Comparative analysis of support vector machine and artificial neural network models for soil cation exchange capacity prediction

Abstract The aim of this study was to compare the performance of support vector machine and artificial neural network techniques to predict the soil cation exchange capacity of an agricultural research station in terms of soil characteristics (clay, silt, sand, gypsum, organic matter). The data consist of 380 soil samples collected from different horizons of 80 soil profiles located in the Khoja (Khajeh) region of Azerbaijani provinces, Iran. The support vector machine and artificial neural network models predict the cation exchange capacity from the above soil characteristics of the samples. The models’ results are compared using three criteria, i.e., root-mean-square errors, Nash–Sutcliffe and the correlation coefficient. A comparison of support vector machine results with artificial neural network method indicates that artificial neural network is better than the support vector machine method in prediction of the cation exchange capacity.

[1]  Hadi Ghorbani,et al.  The effects of agricultural practice and land-use on the distribution and origin of some potentially toxic metals in the soils of Golestan province, Iran , 2012, Environmental Earth Sciences.

[2]  Mehmet Lütfi Yola,et al.  A novel efficient photocatalyst based on TiO2 nanoparticles involved boron enrichment waste for photocatalytic degradation of atrazine , 2014 .

[3]  Liang-Mei Huang,et al.  Multivariate statistical approach to identify heavy metal sources in agricultural soil around an abandoned Pb–Zn mine in Guangxi Zhuang Autonomous Region, China , 2013, Environmental Earth Sciences.

[4]  Oguz Kaynar,et al.  Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils , 2010, Expert Syst. Appl..

[5]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter , 1983, SSSA Book Series.

[6]  Rajib Maity,et al.  Multistep-Ahead River Flow Prediction Using LS-SVR at Daily Scale , 2012 .

[7]  A. Lax,et al.  DETERMINATION OF EXCHANGEABLE CATIONS IN CALCAREOUS SOILS , 1972 .

[8]  Budiman Minasny,et al.  The neuro-m method for fitting neural network parametric pedotransfer functions , 2002 .

[9]  Ashutosh Das,et al.  Linearized and non-linearized isotherm models comparative study on adsorption of aqueous phenol solution in soil , 2009 .

[10]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[11]  Guofeng Wu,et al.  Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy , 2012, Plant and Soil.

[12]  A. H. Sayegh,et al.  FACTORS AFFECTING GYPSUM AND CATION EXCHANGE CAPACITY DETERMINATIONS IN GYPSIFEROUS SOILS1 , 1978 .

[13]  Wei Wu,et al.  Soil Water Content Forecasting by Support Vector Machine in Purple Hilly Region , 2007, CCTA.

[14]  A. Agarwal,et al.  Application and analysis of support vector machine based simulation for runoff and sediment yield , 2009 .

[15]  Özgür Kişi,et al.  Daily River Flow Forecasting Using Artificial Neural Networks and Auto-Regressive Models , 2005 .

[16]  Mwinyikione Mwinyihija,et al.  Determination of adsorption efficiency based on cation exchange capacity related to red earth, bone meal and pulverised fly ash as ameliorants to lead contaminated soils , 2006 .

[17]  A. Suhogusoff,et al.  Evaluation of the potential impact of fluorine-rich fertilizers on the Guarani Aquifer System, Rio Grande do Sul, Southern Brazil , 2013, Environmental Earth Sciences.

[18]  L. Baker,et al.  Optimisation of pedotransfer functions using an artificial neural network ensemble method , 2008 .

[19]  Haifeng Wang,et al.  Comparison of SVM and LS-SVM for Regression , 2005, 2005 International Conference on Neural Networks and Brain.

[20]  Claudionor Ribeiro da Silva,et al.  Soil prediction using artificial neural networks and topographic attributes , 2013 .

[21]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[22]  M. Bilgili,et al.  Application of artificial neural networks for the wind speed prediction of target station using reference stations data , 2007 .

[23]  M. Kovacevic,et al.  Soil type classification and estimation of soil properties using support vector machines , 2010 .

[24]  D. W. Nelson,et al.  Total Carbon, Organic Carbon, and Organic Matter 1 , 1982 .

[25]  Johan Bouma,et al.  Using Soil Survey Data for Quantitative Land Evaluation , 1989 .

[26]  R. Schulin,et al.  A stochastic empirical model for regional heavy-metal balances in agroecosystems. , 2001, Journal of environmental quality.

[27]  R. V. Rossel,et al.  Using data mining to model and interpret soil diffuse reflectance spectra. , 2010 .

[28]  M. Ghorbani,et al.  Relative importance of parameters affecting wind speed prediction using artificial neural networks , 2013, Theoretical and Applied Climatology.

[29]  M. Fernandez-Marcos,et al.  Fluoride sorption and desorption on soils located in the surroundings of an aluminium smelter in Galicia (NW Spain) , 2014, Environmental Earth Sciences.

[30]  Budiman Minasny,et al.  The neuro-m method for fitting neural network parametric pedotransfer functions , 2002 .

[31]  Mohsen Jalali,et al.  Effects of cations and anions on iron and manganese sorption and desorption capacity in calcareous soils from Iran , 2013, Environmental Earth Sciences.

[32]  Wenjian Wang,et al.  Online prediction model based on support vector machine , 2008, Neurocomputing.

[33]  Louis M. McDonald,et al.  Chemically stabilized soil organic carbon fractions in a reclaimed minesoil chronosequence: implications for soil carbon sequestration , 2013, Environmental Earth Sciences.

[34]  Eungyu Park,et al.  Multivariate statistical analysis and 3D-coupled Markov chain modeling approach for the prediction of subsurface heterogeneity of contaminated soil management in abandoned Guryong Mine Tailings, Korea , 2012, Environmental Earth Sciences.

[35]  Remigio Paradelo,et al.  Effect of the addition of granitic powder to an acidic soil from Galicia (NW Spain) in comparison with lime , 2012, Environmental Earth Sciences.

[36]  Lin Tang,et al.  Artificial Neural Network Approach for Predicting Cation Exchange Capacity in Soil Based on Physico-Chemical Properties , 2009 .

[37]  Jichun Wu,et al.  Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China , 2014 .

[38]  A. Klute,et al.  Methods of soil analysis , 2015, American Potato Journal.

[39]  M. McKee,et al.  SOIL MOISTURE PREDICTION USING SUPPORT VECTOR MACHINES 1 , 2006 .

[40]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[41]  Marcel G. Schaap,et al.  Development of Pedotransfer Functions for Estimation of Soil Hydraulic Parameters using Support Vector Machines , 2009 .

[42]  Budiman Minasny,et al.  Comparison of different approaches to the development of pedotransfer functions for water-retention curves , 1999 .

[43]  Krzysztof Lamorski,et al.  Soil Water Dynamic Modeling Using the Physical and Support Vector Machine Methods , 2013 .

[44]  Luis A. Manrique,et al.  Predicting cation-exchange capacity from soil physical and chemical properties , 1991 .

[45]  K. Lee,et al.  A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer , 2011 .

[46]  Kanwar L. Sahrawat,et al.  Pasture degradation effects on soil quality indicators at different hillslope positions in a semiarid region of western Iran , 2017, Environmental Earth Sciences.

[47]  S. Rezapour,et al.  Response of some soil attributes to different land use types in calcareous soils with Mediterranean type climate in north-west of Iran , 2014, Environmental Earth Sciences.

[48]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[49]  Peng Wang,et al.  Link prediction in social networks: the state-of-the-art , 2014, Science China Information Sciences.

[50]  R. Hanley,et al.  Artificial neural network application for multi-ecosystem carbon flux simulation , 2005 .

[51]  H. Gheyi,et al.  A comparison of three methods of determining the cation exchange capacity of calcareous soils , 1975 .

[52]  Ashraf Malekian,et al.  Qualitative land suitability evaluation of the Khajeh research station for Wheat, Barley, Alfalfa, Maize and Safflower , 2011 .

[53]  S. Gruszczyński.  Assessment of suitability of various models for estimating cation exchange capacity (CEC). , 2009 .

[54]  L. Evans,et al.  Chemistry of metal retention by soils , 1989 .

[55]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[56]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[57]  M. Schaap,et al.  Neural network analysis for hierarchical prediction of soil hydraulic properties , 1998 .

[58]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[59]  K. Semhi,et al.  Impact of sewage and mining activities on distribution of heavy metals in the water-soil-vegetation system , 2014, International Journal of Environmental Science and Technology.

[60]  Budiman Minasny,et al.  The Method for Fitting Neural Network Parametric Pedotransfer Functions , 2002 .

[61]  Francis Eng Hock Tay,et al.  Support vector machine with adaptive parameters in financial time series forecasting , 2003, IEEE Trans. Neural Networks.