HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Figures Only Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Google Scholar Articles by Twarakavi, N. K. C. Articles by Schaap, M. G. PubMed Articles by Twarakavi, N. K. C. Articles by Schaap, M. G. Agricola Articles by Twarakavi, N. K. C. Articles by Schaap, M. G. Related Collections Pedotransfer Functions Water Flow Models Variably Saturated Fluid Flow

SOIL PHYSICS

Development of Pedotransfer Functions for Estimation of Soil Hydraulic Parameters using Support Vector Machines

Navin K. C. Twarakavi^a,*, Jirka imnek^b and M. G. Schaap^c

^a Auburn Univ., 201 Funchess Hall, Auburn, AL 36849
^b Dep. of Environmental Sciences, Univ. of California, Riverside, CA 92521
^c Dep. of Soil, Water, and Environmental Science, Univ. of Arizona, Shantz Bldg., Tucson, AZ 85721

^* Corresponding author (twarakavi{at}auburn.edu).

Modeling flow in variably saturated porous media requires reliable estimates of the hydraulic parameters describing the soil water retention and hydraulic conductivity. These soil hydraulic properties can be measured using a wide variety of laboratory and field methods. Frequently, this proves to be an arduous task because of the high spatial and temporal variability of soil properties. In the last decade, researchers have shown a keen interest in developing a class of indirect approaches, called pedotransfer functions (PTFs), to overcome this problem. Pedotransfer functions predict soil hydraulic parameters using easily obtainable soil properties such as textural information, bulk density and/or few retention points. In this paper, we use a new methodology called Support Vector Machines (SVMs) to derive a new set of PTFs. Support vector machines represent a pattern recognition approach where the overall prediction error and complexity of the SVM structure are minimized simultaneously. We used the same database that was utilized to develop ROSETTA to generate the SVM-based PTFs. The performance of the SVM-based PTFs was analyzed using the coefficient of determination, root mean square error (RMSE) and mean error (ME). All soil hydraulic parameters estimated using the SVM-based PTFs showed improved confidence in the estimates when compared with the ROSETTA PTF program. Estimates of water contents and saturated hydraulic conductivities using the hydraulic parameters predicted by the SVM-based PTFs mostly improved compared with those obtained using the artificial neural network (ANN)-based ROSETTA. The RMSE for water contents decreased from 0.062 to 0.034 as more predictors were used, while the RMSE for the saturated hydraulic conductivity decreased from 0.716 to 0.552 (dimensionless log₁₀ units). Similarly, the bias in the water contents estimated using the SVM-based PTF was reduced significantly compared with ROSETTA.

Abbreviations: ANN, Artificial neural networks • HYPRES, Database of hydraulic properties of European soils • ME, Mean Error • PTFs, Pedotransfer functions • RMSE, Root mean squared error • SLT, Statistical learning theory • SVMs, Support vector machines • UNSODA, Unsaturated soil hydraulic properties database • WISE, World inventory of soil emission potentials