Comparison of pedotransfer functions based on machine learning methods to estimate soil moisture at field capacity and permanent wilting point (Case study: Ravansar District, Kermanshah Province)

Document Type : Complete scientific research article

Authors

1 M.Sc. Graduate, Dept. of Water Engineering, Faculty of Agriculture, Razi University, Kermanshah, Iran.

2 Corresponding Author, Associate Prof., Dept. of Water Engineering, Faculty of Agriculture, Razi University, Kermanshah, Iran.

3 Research Assistant Prof., Soil and Water Research Department, Kermanshah Agricultural and Natural Resources Research and Education Center, AREEO, Kermanshah, Iran.

4 Assistant Researcher, Dept. of Water Engineering, Faculty of Agriculture, Razi University, Kermanshah, Iran.

Abstract

Background and Objectives: The physical properties of the soil, which cannot be easily measured, play an important role in the design of irrigation and drainage systems. Since the direct measurement of these characteristics is time-consuming and expensive, therefore, to estimate these parameters, most researchers use indirect methods such as transfer functions. This research aims to investigate and determine the best model for estimating soil moisture content in Field capacity (FC) and Permanent Wilting Point (PWP) using easily measured soil characteristics and pedotransfer functions in the R software environment and choosing the most suitable model for the soils of the Ravansar region in Kermanshah province.
Materials and methods: In this research, the easily measurable properties of soil were used as input variables for five transfer functions of the multivariable linear, artificial neural network, Cubist, random forest, and support vector machine. At first, in the study area, the location of 120 profiles was determined using the Latin hypercube method. In these observation points, soil profile was dug and studied and samples were taken from its horizons. Then, laboratory analysis including measurement of electrical conductivity, pH, calcium carbonate equivalent, organic carbon, and percentage of sand, silt, and clay was performed on soil samples. Based on the range of changes of these characteristics, especially the soil texture, 75 surface soil samples and 33 soil samples from ten different soil profiles were selected. PWP measurement was performed on 33 samples and FC measurement was performed on surface and depth samples, i.e., 108, and then modeling operations were performed on them. Root mean square error (RMSE), mean absolute error (MAE), and R2 indices were used to evaluate the models.
Results: The results showed that the accuracy of pedotransfer functions in estimating PWP is higher than FC (R2 and RMSE values of the Cubist model for PWP are 0.81 and 0.054 and for FC are 0.53 and 0.085, respectively). Also, the results for FC showed that between the models, the Cubist and the artificial neural network have low MAE (0.066 and 0.068) and RMSE (0.085) and high R2 (0.53 and 0.54) respectively, compared to other models.

Conclusion: The overall results showed that Cubist, Artificial Neural Network, and Random Forest models with lower error and higher R2 have higher efficiency for soil moisture estimation in FC than other models. The results showed that the Cubist and random forest models were the best models for estimating moisture at the PWP in terms of comparing the coefficient of determination. This research showed the importance of using new machine learning methods in studies related to soil transfer functions to estimate difficult-to-measure soil properties. Also, the results of this research are acceptable for a wide range of plains in Kermanshah province, which has similar soil formation conditions to the Ravansar region.

Keywords

Main Subjects

References

1.Schaap, M.G., and Leij, F.J. 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil and Tillage Research. 47: 1-2. 37-42.
2.Nemes, A., and Rawls, W.J. 2006. Evaluation of different representations of the particle-size distribution to predict soil water retention. Geoderma. 132: 1-2. 47-58.
3.Tomasella, J., Pachepsky, Y., Crestana, S., and Rawls, W.J. 2003. Comparison of two techniques to develope pedotransfer functions for water retention. Soil Science Society of American Journal, 67: 4. 1085-1092.
4.Bayat, H., Neyshabouri, M., Mohammadi, K., Nariman-Zadeh, N., Irannejad, M., and Gregory, A.S. 2013. Combination of artificial neural networks and fractal theory to predict soil water retention curve. Computers and Electronics in Agriculture. 92: 92-103.
5.Twarakavia, N.K.C., Simunek, J., and Schaap, M.G. 2009. Development of pedotransfer functions for estimation of soil hydraulic parameters using support vector machines. Soil Science Society of American Journal. 73: 5. 1443-1452.
6.Babaeian, E., Homaee, M., and Norouzi, A.A. 2014. Evaluating point and parametric spectral transfer functions for a prediction of soil water characteristics. Iranian Journal of Soil and Water Research. 45: 4. 475-490. (In Persian)
7.Mehrabi Gohri, A., Sarmidian, F., and Taghizadeh Mehrjardi, R. 2013. Prediction of the amount of water at Field Capacity and Permananent Wilting Point using Artificial Neural Network and Multivariate Regression. J. of Irrigation and water engineering. 3: 10. 42-52. (In Persian)
8.Amir Abedi, H., Asghari, S., Mesri Gandoshmin, T., and Keivan Behjo, F. 2013. Estimating of field capacity, permanent wilting and available water content in Ardabil plain soils using regression and artificial neural network models. Applied Soil Research. 1: 1. 60-72. (In Persian)
9.Norouzi Engnaee, O., Khalafi, M., and Karimi Soorvand, M. 2019. Investigating the performance of data-based methods in estimating important moisture points in Shahrood area. Journal of Irrigation Sciences and Engineering. 42: 4. 29-44. (In Persian)
10.Lieb, M., Glaser, B., and Huwe, B. 2012. Uncertainty in the spatial prediction of soil texture comparison of regression tree and random forest models. Groderma. 170: 70-79.
11.McBratney, A.B., Minasny, B., and Tranter, G. 2011. Necessary meta-data for pedotransfer functions. Geoderma. 160: 3-4. 627-629.
12.Rastgou, M., Bayat, H., Mansoorizadeh, M., and Gregory, Andrew S. 2020. Estimating the soil water retention curve: Comparison of multiple nonlinear regression approach and random forest data mining technique. Computers and Electronics in Agriculture. 174: 1-13.
13.Cueff, S., Coquet, Y.B., Aubertot, J.N., Bel, L., Pot, V., and Alletto, L. 2021. Estimation of soil water retention in conservation agriculture using published and new pedotransfer functions. Soil and Tillage Research. 209: 104967.
14.Abdelhafid, Y., Chebbah, M., and Rechachi, M.Z. 2021. Comparison of regression methods for predicting soil water contents at field capacity and wilting point in Bas Sahara of Algeria. International Journal of Forest, Soil and Erosion. 11: 2. 45-62.
15.Fritsch, S., Guenther, F., and Wright, M.N. 2019. neuralnet: Training of Neural Networks. URL https:// CRAN. R-project.org/ package = neuralnet. R package version 1.44.2.
16.Quinlan, J.R. 1992. Learning with continuous classes. P 343-348, In: Proceedings of 5th Australian conference on artificial intelligence. World Scientific. Singapore.
17.Zhou, Zhi-Hua. 2012. Ensemble Methods: Foundations and Algorithms. Chapman and Hall/CRC. 23p.
18.Kuhn, M., Weston, S., Keefer, C., Coulter, N., and Quinlan, R. 2023. Cubist: Rule-and Instance-based Regression Modeling, R package version 0.4.2.1. (https://cran.r-project.org/web/ packages/Cubist/Cubist.pdf. Last access date: 3 May 2023).
19.Breiman, L. 2001. Random forests. Machine Learning. 45: 1. 5-32.
20.Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Kenkel B., Team, R.C., Benesty, M., Lescarbeau, R., Ziem, A., Scrucca, L., Tang, Y., Candan, C., and Hunt, T. 2023. caret: Classification and Regression Training. R package version 6.0-94. (https:// cran.r-project.org/web/packages/ caret/ caret.pdf. Las access date: 3 May 2023).
21.Chang, C.C., and Lin, C.J. 2001. Libsvm: A library for support vector machines. ACM transactions on intelligent systems and technology (TIST) 2: 3. 1-27.
22.Cortes, C., and Vapnik, V. 1995. Support-vector networks. Machine Learning. 20: 3. 273-297.
23.Brus, D., Kempen, B., and Heuvelink, G. 2011. Sampling for validation of digital soil maps. European Journal of Soil Science. 62: 3. 394-407.
24.Manyam, C., Morgan, C.L., Heilman, J.L., Fatondji, D., Gerard, B., and Payne, W.A. 2007. Modeling hydraulic properties of sandy soils of Niger using pedotransfer functions. Geoderma. 141: 3-4. 407-415.
25.Gomes, F.P., and Garcia, C.H. 2002. Estatrstica Aplicada an Experimentos Agronomicos e Florestais. FEALQ: Piracicaba, 309p. (In Portuguese)
26.Botula, Y.D., Cornelis, W.M., Baert, G., and Van Ranst, E. 2012. Evaluation of pedotransferfunctions for predicting water retention of soils in Lower Congo (D.R. Congo). Agriculture Water Management, 111: 1-10.
27.Minh Nguyen, P., Van Le, Kh., Dady Botula, Y., and M. Cornelis, W. 2015. Evaluation of soil water retention pedotransfer functions for Vietnamese Mekong Delta soils. Agricultural Water Management. 158: 126-138.
28.Hutson, J.L., and Cass, A. 1987. A retentivity function for use in soil-water simulation models. Journal of Soil Science. 38: 1. 105-113.
29.Merdun, H., Cinar, O., Meral, R., and 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: 1-2. 108-116.
30.Mosaddeghi, M.R., and Mahboubi, A.A. 2011. Point pedotransfer functions for prediction of water retention of selected soil series in a semi-arid region of western Iran. Archives of Agronomy and Soil Science. 57: 4. 327-342.
31.Salchow, E., Lal, R., Fausey, N.R., and Ward, A. 1996. Pedotransfer functions for variable alluvial soils in Southern Ohio. Geoderma. 73: 3-4. 165-181.
32.Minasny, B., and McBratney, A. B. 2002. The Neuro-m Method for Fitting Neural Network Parametric Pedotransfer Functions. Soil Science Society American Journal. 66: 2. 352-361.
33.Medeiros, J.C., Cooper, M., Dalla Rosa, J., Grimaldi, M., and Coquet, Y.M. 2014. Assessment of pedotransfer functions for estimating soil water retention curves for the amazon region. Rev. Bras. Cien. Solo. 38: 3. 730-743.
Journal of Water and Soil Conservation
Volume 30, Issue 1
April 2023
Pages 27-47

Files

Share

How to cite

Statistics