文献类型：期刊文献

英文题名：Groundwater Depth Prediction Using Data-Driven Models with the Assistance of Gamma Test

作者：Tian, Jiyang[1] Li, Chuanzhe[1] Liu, Jia[1,2] Yu, Fuliang[1] Cheng, Shuanghu[3] Zhao, Nana[4] Jaafar, Wan ZurinaWan[5]

第一作者：Tian, Jiyang

通信作者：Li, CZ[1]

机构：[1]China Inst Water Resources & Hydropower Res, State Key Lab Simulat & Regulat Water Cycle River, Beijing 100038, Peoples R China;[2]Hohai Univ, State Key Lab Hydrol Water Resource & Hydraulirc, Nanjing 210098, Jiangsu, Peoples R China;[3]Bur Water Resources Survey Heibei, Shijiazhuang 050031, Peoples R China;[4]Chinese Acad Forestry, Inst Wetland Res, Beijing 100091, Peoples R China;[5]Univ Malaya, Fac Engn, Dept Civil Engn, Kuala Lumpur 50603, Malaysia

年份：2016

卷号：8

期号：11

外文期刊名：SUSTAINABILITY

收录：;Scopus(收录号：2-s2.0-85000460203);WOS:【SSCI(收录号:WOS:000389316200002)，SCI-EXPANDED(收录号:WOS:000389316200002)】；

基金：This study was supported by the National Natural Science Foundation of China (Grant No. 51409270), partition prediction of groundwater system of Hebei Province, the foundation of China Institute of Water Resources and Hydropower Research (1232), the International Science and Technology Cooperation Program of China (Grant No. 2013DFG70990), and the Open Research Fund Program of State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering (2014490611).

语种：英文

外文关键词：groundwater dynamics prediction; data-driven models; Gamma Test; power function model; back-propagation artificial neural network; support vector machine

摘要：Prediction of the groundwater dynamics via models can help better manage the groundwater resources and guarantee their sustainable use. Three types of data-driven models are built for groundwater depth prediction in the plain of Shijiazhuang, the capital of Hebei Province in North China. The data-driven models include the Power Function Model (PFM), Back-Propagation Artificial Neural Network (BPANN) and Support Vector Machines (SVM) with two kernel functions of linear kernel function (LKF) and radial basis function (RBF). Five classes of factors (including 12 indices) are considered as potential model input variables. The Gamma Test (GT) is adopted in this study to help identify the relative importance of the input indices and tackle the tricky issue of the optimal input combinations for the data-driven models. The established models are evaluated in both fitting and testing procedures based on the root mean squared error (RMSE) and Nash-Sutcliffe efficiency (E) for different input combination schemes. The results show that SVM (RBF) performs the best. It is interesting to find that the natural factors (i.e., precipitation and evaporation) are less relevant to the groundwater depth variations. The methods used in this study have much significance for groundwater depth prediction in areas lacking hydrogeological data.