Pedosphere 32(5): 718--732, 2022
ISSN 1002-0160/CN 32-1315/P
©2022 Soil Science Society of China
Published by Elsevier B.V. and Science Press
Comparing the Soil Conservation Service model with new machine learning algorithms for predicting cumulative infiltration in semi-arid regions
Khabat KHOSRAVI1,2, Phuong T. T. NGO3, Rahim BARZEGAR4,5, John QUILTY6, Mohammad T. AALAMI5, Dieu T. BUI7
1Department of Watershed Management Engineering, Ferdowsi University of Mashhad, Mashhad 93 (Iran)
2Department of Earth and Environment, Florida International University, Miami 33199 (USA)
3Institute of Research and Development, Duy Tan University, Da Nang 550000 (Vietnam)
4Department of Bioresource Engineering, McGill University, Ste Anne de Bellevue QC H9X (Canada)
5Faculty of Civil Engineering, University of Tabriz, Tabriz 51 (Iran)
6Department of Civil and Environmental Engineering, University of Waterloo, Waterloo N2L 3G1 (Canada)
7Department of Business and IT, University of South-Eastern Norway, Notodden 3603 (Norway)
Corresponding Author:Khabat KHOSRAVI
      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.
Key Words:  additive regression,hybrid algorithms,empirical model,soil water infiltration,weighted instances handler wrapper
Citation: Khosravi K, Ngo P T T, Barzegar R, Quilty J, Aalami M T, Bui D T. 2022. Comparing the Soil Conservation Service model with new machine learning algorithms for predicting cumulative infiltration in semi-arid regions. Pedosphere. 32(5): 718-732.
View Full Text

Copyright © 2024 Editorial Committee of PEDOSPHERE. All rights reserved.
Address: No.298 Chuangyou Road, Jiangning District, Nanjing 210008, China PostCode:211135    E-mail:
Technical support: Beijing E-Tiller Co.,Ltd.