降雨径流连续模拟参数全局灵敏性分析  

Global sensitivity analysis of a rainfall-runoff model using continuous simulation

作　　者：赵冬泉[1] 董鲁燕[1] 王浩正[1] 邢薇[1] 

机构地区：[1]北京清华城市规划设计研究院环境与市政所,北京100084

出　　处：《环境科学学报》2011年第4期717-723,共7页Acta Scientiae Circumstantiae

基　　金：水体污染控制与治理科技重大专项(No.2009ZX07317-006)~~

摘　　要：长期连续模拟是客观评价城市排水系统性能、雨洪控制措施效果的重要方法之一.运用普适似然度法(Generalized Likelihood Uncertainty Estimation,简称GLUE),综合分析了暴雨管理模型(Storm Water Management Model,简称SWMM)在不同间隔降雨情景下的水量、水质参数的全局灵敏性.研究结果表明:研究小区中屋面冲刷累积参数的灵敏度较高;不透水率、屋面最大累积量、屋面累积速率及屋面冲刷指数的灵敏性随降雨间隔的增加而有所提高,且当降雨间隔大于土壤干燥时间时,上述参数的灵敏性均趋于稳定;进行SWMM模型连续模拟时,选择雨前晴天数长于土壤干燥时间的降雨事件进行参数识别可降低参数不确定性.Long-term continuous simulation is an important method to evaluate the performance of urban drainage systems and the effectiveness of stormwater management practices.Global sensitivity analysis was conducted using the algorithm of Generalized Likelihood Uncertainty Estimation （GLUE） for the water quantity and quality parameters in the Storm Water Management Model （SWMM） under a series of continuous simulation scenarios with different intervals among rainfalls.The results showed that model outputs were sensitive to the variations of the buildup and washoff parameters of roof.The sensitivities of the percentage of impervious area and the maximum pollution buildup,buildup rate,and roof washoff exponent were found to increase with rainfall intervals.Furthermore,when the rainfall interval was longer than the soil drying time,the sensitivities of these parameters tended to converge to constants.Rainfall events with antecedent intervals longer than the soil drying time were therefore recommended to be used for parameter identification in the continuous simulation of SWMM to reduce parameter uncertainties.

关 键 词：SWMM 连续模拟 全局灵敏性 GLUE法 水量水质参数 

分 类 号：X522[环境科学与工程—环境工程]