偏差率都小于50%。在此基础上,选取表现最好的3个模式,在订正后做模式集合平均(MME),展示在RCP2.6、RCP4.5、RCP8.5的情形下,21世纪初期(2010-2039年)、中期(2040-2069年)、末期(2070-2099年)四川盆地湿季平均降水和湿季极端降水阈值的空间分布特征。结果显示,在RCP2.6的情形下,相对于1971-2000年的气候平均态,四川盆地湿季降水自东向西呈现“减-增-减”的形势,并且随着时间变化并无明显变化。在RCP4.5与RCP8.5的情形下,特征与RCP2.6不同,自东向西呈现“增-减-增”的形势。盆地东部湿季平均降水普遍增多,部分区域的变率达到了20%。对于极端降水阈值空间分布,特征与平均降水类似,三种情形下高值区均为在盆地中部偏东的一条南北走向的狭长带状区域。该区域内包括了成都、雅安、眉山、乐山等四川主要城市,并且随时间变化,该区域还有扩大的趋势,而RCP8.5模拟的降水要显著多于另两种情形。此外研究还发现,在全球变暖的背景下,四川盆地某一区域湿季平均降水减少的情况下,其极端降水阈值一定降低,反之不一定成立。只有当平均降水增幅超过10%时,该地区极端降水阈值才会增加。Sichuan Basin is an important agricultural and economic center in China.Precipitation in wet season,especially extreme precipitation,is particularly important.This paper evaluates possible future changes in wet season precipitation and extreme precipitation based on multiple model results of the Coupled Model Inter-comparison Project Phase 5(CMIP5).First,the CRU data was used to test the models’ ability to simulate the MaySeptember precipitation in Sichuan Basin from 1971 to 2000.The results show that 17 of the 31 models had better simulation capabilities,and pass the 99% of the spatial correlation reliability test.The results successfully reproduce the spatial pattern of "east more and west less".The ratio of the standard deviation of 21 patterns to observations is less than 2.5.The average precipitation bias of all models is less than 50%.On this basis,we select three best-performing models,and after the correction we will perform the MME to display the spatial distribution characteristics of average precipitation and wet season extreme precipitation thresholds in the Sichuan Basin in early 21 st century(2010-2039)、middle period(2040-2069) and late period(2070-2099),in the case of RCP2.6,RCP4.5,and RCP8.5.The results show that in the case of RCP2.6,compared to the climatology of1971-2000,precipitation in wet season of Sichuan Basin shows a "decreasing-increasing-decreasing" trend from east to west,and there is no obvious change over time.In the case of RCP4.5 and RCP8.5,the characteristics are different from those of RCP2.6,showing a "increasing-decreasing-increasing" situation from east to west.The average precipitation in wet season in the east of basin generally increases,and the variability in some regions even reached 20%.For the spatial distribution of extreme precipitation thresholds,the characteristics are similar to the average precipitation.In the three cases,the large-value areas are in a north-south trending striplike zone in the east of the basin.This area includes major cities in Sichuan,such

关 键 词：CMIP5 模式评估与订正 湿季 月平均降水与极端降水 

分 类 号：P467[天文地球—大气科学及气象学]