Utilization of relevance vector machine for rock slope stability analysis

This study examines the potential of Relevance Vector Machine (RVM) for the prediction of stability of rock slope. RVM is based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. In this paper, the input data for rock slope stability estimation consist of values of geotechnical and geometrical input parameters. Overall, the RVM shows good performance and it also provides probabilistic output. An equation has been also developed for the determination of stability of rock slope based on the present study. The model provides a viable tool for geotechnical engineers to assess the status of rock slope.