基于结构-参数同步优化的河湖水位模型及应用  

River-lake water level model based on structure-parameter synchronized optimization and its application

作　　者：胡腾飞 施勇[1,2] 毛劲乔 栾震宇[1,2] 陈炼钢[1,2] 陈黎明 金秋[1,2] 徐祎凡 戴会超[3] HU Tengfei;SHI Yong;MAO Jingqiao;LUAN Zhenyu;CHEN Liangang;CHEN Liming;JIN Qiu;XU Yifan;DAI Huichao(Hydrology and Water Resources Department, Nanjing Hydraulic Research Institute, Nanjing, Jiangsu 210029, China;State Key Laboratory of Hydrology Water Resources and Hydraulic Engineering, Nanjing, Jiangsu 210029, China;College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing, Jiangsu 210098, China)

机构地区：[1]南京水利科学研究院水文水资源研究所,江苏南京210029 [2]水文水资源与水利工程科学国家重点实验室,江苏南京210029 [3]河海大学水利水电学院,江苏南京210098

出　　处：《排灌机械工程学报》2022年第5期461-466,481,共7页Journal of Drainage and Irrigation Machinery Engineering

基　　金：国家重点研发计划项目(2021YFC3200301);国家自然科学基金资助项目(51909168);中央公益性科研院所基本科研业务费项目(Y519008);重庆市交通局科技项目(2020-07)。

摘　　要：为解决河湖水位支持向量回归(SVR)模型输入变量选择问题,提出了基于进化算法的模型结构-参数同步优化方法.该方法可应对复杂河湖交汇水系输入变量搜索空间的高维特性,减小源自模型结构及参数不确定性的模型误差.将提出方法应用于洞庭湖城陵矶站和荆江陈二口站水位建模,结果显示:提出方法可准确反映不同影响因素对水位预测的作用大小,城陵矶水位预测最主要的外部变量为长江来水和湘江来水,陈二口水位预测则为枝城站和马家店水位;该方法可充分发掘SVR潜力,2个站点的水位模型均取得了理想精度(R^(2)>0.998);提出方法采用的n折交叉验证方式可有效避免模型过拟合问题.综上,提出的SVR模型结构-参数同步优化方法适用于河流湖泊,特别是复杂河湖交汇水系的水位建模.To solve the problem of input variables selection in support vector regression(SVR)model of river and lake water level,a synchronized optimization method of model structure-parameter based on envolutionary algorithm was proposed.The method can deal with the high-dimensional characteristics of the input variable search space of the complex river-lake water system,and reduce the model error resulting from the model structure and parameter uncertainties.The proposed method was applied to water level modeling at Chenglingji in Dongting Lake and Chenerkou in Jingjiang River.The results show that the proposed method can accurately reflect the effects of different influencing factors on water level prediction.The main external variables are discharged from the Yangtze River and Xiang River for Chenglingji,while thewater level prediction of Chenerkou is Zhicheng station and Majiadian water level;the method can fully exploit the potential of SVR,and the water level models at both stations achieve ideal accuracy(R^(2)>0.998);the n-fold cross-validation method used in the proposed can effectively avoids the model over-fitting problem.In summary,the proposed SVR model structure-parameter synchronous optimization method is suitable for water level modeling of rivers and lakes,especially complex river-lake water system.

关 键 词：水位预测 支持向量回归 输入变量选择 模型结构 模型参数 

分 类 号：S277.9[农业科学—农业水土工程]