{"title":"Developing Pedotransfer Functions for Estimating Some Soil Properties using Artificial Neural Network and Multivariate Regression Approaches","authors":"Fereydoon Sarmadian, Ali Keshavarzi","volume":48,"journal":"International Journal of Geological and Environmental Engineering","pagesStart":650,"pagesEnd":657,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/5214","abstract":"
Study of soil properties like field capacity (F.C.) and permanent wilting point (P.W.P.) play important roles in study of soil moisture retention curve. Although these parameters can be measured directly, their measurement is difficult and expensive. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data. In this investigation, 70 soil samples were collected from different horizons of 15 soil profiles located in the Ziaran region, Qazvin province, Iran. The data set was divided into two subsets for calibration (80%) and testing (20%) of the models and their normality were tested by Kolmogorov-Smirnov method. Both multivariate regression and artificial neural network (ANN) techniques were employed to develop the appropriate PTFs for predicting soil parameters using easily measurable characteristics of clay, silt, O.C, S.P, B.D and CaCO3. The performance of the multivariate regression and ANN models was evaluated using an independent test data set. In order to evaluate the models, root mean square error (RMSE) and R2 were used. The comparison of RSME for two mentioned models showed that the ANN model gives better estimates of F.C and P.W.P than the multivariate regression model. The value of RMSE and R2 derived by ANN model for F.C and P.W.P were (2.35, 0.77) and (2.83, 0.72), respectively. The corresponding values for multivariate regression model were (4.46, 0.68) and (5.21, 0.64), respectively. Results showed that ANN with five neurons in hidden layer had better performance in predicting soil properties than multivariate regression.<\/p>\r\n","references":"[1] M. Amini, K.C. Abbaspour, H. Khademi, N. Fathianpour, M. Afyuni\r\nand R. Schulin, \"Neural network models to predict cation exchange\r\ncapacity in arid regions of Iran\", Eur. J. Soil Sci., Vol. 53, pp 748-757,\r\n2005.\r\n[2] L. Baker and D. Ellison, \"Optimisation of pedotransfer functions using\r\nan artificial neural network ensemble method\", Geoderma, Vol.144, pp\r\n212-224, 2008.\r\n[3] M. Banimahd, S.S. Yasrobi and P.K. Woodward, \"Artificial neural\r\nnetwork for stress-strain behavior of sandy soils: Knowledge based\r\nverification\", Comput. Geotech., Vol. 32, pp 377-386, 2005.\r\n[4] G. R. Blake and K. H. Hartge, \"Particle density\", In: A. Klute, (ed)\r\nMethods of soil analysis, Part 1, Agron Monogr 9, ASA, Madison, WI,\r\npp 377-382, 1986.\r\n[5] J. Bouma, \"Using soil survey data for quantitative land evaluation\",\r\nAdvances in Soil Science., Vol. 9, pp 177-213, 1989.\r\n[6] D. K. Cassel and D. R. Nielsen, \"Field capacity and available water\r\ncapacity\". In: A. Klute, (Ed) Methods of Soil Analysis, Part 1, second\r\nedn. Agron Monogr 9, ASA and SSSA, Madison, WI, pp 901-926,\r\n1986.\r\n[7] L. Cavazza, A. Patruno and E. Cirillo, \"Field capacity in soils with a\r\nyearly oscillating water table\", Biosystems Engineering., Vol. 98, pp\r\n364-370, 2007.\r\n[8] J. A. Field, J. C. Parker and N. L. Powell, \"Comparison of field- and\r\nlaboratory measured and predicted hydraulic properties of a soil with\r\nmacropores\", Soil Sci., Vol. pp 138, 385-396, 1984.\r\n[9] J. Givi, S. O. Prasherb and R. M. Patel, \"Evaluation of pedotransfer\r\nfunctions in predicting the soil water contents at field capacity and\r\nwilting point\", Agricultural Water Management., Vol. 70, pp 83-96,\r\n2004.\r\n[10] S. A. Heusher, C. C. Brandt and P. M. Jardin, \"Using soil physical and\r\nchemical properties to estimate bulk density\", Soil Sci Soc Am J., Vol.\r\n69, pp 51-56, 2005.\r\n[11] D. Hillel, \" Environmental Soil Physics\" , Academic Press, New York,\r\nUSA, 1998.\r\n[12] A. Jain and A. Kumar, \"An evaluation of artificial neural network\r\ntechnique for the determination of infiltration model parameters\", Appl.\r\nSoft Comput., Vol. 6, pp 272-282, 2006.\r\n[13] F. Karaca and B. Ozkaya, \"NN-LEAP: A neural network-based model\r\nfor controlling leachate flow-rate in a municipal solid waste landfill\r\nsite\", Environ. Modell. Software., Vol. 21, pp 1190-1197, 2006.\r\n[14] R. Kaur, S. Kumar and H.P. Gurung, \"A pedotransfer function soil data\r\nand its comparison with existing PTFs\", Aust. J. Soil Res., Vol. 40, pp\r\n847- 857, 2002.\r\n[15] A. Keller, B. Von Steiger, S.T. Vander Zee and R. Schulin, \"A\r\nstochastic empirical model for regional heavy metal balances in\r\nagroecosystems\". Journal of Environmental Quality., Vol. 30, pp 1976-\r\n1989, 2001.\r\n[16] E.J.W. Koekkoek and H. Booltink, \"Neural network models to predict\r\nsoil water retention\", Eur. J. Soil Sci., Vol. 50, pp 489-495, 1999.\r\n[17] H.R. Lake, A. Akbarzadeh and R. Taghizadeh Mehrjardi, \"Development\r\nof pedotransfer functions (PTFs) to predict soil physico-chemical and\r\nhydrological characteristics in southern coastal zones of the Caspian\r\nSea\", Journal of Ecology and the Natural Environment., Vol. 1, No.7,\r\npp 160-172, 2009.\r\n[18] L.A. Manrique, C.A. Jones and P.T. Dyke, \"Predicting cation exchange\r\ncapacity from soil physical and chemical properties\", Soil Science\r\nSociety of America Journal., Vol. 50, pp 787-794, 1991.\r\n[19] C. Manyame, C.L. Morgan, J.L. Heilman, D. Fatondji, B. Gerard and\r\nW.A. Payne, \"Modeling hydraulic properties of sandy soils of Niger\r\nusing pedotransfer functions\", Geoderma., Vol. 141, pp 407-415, 2007.\r\n[20] H. Merdun, O. C\u2500\u2592nar, R. Meral and M. Apan, \"Comparison of artificial\r\nneural network and regression pedotransfer functions for prediction of\r\nsoil water retention and saturated hydraulic conductivity\", Soil Till.Res.,\r\nVol. 90, pp 108-116, 2006.\r\n[21] A. Mermoud and D. Xu, \"Comparative analysis of three methods to\r\ngenerate soil hydraulic functions\", Soil Till. Res., Vol. 87, pp 89-100,\r\n2006.\r\n[22] B. Minasny and A.B. McBratney, \"The neuro-m methods for fitting\r\nneural network parametric pedotransfer functions\", Soil Sci. Soc. Am.\r\nJ., Vol. 66, pp 352-361, 2002.\r\n[23] B. Minasny, A.B. McBratney and K.L. Bristow, \"Comparison of\r\ndifferent approaches to the development of pedotransfer functions for\r\nwater retention curves\", Geoderma., Vol. 93, pp 225- 253, 1999.\r\n[24] M. Najafi and J. Givi, \"Evaluation of prediction of bulk density by\r\nartificial neural network and PTFs\", 10th Iranian Soil Science Congress,\r\nKaraj., pp 680-681, 2006.\r\n[25] D.W. Nelson and L.E. Sommers, \"Total carbon, organic carbon, and\r\norganic matter\". In: A.L. Page, R.H. Miller and D.R. Keeney (Eds.),\r\nMethods of Soil Analysis. Part II, 2nd ed. American Society of\r\nAgronomy, Madison, WI, USA, pp: 539-580, 1982.\r\n[26] M. H. Omid, M. Omid and M. E. Varaki, \"Modeling hydraulic jumps\r\nwith artificial neural networks\", Proceedings of ICE-Water\r\nManagement., Vol. 158, No. 2, pp 65-70, 2005.\r\n[27] M. Omid, A. Baharlooei and H. Ahmadi, \"Modeling drying kinetics of\r\npistachio nuts with multilayer feed-forward neural network\", Drying\r\nTech., Vol. 27, pp 1069-1077. 2009.\r\n[28] Y.A. Pachepsky, D. Timlin and G. Varallyay, \"Artificial neural\r\nnetworks to estimate soil water retention from easily measurable data\",\r\nSoil Sci. Soc. Am. J., Vol. 60, pp 727-733, 1996.\r\n[29] Y. A. Pachepsky and W. J. Rawls, \"Soil structure and pedotransfer\r\nfunctions\", Eur J Soil Sci., Vol. 54, pp 443- 451, 2003.\r\n[30] B. J. Park, W. Pedrycz and S. K. Oh, \"Polynomial-based radial basis\r\nfunction neural networks (P-RBFNNs) and their application to pattern\r\nclassification\", Applied Intelligence., Vol. 32, pp 27-46, 2010.\r\n[31] F. Sarmadian, R. Taghizadeh Mehrjardi and A. Akbarzadeh, \"Modeling\r\nof some soil properties using artificial neural network and multivariate\r\nregression in Gorgan province, north of Iran\", Australian J. of Basic and\r\nApplied Sci., Vol. 3, No. 1, pp 323-329, 2009.\r\n[32] M.G. Schaap and F.J. Leij, \"Using neural networks to predict soil water\r\nretention and soil hydraulic conductivity\", Soil Till. Res., Vol. 47, pp\r\n37-42, 1998.\r\n[33] M.G. Schaap, F.J. Leij and M.Th. Van Genuchten, \"Neural network\r\nanalysis for hierarchical prediction of soil hydraulic properties\", Soil\r\nSci. Soc. Am. J., Vol. 62, pp 847-855, 1998.\r\n[34] W. M. Shuh, R. D. Cline and M. D. Sweeney, \"Comparison of a\r\nlaboratory procedure and a textural model for predicting in situ water\r\nretention\", Soil Sci Soc Am J., Vol. 52, pp 1218-1227, 1988.\r\n[35] D.L. Sparks, A.L. Page, P.A. Helmke, R.H. Leoppert, P.N. Soltanpour,\r\nM.A. Tabatabai, G.T. Johnston and M.E. Summer, \"Methods of soil\r\nanalysis\", Soil Sci. Soc. of Am. Madison, Wisconsin, 1996.\r\n[36] Ir. C. Sys, E.Van Ranst and Ir. J. Debaveye, \"Land evaluation\". Part I.\r\nPrincipal Land evaluation and Crop production calculation general\r\nadministration for development, Cooperation agric Pub., Vol. 1, No. 7,\r\npp 247, 1991.\r\n[37] S. Tamari, J.H.M. Wosten and J.C. Ruiz-Suarez, \"Testing an artificial\r\nneural network for predicting soil hydraulic conductivity\", Soil Sci. Soc.\r\nAm. J., Vol. 60, pp 1732-1741, 1996.\r\n[38] USDA, \"Soil Survey Staff, Keys to Soil Taxonomy\", 11th edition, 2010.\r\n[39] B.D. Vos, M.V. Meirvenne, P. Quataert, J. Deckers and B. Muys,\r\n\"Predictive quality of pedotransfer functions for estimating bulk density\r\nof forest soils\", Soil Sci. Soc. Am. J., Vol. 69, pp 500-510, 2005.\r\n[40] B. Wagner, V.R. Tarnawski, V. Hennings, U. Muller, G. Wessolek and\r\nR. Plagge, \"Evaluation of pedo-transfer functions for unsaturated soil\r\nhydraulic conductivity using an independent data set\", Geoderma.,\r\nVol.102, pp 275-279, 2001.\r\n[41] J.H.M. W\u00f6sten, A. Lilly, A. Nemes and C. Le Bas, \"Development and\r\nuse of a database of hydraulic properties of European soils\", Geoderma.,\r\nVol. 90, pp 169-185, 1999.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 48, 2010"}