A data-driven approach to predict soil hydraulic conductivity: GMDH compared with ANN and multiple regression

Document Type : Original Article

Author

1 Department of Soil Science and Engineering, Faculty of Agriculture, University of Maragheh, Maragheh, Iran, 2 Forschungszentrum Jülich GmbH, Institute of Bio- and Geosciences: Agrosphere (IBG-3), Jülich, Germany

Abstract

Accurate estimation of saturated hydraulic conductivity (Ks) is essential for soil and water management, yet the reliability of the pedotransfer functions (PTFs) is often overlooked.Tthis study compares the predictive performance and the robustness of field estimates of Ks obtained by three types of PTFs: Multiple Regression (MR), Artificial Neural Networks (ANN) and the Group Method of Data Handling (GMDH) developed using 134 soil samples collected in north-western Iran, which is a region with semi-arid conditions and mixed agricultural uses whereas the dataset encompasses a wide range of structural and textural variationsto Ks prediction. In addition to traditional soil properties soil moisture deficit compared to the optimum value at the time of sampling, θd, was used as a proxy indicator of soil structural condition. Model precision was evaluated using Root Mean Square Error (RMSE) and the Nash–Sutcliffe efficiency; reliability was determined through repeated data splitting. Even though ANN provided good accuracy for the training set, its performance for the validation set was inconsistence. MR produced consistent, albeit limited performances over both the training and validation subsets. Conversely, GMDH appears to strike a good compromise between prediction accuracy, reliability, parsimony of the predictor set, and texture versus structure variables. The results point to the importance of including structural measures such as θd in PTF development and provide a basis for considering model repeatability a long with accuracy. In general, the results indicate that GMDH is a robust and feasible technique to develop accurate PTFs for Ks predictions with limited amount of data.

Keywords

Main Subjects

References

Agyare, W.A., Park, S., Vlek, P., 2007. Artificial neural network estimation of saturated hydraulic conductivity. Vadose Zone Journal 6(2), 423-431.
Aimrun, W., Amin, M., 2009. Pedo-transfer function for saturated hydraulic conductivity of lowland paddy soils. Paddy and Water Environment 7(3), 217-225.
Albalasmeh, A., Mohawesh, O., Gharaibeh, M., Deb, S., Slaughter, L., & El Hanandeh, A. (2022). Artificial neural network optimization to predict saturated hydraulic conductivity in arid and semi-arid regions. Catena, 217, 106459.
Alvarez-Acosta, C., Lascano, R.J., Stroosnijder, L., 2012. Test of the Rosetta pedotransfer function for saturated hydraulic conductivity. Open Journal of Soil Science 2(03), 203.
Arshad, R., Sayad, G., Mazlum, M., Jafarnejadi, A., Mohammadi Safarzadeh, V., 2010. Pedo-transfer functions application to estimate the infiltration rate of the soil using neural network and linear regression methods. Journal of Crop Improvement 2(5), 55-62.
Arshad, R.R., Sayyad, G., Mosaddeghi, M., Gharabaghi, B., 2013. Predicting saturated hydraulic conductivity by artificial intelligence and regression models. ISRN Soil Science 2013.
Bouma, J., 1989. Using soil survey data for quantitative land evaluation, Advances in soil science. Springer, pp. 177-213.
Brakensiek, D., Rawls, W., Stephenson, G., 1984. Modifying SCS hydrologic soil groups and curve numbers for rangeland soils. American Society of Agricultural Engineers.
Brooks, R.H., Corey, A.T., 1966. Properties of porous media affecting fluid flow. Journal of the Irrigation and Drainage Division 92(2), 61-90.
Campbell, G., Shiozawa, S., 1992. Prediction of hydraulic properties of soils using particle-size distribution and bulk density data. Indirect methods for estimating the hydraulic properties of unsaturated soils. University of California, Riverside, 317-328.
Campbell, G.S., 1974. A simple method for determining unsaturated conductivity from moisture retention data. Soil science 117(6), 311-314.
Christiaens, K., Feyen, J., 2001. Analysis of uncertainties associated with different methods to determine soil hydraulic properties and their propagation in the distributed hydrological MIKE SHE model. Journal of Hydrology 246(1), 63-81.
Cosby, B., Hornberger, G., Clapp, R., Ginn, T., 1984. A statistical exploration of the relationships of soil moisture characteristics to the physical properties of soils. Water resources research 20(6), 682-690.
Dane, J., Puckett, W., 1994. Field soil hydraulic properties based on physical and mineralogical information, Proceedings of the international workshop on indirect methods for estimating the hydraulic properties of unsaturated soils. University of California, Riverside, pp. 389-403.
Doussan, C., Ruy, S., 2009. Prediction of unsaturated soil hydraulic conductivity with electrical conductivity. Water Resources Research 45(10).
Elbisy, M. S. (2025). Predictive Modeling of Saturated Hydraulic Conductivity using Machine Learning Techniques. Engineering, Technology & Applied Science Research, 15(2), 21348-21355.
Farlow, S.J., 1984. Self-organizing methods in modeling: GMDH type algorithms, 54. CrC Press.
Flint, A.L., Flint, L.E., 2002. 2.2 Particle Density. Methods of Soil Analysis: Part 4 Physical Methods (methodsofsoilan4), 229-240.
Gee, G.W., Or, D., 2002. 2.4 Particle-size analysis. Methods of soil analysis. Part 4, 255-293.
Ghanbarian-Alavijeh, B., Liaghat, A., Sohrabi, S., 2010. Estimating saturated hydraulic conductivity from soil physical properties using neural networks model. World Acad. Sci. Eng. Technol 4, 108-113.
Grossman, R., Reinsch, T., 2002. 2.1 Bulk density and linear extensibility. Methods of Soil Analysis: Part 4 Physical Methods (methodsofsoilan4), 201-228.
Grossman, R., Reinsch, T., Dane, J., Topp, G., 2002. Methods of soil analysis. Part 4. Physical methods. Methods of soil analysis: Parth 4. Physical methods.
Gupta, R., Rudra, R., Dickinson, W., Patni, N., Wall, G., 1993. Comparison of saturated hydraulic conductivity measured by various field methods. Transactions of the ASAE 36(1), 51-55.
Hecht-Nielsen, R., 1990. Solution for a distributed hydrological model and applications. Neurocomputing, Addison-Wesley, Reading, MA, 89-93.
Herbst, M., Diekkrüger, B., Vanderborght, J., 2006. Numerical experiments on the sensitivity of runoff generation to the spatial variation of soil hydraulic properties. Journal of Hydrology 326(1), 43-58.
Islam, N., Wallender, W.W., Mitchell, J.P., Wicks, S., Howitt, R.E., 2006. Performance evaluation of methods for the estimation of soil hydraulic parameters and their suitability in a hydrologic model. Geoderma 134(1), 135-151.
Jabro, J., 1992. Estimation of saturated hydraulic conductivity of soils from particle size distribution and bulk density data. Transactions of the ASAE 35(2), 557-560.
Julia, M.F., Monreal, T.E., del Corral Jiménez, A.S., Meléndez, E.G.a., 2004. Constructing a saturated hydraulic conductivity map of Spain using pedotransfer functions and spatial prediction. Geoderma 123(3), 257-277.
Klute, A., Dirksen, C., 1986. Hydraulic conductivity and diffusivity: Laboratory methods. Methods of Soil Analysis: Part 1—Physical and Mineralogical Methods (methodsofsoilan1), 687-734.
Kosugi, K.i., 1996. Lognormal distribution model for unsaturated soil hydraulic properties. Water Resources Research 32(9), 2697-2703.
Logsdon, S., Berli, M., Horn, R., 2013. Quantifying and modeling soil structure dynamics. Soil Science Society of America.
Luk, K., Ball, J.E., Sharma, A., 2000. A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting. Journal of Hydrology 227(1), 56-65.
Mallants, D., Jacques, D., Tseng, P.-H., van Genuchten, M.T., Feyen, J., 1997a. Comparison of three hydraulic property measurement methods. Journal of hydrology 199(3-4), 295-318.
Mallants, D., Mohanty, B.P., Vervoort, A., Feyen, J., 1997b. Spatial analysis of saturated hydraulic conductivity in a soil with macropores. Soil Technology 10(2), 115-131.
Masís-Meléndez, F., Deepagoda, T.C., de Jonge, L.W., Tuller, M., Moldrup, P., 2014. Gas diffusion-derived tortuosity governs saturated hydraulic conductivity in sandy soils. Journal of Hydrology 512, 388-396.
McBratney, A.B., Minasny, B., Cattle, S.R., Vervoort, R.W., 2002. From pedotransfer functions to soil inference systems. Geoderma 109(1), 41-73.
Merdun, H., Çınar, Ö., Meral, R., Apan, M., 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research 90(1), 108-116.
Minasny, B., Hopmans, J., Harter, T., Eching, S., Tuli, A., Denton, M., 2004. Neural networks prediction of soil hydraulic functions for alluvial soils using multistep outflow data. Soil Science Society of America Journal 68(2), 417-429.
Mohanty, B., Kanwar, R.S., Everts, C., 1994. Comparison of saturated hydraulic conductivity measurement methods for a glacial-till soil. Soil Science Society of America Journal 58(3), 672-677.
Møller, M.F., 1993. A scaled conjugate gradient algorithm for fast supervised learning. Neural networks 6(4), 525-533.
Montzka, C., Herbst, M., Weihermüller, L., Verhoef, A., Vereecken, H., 2017. A global data set of soil hydraulic properties and sub-grid variability of soil water retention and hydraulic conductivity curves. Earth Syst. Sci. Data Discuss. 2017, 1-25.
Moosavi, A. A., Nematollahi, M. A., & Omidifard, M. (2024). Comparing machine learning approaches for estimating soil saturated hydraulic conductivity. PloS one, 19(11), e0310622.
Mozaffari, H., Moosavi, A. A., & Nematollahi, M. A. (2024). Predicting saturated and near-saturated hydraulic conductivity using artificial neural networks and multiple linear regression in calcareous soils. Plos one, 19(1), e0296933.
Mozaffari, H., Pakjoo, M., Nematollahi, M. A., Forouzan, S., & Moosavi, A. A. (2025). Predicting Soil Hydraulic Conductivity: A Review of Artificial Neural Networks Applications. Artificial Intelligence Applications for a Sustainable Environment, 441-462.
Mualem, Y., 1976. A new model for predicting the hydraulic conductivity of unsaturated porous media. Water resources research 12(3), 513-522.
Naderianfar, M. (2025). Developing a simple artificial intelligence fuzzy-based model for estimating saturated hydraulic conductivity of soil. Scientific Reports, 15(1), 28476.
Nash, J.E., Sutcliffe, J.V., 1970. River flow forecasting through conceptual models part I—A discussion of principles. Journal of hydrology 10(3), 282-290.
Nelson, D., Sommers, L.E., 1982. Total carbon, organic carbon, and organic matter. Methods of soil analysis. Part 2. Chemical and microbiological properties (methodsofsoilan2), 539-579.
Neyshabouri, M.R., Rahmati, M., Doussan, C., Behroozinezhad, B., 2013. Simplified estimation of unsaturated soil hydraulic conductivity using bulk electrical conductivity and particle size distribution. Soil research 51(1), 23-33.
Neyshaboury, M.R., Rahmati, M., Alavi, S.A.R., Rezaee, H., Nazemi, A., 2015. Prediction of unsaturated soil hydraulic conductivity using air permeability: Regression approach. Indian Journal Of Agricultural Research 49(6).
Nimmo, J.R., Perkins, K.S., 2002. 2.6 Aggregate Stability and Size Distribution. Methods of soil analysis: Part 4, 317-328.
Pachepsky, Y., Rawls, W., Gimenez, D., Watt, J., 1998. Use of soil penetration resistance and group method of data handling to improve soil water retention estimates. Soil and Tillage Research 49(1), 117-126.
Pachepsky, Y.A., Rawls, W., 1999. Accuracy and reliability of pedotransfer functions as affected by grouping soils. Soil Science Society of America Journal 63(6), 1748-1757.
Pachepsky, Y.A., Timlin, D., Varallyay, G., 1996. Artificial neural networks to estimate soil water retention from easily measurable data. Soil Science Society of America Journal 60(3), 727-733.
Paige, G.B., Hillel, D., 1993. Comparison of three methods for assessing soil hydraulic properties. Soil Science 155(3), 175-189.
Parasuraman, K., Elshorbagy, A., Si, B.C., 2006. Estimating saturated hydraulic conductivity in spatially variable fields using neural network ensembles. Soil Science Society of America Journal 70(6), 1851-1859.
Puckett, W., Dane, J., Hajek, B., 1985. Physical and mineralogical data to determine soil hydraulic properties. Soil Science Society of America Journal 49(4), 831-836.
Rahmati, M., Oskouei, M. M., Neyshabouri, M. R., Walker, J. P., Fakherifard, A., Ahmadi, A., & Mousavi, S. B. (2015). Soil moisture derivation using triangle method in the lighvan watershed, north western Iran. Journal of soil science and plant nutrition, 15(1), 167-178.
Rahmati, M., 2017. Reliable and accurate point-based prediction of cumulative infiltration using soil readily available characteristics: a comparison between GMDH, ANN, and MLR. Journal of Hydrology On Press.
Rahmati, M., Neyshaboury, M.R., 2016. Soil Air Permeability Modeling and Its Use for Predicting Unsaturated Soil Hydraulic Conductivity. Soil Science Society of America Journal 80(6), 1507-1513.
Rahmati, M., Neyshabouri, M. R., Mohammadi-Oskooei, M., Fakheri-Fard, A., & Ahmadi, A. (2020). Characterizing soil infiltration parameters using field/laboratory measured and remotely-sensed data. Environmental Resources Research, 8(2), 129-146.
Reynolds, W., Elrick, D., 1985. In situ measurement of field-saturated hydraulic conductivity, sorptivity, and the α-parameter using the guelph permeameter. Soil Science 140(4), 292-302.
Reynolds, W., Elrick, D., Youngs, E., Amoozegar, A., Booltink, H., Bouma, J., 2002. 3.4 Saturated and field-saturated water flow parameters. Methods of soil analysis, Part 4, 797-801.
Or, D., Keller, T., & Schlesinger, W. H. (2021). Natural and managed soil structure: On the fragile scaffolding for soil functioning. Soil and Tillage Research, 208, 104912.
Sarmadian, F., Taghizadeh-Mehrjardi, R., 2014. Estimation of infiltration rate and deep percolation water using feed-forward neural networks in Gorgan Province. Eurasian Journal of Soil Science 3(1), 1.
Saxton, K., Rawls, W.J., Romberger, J., Papendick, R., 1986. Estimating generalized soil-water characteristics from texture. Soil Science Society of America Journal 50(4), 1031-1036.
Schaap, M.G., Leij, F.J., 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil and Tillage Research 47(1), 37-42.
Schaap, M.G., Leij, F.J., Van Genuchten, M.T., 1998. Neural network analysis for hierarchical prediction of soil hydraulic properties. Soil Science Society of America Journal 62(4), 847-855.
Sharghi, F., Bauke, S. L., Rahmati, M., Burger, D. J., Vereecken, H., & Amelung, W. (2025). Soil infiltration variability across diverse soil reference groups, textures, and landuse types. Geoderma, 463, 117550.
Sirkin, R.M., 2006. Two-sample t test. In: R.M. Sirkin (Ed.), Statistics for the Social Sciences Thousand Oaks, Calif.: Sage Publications. xxi, London, New Delhi, pp. 271-358.
Spychalski, M., Kaźmierowski, C., Kaczmarek, Z., 2007. Estimation of saturated hydraulic conductivity on the basis of drainage porosity. Electronic Journal of Polish Agricultural Universities 10(1), 04.
Suleiman, A., Ritchie, J., 2001. Estimating saturated hydraulic conductivity from soil porosity. Transactions of the ASAE 44(2), 235.
Tietje, O., Hennings, V., 1996. Accuracy of the saturated hydraulic conductivity prediction by pedo-transfer functions compared to the variability within FAO textural classes. Geoderma 69(1-2), 71-84.
van Genuchten, M.T., 1980. A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil science society of America journal 44(5), 892-898.
Vereecken, H., Maes, J., Feyen, J., 1990. Estimating unsaturated hydraulic conductivity from easily measured soil properties. Soil Science 149(1), 1-12.
Vereecken, H., Schnepf, A., Hopmans, J., Javaux, M., Or, D., Roose, T., Vanderborght, J., Young, M., Amelung, W., Aitkenhead, M., 2016. Modeling soil processes: Review, key challenges, and new perspectives. Vadose zone journal 15(5).
Vereecken, H., Amelung, W., Bauke, S. L., Bogena, H., Brüggemann, N., Montzka, C., ... & Zhang, Y. (2022). Soil hydrology in the Earth system. Nature Reviews Earth & Environment, 3(9), 573-587.
Webster, M., 2006. Merriam-Webster online dictionary.
Weihermüller, L., Lehmann, P., Herbst, M., Rahmati, M., Verhoef, A., Or, D., ... & Vereecken, H. (2021). Choice of pedotransfer functions matters when simulating soil water balance fluxes. Journal of Advances in Modeling Earth Systems, 13(3), e2020MS002404.
Wösten, J., 1997. Pedotransfer functions to evaluate soil quality. Developments in Soil Science 25, 221-245.
Wösten, J., Lilly, A., Nemes, A., Le Bas, C., 1999. Development and use of a database of hydraulic properties of European soils. Geoderma 90(3), 169-185.
Yamaç, S. S., Negiş, H., Şeker, C., Memon, A. M., Kurtuluş, B., Todorovic, M., & Alomair, G. (2022). Saturated hydraulic conductivity estimation using artificial intelligence techniques: a case study for calcareous alluvial soils in a semi-arid region. Water, 14(23), 3875.
Zhao, C., Shao, M.a., Jia, X., Nasir, M., Zhang, C., 2016. Using pedotransfer functions to estimate soil hydraulic conductivity in the Loess Plateau of China. Catena 143, 1-6.
Dryland Soil Research (DLSR)
Volume 2, Issue 1
March 2025
Pages 65-79

Files

Share

How to cite

Statistics

تحت نظارت وف ایرانی