Comparing the Soil Conservation Service model with new machine learning algorithms for predicting cumulative infiltration in semi-arid regions

作     者：Khabat KHOSRAVI Phuong T.T.NGO Rahim BARZEGAR John QUILTY Mohammad T.AALAMI Dieu T.BUI Khabat KHOSRAVI;Phuong T.T.NGO;Rahim BARZEGAR;John QUILTY;Mohammad T.AALAMI;Dieu T.BUI

作者机构：Department of Watershed Management EngineeringFerdowsi University of MashhadMashhad 93(Iran) Department of Earth and EnvironmentFlorida International UniversityMiami 33199(USA) Institute of Research and DevelopmentDuy Tan UniversityDa Nang 550000(Vietnam) Department of Bioresource EngineeringMcGill UniversitySte Anne de Bellevue QC H9X(Canada) Faculty of Civil EngineeringUniversity of TabrizTabriz 51(Iran) Department of Civil and Environmental EngineeringUniversity of WaterlooWaterloo N2L 3G1(Canada) Department of Business and ITUniversity of South-Eastern NorwayNotodden 3603(Norway) 

出 版 物：《Pedosphere》 (土壤圈（英文版）)

年 卷 期：2022年第32卷第5期

页      面：718-732页

核心收录：

学科分类：08[工学] 0815[工学-水利工程] 0903[农学-农业资源与环境] 

主　　题：additive regression hybrid algorithms empirical model soil water infiltration weighted instances handler wrapper 

摘      要：Water infiltration into soil is an important process in hydrologic cycle;however,its measurement is difficult,time-consuming and costly.Empirical and physical models have been developed to predict cumulative infiltration(CI),but are often inaccurate.In this study,several novel standalone machine learning algorithms(M5Prime(M5P),decision stump(DS),and sequential minimal optimization(SMO))and hybrid algorithms based on additive regression(AR)(i.e.,AR-M5P,AR-DS,and AR-SMO)and weighted instance handler wrapper(WIHW)(i.e.,WIHW-M5P,WIHW-DS,and WIHW-SMO)were developed for CI prediction.The Soil Conservation Service(SCS)model developed by the United States Department of Agriculture(USDA),one of the most popular empirical models to predict CI,was considered as a benchmark.Overall,154 measurements of CI(explanatory/input variables)were taken from 16 sites in a semi-arid region of Iran(Illam and Lorestan provinces).Six input variable combinations were considered based on Pearson correlations between candidate model inputs(time of measuring and soil bulk density,moisture content,and sand,clay,and silt percentages)and CI.The dataset was divided into two subgroups at random:70%of the data were used for model building(training dataset)and the remaining 30%were used for model validation(testing dataset).The various models were evaluated using different graphical approaches(bar charts,scatter plots,violin plots,and Taylor diagrams)and quantitative measures(root mean square error(RMSE),mean absolute error(MAE),Nash-Sutcliffe efficiency(NSE),and percent bias(PBIAS)).Time of measuring had the highest correlation with CI in the study area.The best input combinations were different for different algorithms.The results showed that all hybrid algorithms enhanced the CI prediction accuracy compared to the standalone models.The AR-M5P model provided the most accurate CI predictions(RMSE=0.75 cm,MAE=0.59 cm,NSE=0.98),while the SCS model had the lowest performance(RMSE=4.77 cm,MAE=2.64 cm,NSE=0.23).The differences in RMSE between the best model(AR-M5P)and the second-best(WIHW-M5P)and worst(SCS)were 40%and 84%,respectively.