Table of Contents Author Guidelines Submit a Manuscript
Applied and Environmental Soil Science
Volume 2015, Article ID 535216, 16 pages
Research Article

Artificial Neural Networks for Estimating Soil Water Retention Curve Using Fitted and Measured Data

Institute of Hydraulic Researches, Federal University of Rio Grande do Sul (UFRGS), Bento Gonçalves Avenue 9500, P.O. Box 15029, 91501-970 Porto Alegre, RS, Brazil

Received 7 August 2014; Accepted 24 February 2015

Academic Editor: Keith Smettem

Copyright © 2015 Tirzah Moreira de Melo and Olavo Correa Pedrollo. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Artificial neural networks for estimating the soil water retention curve have been developed considering measured data and require a large quantity of soil samples because only retention curve data obtained for the same set of matric potentials can be used. In order to preclude this drawback, we present two ANN models which tested the performance of ANNs trained with fitted water contents data. These models were compared to a recent new ANN approach for predicting water retention curve, the pseudocontinuous pedotransfer functions (PTFs), which is also an attempt to deal with limited data. Additionally, a sensitivity analysis was carried out to verify the influence of each input parameter on each output. Results showed that fitted ANNs provided similar statistical indexes in predicting water contents to those obtained by the pseudocontinuous method. Sensitivity analysis revealed that bulk density and porosity are the most important parameters for predicting water contents in wet regime, whereas sand and clay contents are more significant in drier conditions. The sensitivity analysis for the pseudocontinuous method demonstrated that the natural logarithm of the matric potential became the most important parameter, and the influences of all other inputs were reduced to be not relevant, except the bulk density.