Stability Analysis of Slopes Prone to Circular Failures Using Logistic Regression

Abstract

The analysis of stability of slopes is a classical problem for geotechnical engineers. In practice, much user friendly software is available for proper usage. Besides additional techniques capable of providing information useful for decision-making are necessary. In this research, extensive slope failure data collected by Sah et al. [1] were used for the stability analysis of slopes subjected to circular failures. For the purpose, 44 separate slope models were prepared for each slope case given in the original work. The Slide® program produced similar safety factors for the studied cases. Binary logistic regression analysis was applied in the study as an alternative technique to predict stability condition of slopes. The model predicted the stability condition of slopes with 90.9% accuracy.