Using the nonparametric k-nearest neighbor approach for predicting cation exchange capacity

Abstract The objectives of this study were to apply a k -NN approach to predict CEC in Iranian soils and compare this approach with the popular artificial neural network model (ANN). In this study, a data set of 3420 soil samples from different parts of Iran was used. Two different sets of cheaper-to-measure soil attributes were selected as potential predictors. The first set consisted of clay, silt, sand and organic carbon (OC) contents. The second data set was constructed using OC and clay contents. Two ‘design-parameter’ parameters should be optimized before application of the k- NN approach. Results showed that the algorithm efficiency is not dependent on these parameters. A wide range of suboptimal values around the optimal values may cause a slight error in terms of estimation accuracy. However, the optimal settings of the design-parameters depend on the size of the development/reference data set. In both k -NN and ANN models, the higher number of input variables can relatively improve the estimation of CEC. But this improvement was not statistically significant at the 0.05 level. Furthermore, the results showed that increasing the size of the reference data set to a certain amount (N = 1200) reduced the estimation error significantly in terms of root-mean-squared residuals (RMSE). However, no significant difference in the accuracy of k -NN and ANN methods was detected in the reference data set sizes for N > 1200. Results showed no significant difference between this approach and ANN models, suggesting the competitive advantage of the k -NN technique over other techniques to develop pedotransfer functions (PTFs), for example, the redevelopment of PTFs is not necessarily required as new data become available.

[1]  Budiman Minasny,et al.  From pedotransfer functions to soil inference systems , 2002 .

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

[3]  John Triantafilis,et al.  Elucidation of physiographic and hydrogeological features of the lower Namoi valley using fuzzy k-means classification of EM34 data , 2003, Environ. Model. Softw..

[4]  Kenneth Strzepek,et al.  A technique for generating regional climate scenarios using a nearest‐neighbor algorithm , 2003 .

[5]  Gianni Bellocchi,et al.  Comparison of sensitivity analysis techniques: A case study with the rice model WARM , 2010 .

[6]  M. Bauer,et al.  Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method , 2001 .

[7]  James W. Jones,et al.  DYNAMIC NEAREST-NEIGHBOR METHOD FOR ESTIMATING SOIL WATER PARAMETERS , 2004 .

[8]  A. Warrick,et al.  Unsaturated flow through a spherical inclusion , 2004 .

[9]  Naser Davatgar,et al.  Prediction of CEC Using Fractal Parameters by Artificial Neural Networks , 2014 .

[10]  Cathy A. Seybold,et al.  Predicting Cation Exchange Capacity for Soil Survey Using Linear Models , 2005 .

[11]  Yakov A. Pachepsky,et al.  Software to estimate -33 and -1500kPa soil water retention using the non-parametric k-Nearest Neighbor technique , 2008, Environ. Model. Softw..

[12]  Wim Cornelis,et al.  Prediction of Water Retention of Soils from the Humid Tropics by the Nonparametric k‐Nearest Neighbor Approach , 2013 .

[13]  Paolo Ferrazzoli,et al.  Retrieving soil moisture and agricultural variables by microwave radiometry using neural networks , 2003 .

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

[15]  Tomislav Hengl,et al.  Methods to interpolate soil categorical variables from profile observations: Lessons from Iran , 2007 .

[16]  Upmanu Lall,et al.  A Nearest Neighbor Bootstrap For Resampling Hydrologic Time Series , 1996 .

[17]  Nader Fathianpour,et al.  Neural network models to predict cation exchange capacity in arid regions of Iran , 2005 .

[18]  N. Peinemann,et al.  Effect of clay minerals and organic matter on the cation exchange capacity of silt fractions. , 2000 .

[19]  H. Keulen,et al.  Soil pedotransfer functions for four Mexican soils , 1995 .

[20]  Walter J. Rawls,et al.  Use of the Nonparametric Nearest Neighbor Approach to Estimate Soil Hydraulic Properties , 2006 .

[21]  Balaji Rajagopalan,et al.  A resampling procedure for generating conditioned daily weather sequences , 2004 .

[22]  Kmg Taylor,et al.  Particle size analysis , 2013 .

[23]  E. Van Ranst,et al.  Evaluation of pedotransfer functions for predicting water retention of soils in Lower Congo (D.R. Congo) , 2012 .

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

[25]  André Revil,et al.  Principles of electrography applied to self‐potential electrokinetic sources and hydrogeological applications , 2003 .

[26]  Gerrit Hoogenboom,et al.  Using pattern recognition for estimating cultivar coefficients of a , 2009 .

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

[28]  M. Greve,et al.  Cation-Exchange Capacity Pedotransfer Functions for Danish Soils , 2000 .

[29]  Charles E. Kellogg,et al.  Soil Survey Manual , 2017 .