RESEARCH PAPER
Estimating parameters of empirical infiltration models from the global dataset using machine learning
Seongyun Kim 1  
,   Gulay Karahan 2  
,   Manan Sharma 1  
,   Yakov Pachepsky 3  
 
More details
Hide details
1
USDA ARS EMFSL, BARC East, Bldg 201, RM 103, 10300 Baltimore Ave, Beltsville MD 20705 USA
2
Cankiri Karatekin University, Forestry Faculty, Department of Landscape Architecture, Department of Plant Material and Cultivation, 18100 Çankırı Turkey
3
USDA ARS EMFSL, BARC East, Bldg 177C, RM 108, 10300 Baltimore Ave, Beltsville MD 20705 USA
CORRESPONDING AUTHOR
Yakov Pachepsky   

Environmental Microbial and Food Safety Laboratory, USDA-ARS, United States
Final revision date: 2021-01-23
Acceptance date: 2021-01-29
Publication date: 2021-03-19
 
Int. Agrophys. 2021, 35(1): 73–81
 
KEYWORDS
TOPICS
ABSTRACT
It is beneficial to develop pedotransfer relationships to estimate infiltration equation coefficients in site-specific conditions from readily available data. No systematic studies have been published concerning the relationships between the accuracy of the infiltration equation and the accuracy of the predicted coefficients in this equation. The objective of this work was to test the hypothesis that, for the same infiltration data, the accuracy of pedotransfer predictions for coefficients in an infiltration equation is greater for the infiltration equation that performs better. The hypothesis was tested using the commonly employed Horton and Mezencev (modified Kostiakov) infiltration equations with data from the Soil Water Infiltration Global database. The random forest machine learning algorithm was used to develop the pedotransfer model. The Horton and the Mezencev models performed better with 928 and 758 datasets, respectively. The accuracy of the estimates of the infiltration equation coefficients did not differ substantially between the estimates obtained from all data and from the data where the infiltration equation had lower root-mean-squared error values. The root-mean-squared error values of the pedotransfer estimates decreased by 2 to 25% when only datasets with the same infiltration measurement method were considered. The development of predictive pedotransfer equations with the data obtained from the same infiltration measurement method is recommended.
 
REFERENCES (36)
1.
Araya S.N. and Ghezzehei T.A., 2019. Using machine learning for prediction of saturated hydraulic conductivity and its sensitivity to soil structural perturbations. Water Res. Res., 55(7), 5715-5737. https://doi.org/10.1029/2018wr....
 
2.
Bayabil H.K., Dile Y.T., Tebebu T.Y., Engda T.A., and Steenhuis T.S., 2019. Evaluating infiltration models and pedotransfer functions: implications for hydrologic modeling. Geoderma, 338, 159-169. https://doi.org/10.1016/j.geod....
 
3.
Brevnova E.V., 2001. Green-Ampt infiltration model parameter determination using SCS curve number (CN) and soil texture class, and application to the SCS runoff model. Graduate Theses, Dissertations, and Problem Reports, 1152. https://researchrepository.wvu....
 
4.
Brutsaert W., 1977. Vertical infiltration in dry soil. Water Res. Res., 13(2), 363-368. https://doi.org/10.1029/wr013i....
 
5.
Dashtaki S.G., Homaee M., Mahdian M.H., and Kouchakzadeh M., 2009. Site-dependence performance of infiltration models. Water Res. Manag., 23(13), 2777-2790. https://doi.org/10.1007/s11269....
 
6.
de Almeida W.S., Panachuki E., de Oliveira P.T.S., da Silva Menezes R., Sobrinho T.A., and de Carvalho D.F., 2018. Effect of soil tillage and vegetal cover on soil water infiltration. Soil Till. Res., 175, 130-138. https://doi.org/10.1016/j.stil....
 
7.
Farid H.U., Mahmood-Khan Z., Ahmad I., Shakoor A., Anjum M.N., Iqbal M.M., Mubeen M., and Asghar M., 2019. Estimation of infiltration models parameters and their comparison to simulate the onsite soil infiltration characteristics. Int. J. Agric. Biol. Eng., 12(3), 84-91. https://doi.org/10.25165/j.ija....
 
8.
Furman A., Warrick A.W., Zerihun D., and Sanchez C.A., 2006. Modified Kostiakov infiltration function: Accounting for initial and boundary conditions. J. Irrig. Drain. Eng., 132(6), 587-596. https://doi.org/10.1061/(asce)....
 
9.
Ghanbarian B., Taslimitehrani V., Dong G., and Pachepsky Y.A., 2015. Sample dimensions effect on prediction of soil water retention curve and saturated hydraulic conductivity. J. Hydrol., 528, 127-137. https://doi.org/10.1016/j.jhyd....
 
10.
Green W.H. and Ampt G.A., 1911. Studies on soil physics. Part I. The flow of air and water through soils. J. Agric. Sci., 4, 1-24.
 
11.
Hastie T., Tibshirani R., and Friedman J., 2009. The elements of statistical learning: data mining, inference and prediction. Springer Science+Business Media, New York, NY. http://www.springerlink.com/in....
 
12.
Holtan H.N., 1961. A Concept for Infiltration Estimates in Watershed Engineering. USDA Bulletin, Washington, DC, USA.
 
13.
Horton R.E., 1940. An approach towards a physical interpretation of infiltration capacity. Soil Sci. Soc. Am. J., 5, 399-417.
 
14.
Kidwell M.R., Weltz M.A., and Guertin D.P., 1997. Estimation of green-Ampt effective hydraulic conductivity for rangelands. Rangeland Ecol. Manag./J. Range Manag. Archives, 50(3), 290-299. https://doi.org/10.2307/400373....
 
15.
Kostiakov A.N., 1932. On the dynamics of the coefficients of water percolation in soils and on the necessity of studying it from a dynamic point of view for purpose of amelioration. Trans. Sixth Comm. Int. Soc. Soil Sci., 1, 7-21.
 
16.
Kutílek M. and Krejča M., 1987. A three-parameter infiltration equation of the Philip’s type solution (in Czech). Vodohosp.Čas., 35, 52-61.
 
17.
Lei G., Fan G., Zeng W., and Huang J., 2020. Estimating parameters for the Kostiakov-Lewis infiltration model from soil physical properties. J. Soils Sediments, 20(1), 166-180. https://doi.org/10.1007/s11368....
 
18.
Liaw A. and Wiener M., 2018. Breiman and Cutler’s Random Forests for Classification and Regression. R Package ‘random Forest. https://cran.r-Fproject.org/we....
 
19.
Maheshwari B.L., 1997. Interrelations among physical and hydraulic parameters of non-cracking soils. J. Agric. Eng. Res., United Kingdon, 68(4), 297-309.
 
20.
Mazloom H. and Foladmand H., 2013. Evaluation and determination of the coefficients of infiltration models in Marvdasht region, Fars province. Int. J. Advanced Biolog. Biomedical Res., 1(8): 822-829.
 
21.
Mezencev V.J., 1948. Theory of formation of the surface runoff (in Russian). Meteorol. Gidrol., 3, 33-40.
 
22.
Mishra S.K., Tyagi J.V., and Singh V.P., 2003. Comparison of infiltration models. Hydrol. Process., 17(13), 2629-2652. https://doi.org/10.1002/hyp.12....
 
23.
Pachepsky Y., Guber A.K., Yakirevich A.M., McKee L., Cady R.E., and Nicholson T.J., 2014. Scaling and pedotransfer in numerical simulations of flow and transport in soils. Vadose Zone J., 13(12). https://doi.org/10.2136/vzj201....
 
24.
Pachepsky Y. and Park Y., 2015. Saturated hydraulic conductivity of US soils grouped according to textural class and bulk density. Soil Sci. Soc. Am. J., 79(4), 1094-1100. https://doi.org/10.2136/sssaj2....
 
25.
Pachepsky Y. and Rawls W.J., 2003. Soil structure and pedotransfer functions. Eur. J. Soil Sci., 54(3), 443-452. https://doi.org/10.1046/j.1365....
 
26.
Pandey P.K. and Pandey V., 2019. Estimation of infiltration rate from readily available soil properties (RASPs) in fallow cultivated land. Sust. Water Res. Manag., 5(2), 921-934. https://doi.org/10.1007/s40899....
 
27.
Parchami-Araghi F., Mirlatifi S.M., Dashtaki S.G., and Mahdian M.H., 2013. Point estimation of soil water infiltration process using Artificial Neural Networks for some calcareous soils. J. Hydrol., 481, 35-47. https://doi.org/10.1016/j.jhyd....
 
28.
Philip J.R., 1957. The theory of infiltration: The infiltration equation and its solution. Soil Sci., 83, 345-357. https://doi.org/10.1097/000106....
 
29.
R Core Team. R, 2019. The R project for statistical computing. http://www.R-project.org/.
 
30.
Rahmati M., 2017. Reliable and accurate point-based prediction of cumulative infiltration using soil readily available characteristics: a comparison between GMDH, ANN, and MLR. J. Hydrol., 551, 81-91. https://doi.org/10.1016/j.jhyd....
 
31.
Rahmati M., Weihermüller L., Vanderborght J., Pachepsky Y.A., Mao L., Sadeghi S.H., Moosavi N., Kheirfam H., Montzka C., Van Looy K., and Toth B., 2018. Development and analysis of the Soil Water Infiltration Global database. Earth System Science Data, 10, 1237-1263.
 
32.
Salahou M.K., Jiao X., and Lü H., 2020. Assessment of empirical and semi-empirical models for estimating a soil infiltration function. Trans. ASABE, 63(4), 833-845. https://doi.org/10.13031/trans....
 
33.
Santra P., Kumar M., and Kumawat R.N., 2021. Characterization and modeling of infiltration characteristics of soils under major land use systems in Hot Arid Region of India. Agric. Res., 1-17. https://doi.org/10.1007/s40003....
 
34.
Shao Q. and Baumgartl T., 2014. Estimating input parameters for four infiltration models from basic soil, vegetation, and rainfall properties. Soil Sci. Soci. Am. J., 78(5), 1507-1521. https://doi.org/10.2136/sssaj2....
 
35.
Swartzendruber D., 1987. A quasi‐solution of Richards’ Equation for the downward infiltration of water into soil. Water Res. Res., 23(5), 809-817. https://doi.org/10.1029/wr023i....
 
36.
Van de Genachte G., Mallants D., Ramos J., Deckers J.A., and Feyen J., 1996. Estimating infiltration parameters from basic soil properties. Hydrol. Processes, 10(5), 687-701. https://doi.org/10.1002/(sici)...<687::aid-hyp311>3.0.co;2-p.
 
eISSN:2300-8725
ISSN:0236-8722