Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity

Abstract Modeling water flow and solute transport in vadose zone requires knowledge of soil hydraulic properties, which are water retention and hydraulic conductivity curves. As an alternative to direct measurement, indirect determination of these functions from basic soil properties using pedotransfer functions (PTFs) has attracted the attention of researchers in a variety of fields such as soil scientists, hydrologists, and agricultural and environmental engineers. In this study, PTFs for point and parametric (van Genuchten's parameters) estimation of soil hydraulic parameters from basic soil properties such as particle-size distribution, bulk density, and three different pore sizes were developed and validated using artificial neural network (ANN) and multiple-linear regression methods and the predictive capabilities of the two methods was compared using some evaluation criteria. Total of 195 soil samples was divided into two groups as 130 for the development and 65 for the validation of PTFs. Although the differences between the two methods were not statistically significant ( p  > 0.05), regression predicted point and parametric variables of soil hydraulic parameters better than ANN. Both methods had lower accuracy in parametric predictions than in point predictions. Accuracy of the predictions was evaluated by the coefficient of determination ( R 2 ) and the root mean square error (RMSE) between the measured and predicted parameter values. The R 2 and RMSE varied from 0.637 to 0.979 and from 0.013 to 0.938 for regression, and varied from 0.444 to 0.952 and from 0.020 to 3.511 for ANN, respectively. Even though regression performs insignificantly better than ANN in this case, ANN produces promising results and its advantages can be utilized by developing or using new algorithms in future studies.

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

[2]  J. Tomasella,et al.  Pedotransfer functions for the estimation of soil water retention in Brazilian soils. , 2000 .

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

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

[5]  Walter J. Rawls,et al.  Accuracy and reliability of pedotransfer functions as affected by grouping soils , 1999 .

[6]  Kevin J. McInnes,et al.  Effects of Soil Morphology on Hydraulic Properties II. Hydraulic Pedotransfer Functions , 1999 .

[7]  Vitaly Schetinin.  A Learning Algorithm for Evolving Cascade Neural Networks , 2004, Neural Processing Letters.

[8]  Rattan Lal,et al.  Pedotransfer functions for variable alluvial soils in southern Ohio , 1996 .

[9]  R. H. Brooks,et al.  Hydraulic properties of porous media , 1963 .

[10]  D. Hillel.  Environmental soil physics , 1998 .

[11]  Y. Pachepsky,et al.  Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data , 1996 .

[12]  Niels H. Batjes,et al.  Development of a world data set of soil water retention properties using pedotransfer rules , 1996 .

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

[14]  D. K. Cassel,et al.  EVALUATION OF SPATIAL DISTRIBUTION OF HYDRAULIC CONDUCTIVITY USING EFFECTIVE POROSITY DATA , 1989 .

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

[16]  Kishan G. Mehrotra,et al.  Elements of artificial neural networks , 1996 .

[17]  W. M. Schuh,et al.  Comparison of a Laboratory Procedure and a Textural Model for Predicting In Situ Soil Water Retention , 1988 .

[18]  Thomas Harter,et al.  Neural Networks Prediction of Soil Hydraulic Functions for Alluvial Soils Using Multistep Outflow Data , 2004 .

[19]  J.H.M. Wösten,et al.  Testing an Artificial Neural Network for Predicting Soil Hydraulic Conductivity , 1996 .

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

[21]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[22]  Peter Finke,et al.  Comparison of class and continuous pedotransfer functions to generate soil hydraulic characteristics , 1995 .

[23]  H.W.G. Booltink,et al.  Neural network models to predict soil water retention , 1999 .

[24]  Yakov A. Pachepsky,et al.  Soil structure and pedotransfer functions , 2003 .

[25]  M. Schaap,et al.  Using neural networks to predict soil water retention and soil hydraulic conductivity , 1998 .

[26]  Feike J. Leij,et al.  The RETC code for quantifying the hydraulic functions of unsaturated soils , 1992 .

[27]  Van Genuchten,et al.  A closed-form equation for predicting the hydraulic conductivity of unsaturated soils , 1980 .

[28]  T. Mayr,et al.  Pedotransfer functions to estimate soil water retention parameters for a modified Brooks-Corey type model , 1999 .

[29]  N. L. Powell,et al.  COMPARISON OF FIELD- AND LABORATORY‐MEASURED AND PREDICTED HYDRAULIC PROPERTIES OF A SOIL WITH MACROPORES , 1984 .

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