Mathematical Model of Soil Cation Exchange Capacity Using GMDH-type Neural Network and Genetic Algorithm
Keywords:
Artificial neural network, Clay, GMDH model, Pedotransfer functionsAbstract
Measuring the cation exchange capacity (CEC) for all horizons of every map unit component in a survey area is very time consuming and costly. This study was conducted (i) to evaluate the group method of data handling (GMDH) neural network (NN) and genetic algorithm model and (ii) to compare GMDH-type NN with other artificial neural networks such as the multilayer perceptron (MLP), radial basis function (RBF) and regression-based models for predicting CEC in soils of Lahijan, north of Iran. In this paper, the proposed model was trained before requested predictions. The data set was divided into two parts: 70% were used as data for training (110 soil samples), and 30% (40 soil samples) were used as a test set, which were randomly extracted from the database. In order to evaluate the models, coefficient of determination (R2), mean square error (MSE), root mean square error (RMSE) and mean absolute deviation (MAD) were used. Results showed that the GMDH-type and MLP NN models had larger R2 values than the multiple regression and RBF models. The results of GMDH model were very encouraging and congruent with the experimental results. In general, the GMDH-type-NNs models provided more reliable predictions than the ANNs and regression-based models.
References
Amini, M., Abbaspour, K.C., Khademi, H., Fathipour, N., Afyuni, M., Schulin, R., 2005. Neural network models to predict cation exchange capacity in arid regions of Iran. Eur. J. Soil Sci., 56, 551-559.
Anells, R.N., Arthurton, R.S., Bazley, R.A., Davis, R.G., 1975. Explanatory text of the Qazvin and Rasht Quadrangle map, 1:250,000. Geological survey of Iran, E3 and E4, p. 94.
Bell, M.A., van Keulen, J., 1995. Soil pedotransfer functions for four Mexican soils. Soil Sci. Soc. Am. J., 59, 865–871.
Drake, E.H., Motto, H.L., 1982. An analysis of the effect of clay and organic matter content on the cation exchange capacity of New Jersey soils. Soil Sci., 133, 281–288.
Erzin, Y., Hanumantha, Rao, B., Singh, D.N., 2008. Artificial neural network models for predicting soil thermal resistivity, Int. J. Therm. Sci., 47, 1347–1358.
Farlow, S.J., 1984. Self-Organizing Method in Modelling: GMDH-Type Algorithm, Marcel Dekker, New York.
Gee, G.W., Or, D., 2002. Particle-size analysis, In: Dane J.H., Topp G.C., (eds.). Methods of soil analysis, Part 4- Physical methods. Agronomy Monograph, vol. 9. ASA and SSSA, Madison, WI. USA. p. 255-293.
Ghanadzadeh, H., Ganji, M., Fallahi, S., 2012. Mathematical model of liquid–liquid equilibrium for a ternary system using the GMDH-type neural network and genetic algorithm. Appl. Math. Model., 36, 4096–4105.
Hagan, M.T., Demuth, H.B., Beale, M., 2002. Neural Network Design, Thomson Learning Pub., Singapore. p. 736.
Haykin, S., 1998. Neural Networks: A Comprehensive Foundation, 2nd edition. New York: Macmillan College Publishing.
Hecht-Nielsen, R., 1990. Neurocomputing. Addison-Wesley pub., Harlow. p. 433.
Ivakhnenko, A.G., 1971. IEEE Trans. Syst. man Cybernetics, 1, 364-78.
Ketabchi, S., Ghanadzadeh, H., Ghanadzadeh, A., Fallahi, S., Ganji, M., 2010. Estimation of VLE of binary systems (tert-butanol + 2-ethyl-1-hexanol) and (n-butanol + 2-ethyl-1-hexanol) using GMDH-type neural network. J. Chem. Thermodyn., 42(11), 1352–1355.
Minasny, B., McBratney, A.B., 2002. The neuro-m method for fitting neural network parametric pedotransfer functions. Soil Sci. Soc. Am. J., 66, 352–361.
Nariman-Zadeh, N., Jamali, A., 2007. Pareto Genetic Design of GMDH-type Neural Networks for Nonlinear Systems. In: Proc. of the International Workshop on InductiVe Modelling, Drchal J, Koutnik J, (eds.). Czech Technical University: Prague, Czech Republic. p. 96-103.
Nelson, D.W., Sommers, L.E., 1996. Total carbone, organic carbone, and organic matter, In: Sparks DL, (ed.), Methods of soil analysis, Part 3- chemical methods. Agronomy Monograph, vol. 9. ASA and SSSA, Madison, WI. USA. p. 961-1010.
Pachepsky, Y.A., Rawls, W.J., 1999. Accuracy and Reliability of Pedotransfer Functions as Affected by Grouping Soils. Soil Sci. Soc. Am. J., 63, 1748–1757.
Ripley, B.D., 1996. Pattern Recognition and Neural Networks. Cambridge: Cambridge University Press.
Sahrawat, K.L., 1983. An analysis of the contribution of organic matter and clay to cation exchange capacity of some Philippine soils. Commu. Soil Sci. Plant Anal., 14, 803–809.
Sarmadian, F., Taghizadeh Mehrjardi, R., 2008. Modeling of some soil properties using artificial neural network and multivariate regression in Gorgan province, north of Iran. Global J. Environ. Res., 2(1), 30-35.
Seybold, C.A., Grossman, R.B., Reinsch, T.G., 2005. Predicting cation exchange capacity for soil survey using linear models, Soil Sci. Soc. Am. J., 69, 856–863.
Sonmez, H., Gokceoglu, C., Nefeslioglu, H.A., Kayabasi, A., 2005. Estimation of rock modulus: For intact rocks with an artificial neural network and for rock masses with a new empirical equation, Int. J. Rock Mech. Mining Sci., 43(2), 224–235.
Sumner, M.E., Miller, W.P., 1996. Cations exchange capacity and Exchange Coefficients, In: Sparks DL, (ed.). Methods of soil analysis, Part 3- chemical methods. Agronomy Monograph, vol. 9. ASA and SSSA, Madison, WI., USA. p. 1201-1230.
A. Bazrafshan et al. / Agricultural Advances (2014) 3(4) 111-123
Thomas, G.W., 1996. Soil pH and soil acidity, In: Sparks DL, (ed.). Methods of soil analysis, Part 3- chemical methods. Agronomy Monograph, vol. 9. ASA and SSSA, Madison, WI. USA. p. 475-490.
Wagner, B., Tarnawski, V.R., Hennings, V., Muller, U., Wessolek, G., Plagge, R., 2001. Evaluation of pedo-transfer functions for unsaturated soil hydraulic conductivity using an independent data set. Geoderma, 102, 275–279.
Zacharias, S., 2007. Excluding organic matter content from pedotransfer predictors of soil water retention. Soil Sci. Soc. Am. J., 71, 43-50.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2014 A. bazrafshan, M. Shabanpour, M. Norouzi, S. Fallahi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
