Enhanced pedotransfer functions with support vector machines to predict water retention of calcareous soil

Knowledge of soil hydraulic properties is of major importance for land management in dry-land areas. The most important properties are the soil–water retention curve (SWRC) and hydraulic conductivity characteristics. Direct measurement of the SWRC is time and cost prohibitive. Pedotransfer functions (PTFs) use data mining tools to predict SWRC. Modern data mining techniques enable accurate predictions and good generalization of SWRC data. In this research we explore whether the use of support vector machines (SVMs) could improve the accuracy of prediction of SWRC. The novelty of our work is in the application of SVM data mining techniques, which are seldom used in soil research, to a limited dataset from Syria. The soil studied is calcareous and the climate is arid, for which no PTFs have been developed. Seventy-two undisturbed soil samples were taken from four different agro-climatic zones of Syria. The soil water contents at eight matric potentials were determined and selected as output variables. The data were split into two subsets: a training set with 54 samples for model calibration or PTF development and a test set with 18 samples for PTF validation. An overview of the theoretical foundation of this new approach and the use of specific kernel functions is given. Then, the model parameters were optimized with ninefold cross-validation and a grid search method. The predictions of the SVM-based PTFs were analysed with the coefficient of determination (R2) and root mean square error (RMSE). Our results showed that the accuracy of SVM was better in terms of RMSE and R2 than multiple linear regression (MLR) and the artificial neural network (ANN). The results support previous findings that the SVM approach performs better than MLR and the ANN. Furthermore, improvements in predictions of SWRC with the three data mining techniques were obtained by replacing the more conventional organic matter in the PTF with the plastic limit (PL). Therefore, SVM and PL markedly improved the accuracy of prediction of SWRC for calcareous soil. Highlights Pedotransfer functions (PTFs) to predict the soil–water retention curve of calcareous soil. Improved prediction of water retention with support vector machines (SVMs) The plastic limit (PL) appeared to be a significant predictor variable. The results suggest the use of SVMs and PL to improve and develop PTFs further.

[1]  Y. Pachepsky,et al.  Soil Consistence and Structure as Predictors of Water Retention , 2002 .

[2]  R. T. Walczak,et al.  Using Support Vector Machines to Develop Pedotransfer Functions for Water Retention of Soils in Poland , 2008 .

[3]  Yakov A. Pachepsky,et al.  The Current Status of Pedotransfer Functions: Their Accuracy, Reliability, and Utility in Field‐ and Regional‐Scale Modeling , 2013 .

[4]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[5]  A. Walkley,et al.  AN EXAMINATION OF THE DEGTJAREFF METHOD FOR DETERMINING SOIL ORGANIC MATTER, AND A PROPOSED MODIFICATION OF THE CHROMIC ACID TITRATION METHOD , 1934 .

[6]  Steffen Zacharias,et al.  Excluding Organic Matter Content from Pedotransfer Predictors of Soil Water Retention , 2007 .

[7]  Marcel G. Schaap,et al.  Database-related accuracy and uncertainty of pedotransfer functions , 1998 .

[8]  Jan De Pue,et al.  Impact of regression methods on improved effects of soil structure on soil water retention estimates , 2015 .

[9]  Walter J. Rawls,et al.  Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics , 2001 .

[10]  Anthony R. Dexter,et al.  Plastic limits of agricultural soils as functions of soil texture and organic matter content , 2012 .

[11]  Xiugang Li,et al.  Predicting motor vehicle crashes using Support Vector Machine models. , 2008, Accident; analysis and prevention.

[12]  W. Cornelis,et al.  Exploration of the Interaction between Hydraulic and Physicochemical Properties of Syrian Soils , 2013 .

[13]  L. Buydens,et al.  Determination of optimal support vector regression parameters by genetic algorithms and simplex optimization , 2005 .

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

[15]  R. T. Odell,et al.  Relationships of Atterberg limits to some other properties of Illinois soils. , 1960 .

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

[17]  M. Schaap,et al.  ROSETTA: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions , 2001 .

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

[19]  Jianting Zhu,et al.  Including Topography and Vegetation Attributes for Developing Pedotransfer Functions , 2006 .

[20]  J. Mateu,et al.  Spatial dynamics of soil salinity under arid and semi-arid conditions: geological and environmental implications , 2004 .

[21]  Marc Van Meirvenne,et al.  Evaluation of Pedotransfer Functions for Predicting the Soil Moisture Retention Curve , 2001 .

[22]  Lipo Wang.  Support vector machines : theory and applications , 2005 .

[23]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[24]  Jack F. Paris,et al.  A Physicoempirical Model to Predict the Soil Moisture Characteristic from Particle-Size Distribution and Bulk Density Data 1 , 1981 .

[25]  Marc Van Meirvenne,et al.  Comparison of Unimodal Analytical Expressions for the Soil-Water Retention Curve , 2005 .

[26]  Harry Vereecken,et al.  ESTIMATING THE SOIL MOISTURE RETENTION CHARACTERISTIC FROM TEXTURE, BULK DENSITY, AND CARBON CONTENT , 1989 .

[27]  W. E. Larson,et al.  Estimating soil water retention characteristics from particle size distribution, organic matter percent, and bulk density , 1979 .

[28]  M. Tapkenhinrichs,et al.  Evaluation of Pedo-Transfer Functions , 1993 .

[29]  Anthony R. Dexter,et al.  Methods for predicting the optimum and the range of soil water contents for tillage based on the water retention curve , 2001 .

[30]  J. Deckers,et al.  World Reference Base for Soil Resources , 1998 .

[31]  Wim Cornelis,et al.  Revisiting the pseudo continuous pedotransfer function concept: impact of data quality and data mining method , 2014 .