基于智能聚类识别的SWAT模型参数优化方法——以石头口门水库流域为例  

Parameters optimization of SWAT model based on SOM clustering algorithm:A case study of Shitoukoumen Reservoir watershed

作　　者：姚美初 陈莹[2] 李鸿雁 赵红玲 李昌海 次旦央宗 刘莹莹 孙建 YAO Meichu;CHEN Ying;LI Hongyan;ZHAO Hongling;LI Changhai;Cidanyangzong;LIU Yingying;SUN Jian(College of New Energy and Environment,Jilin University,Key Laboratory of Groundwater Resources and Environment(Jilin University),Ministry of Education,Jilin Provincial Key Laboratory of Water Resources and Environment,Jilin University,Changchun 130012,China;Water Resource Management Center,Ministry of Water Resources,Beijing 100053,China;College of Water Conservancy and Civil Engineering,Tibet Agriculture and Animal Husbandry University,Linzhi 860000,China)

机构地区：[1]吉林大学新能源与环境学院,吉林大学地下水资源与环境教育部重点实验室,吉林省水资源与水环境重点实验室,长春130012 [2]水利部水资源管理中心,北京100053 [3]西藏农牧学院水利土木工程学院,西藏林芝860000

出　　处：《南水北调与水利科技（中英文）》2023年第3期457-469,共13页South-to-North Water Transfers and Water Science & Technology

基　　金：国家自然科学基金重点项目(U19A20107);吉林省科技厅重点研发项目(20200403070SF)。

摘　　要：为探究SWAT模型参数优化过程与方法,降低参数估计不确定性,采用敏感性分析方法遴选关键参数,针对关键参数采用拉丁超立方抽样构建参数样本集,进而结合各组关键参数组合下的模拟精度指标构建聚类指标集,采用SOM聚类算法进行聚类,并基于模拟精度较高且波动较小类别识别各关键参数取值范围,形成一种SWAT模型关键参数优化系统方法。以石头口门水库流域为例,选取1980—2016年(1980—1986年为预热期,1987—2009年为率定期,2010—2016年为验证期)的月径流实测资料,建立流域SWAT模型,引入SOM聚类算法进行参数优化,不断缩小模型关键参数合理取值区间,并应用SUFI-2算法进行模拟结果对比。结果表明:SWAT模型适用于石头口门水库流域,且参数优化前验证期的决定系数R^(2)为0.79,纳什效率系数E_(NS)为0.74,P-factor为0.65,R-factor为0.56;参数优化后验证期R^(2)为0.88,E_(NS)为0.83,P-factor为0.70,R-factor为0.50,模拟效果较好。故应用SOM算法进行SWAT模型参数优化可以降低模型不确定性,提高径流模拟精度,为水文模型参数优化算法的选择提供思路,对水资源管理政策制定与水库优化调度具有重要意义。Parameter optimization is a crucial part of hydrological model simulation,which determines the accuracy of simulation and forecast.The Soil and Water Assessment Tool(SWAT)model is a distributed basin hydrological model based on the physical mechanism,and in the study of basin runoff simulation using the SWAT model,the model parameter optimization is mainly determined by the SWAT Calibration Uncertainties Program(SWAT-CUP)automatic rate method,including the SUFI-2 algorithm,Particle Swarm Optimization(PSO)algorithm,Parasol algorithm and General Language Understanding Evaluation(GLUE)algorithm.SWAT models often require thousands of hydrological model runs through the parameter optimization process to find a satisfactory combination of parameters.In recent years,in-depth studies on parameter optimization have concluded that the uniqueness of the optimal parameters is difficult to achieve,the problem of different reference effect is inevitable,so a common practice is to consider the parameter solutions as probability distributions that can be solved by applying mathematical methods.When the SUFI-2 algorithm is used for parameter optimization,it is found that the results often show uncertainties caused by different reference effect,or the runoff extremes are not well simulated.SOM algorithm is a neural network algorithm based on unsupervised learning,which can achieve intelligent clustering of data through self-organized competitive learning without understanding the interrelationship between sample data,and is also for achieving clustering through data mining technology.In practical engineering problems,taking the clustering analysis method can simplify the complex data system,make the data computation processing efficient,and make the internal laws of things clear.The SOM clustering algorithm was applied to the process of SWAT model parameter optimization to reduce the parameter estimation uncertainty.The sensitivity analysis method was used to select key parameters,Latin hypercube sampling was used to construct a p

关 键 词：SWAT模型 SOM算法 聚类分析 参数率定 参数优化 石头口门水库 

分 类 号：TV121[水利工程—水文学及水资源]