Data mining techniques for slope stability estimation with probabilistic neural networks

Abstract

Probabilistic neural networks are applied to facilitate slope stability estimation by making use of data mining techniques and an intelligent system. Data mining can draw attention to meaningful structures in the archives of such slope stability data. The soil mechanical characteristics and the slope shapes with significant influences on slope stability are used to train and test the neural networks. Validation is performed to show the efficiency of probabilistic neural networks for estimation of slope stability. The simulation results show that probabilistic neural network models generate higher predicting precision than the conventional linear regression, limit equilibrium method and maximum likelihood estimation. © 2005 by International Federation for Information Processing.