Estimation of effective stress parameter of unsaturated soils by using artificial neural networks

WOS: 000257088900004Great efforts are required for determination of the effective stress parameter chi, applying the unsaturated testing procedure, since unsaturated soils that have the three-phase system exhibit complex mechanical behavior. Therefore, it seems more reasonable to use the empirical methods for estimation of chi. The objective of this study is to investigate the practicability of using artificial neural networks (ANNs) to model the complex relationship between basic soil parameters, matric suction and the parameter chi. Five ANN models with different input parameters were developed. Feed-forward back propagation was applied in the analyses as a learning algorithm. The data collected from the available literature were used for training and testing the ANN models. Furthermore, unsaturated triaxial tests were carried out under drained condition on compacted specimens. ANN models were validated by a part of data sets collected from the literature and data obtained from the current study, which were not included in the training phase. The analyses showed that the results obtained from ANN models are in satisfactory agreement with the experimental results and ANNs can be used as reliable tool for prediction of chi. Copyright (C) 2007 John Wiley & Sons, Ltd