Slope stability assessment based on finite element method and artificial neural networks approaches

Abstract

This study is conducted in Lam Dong Province, a region frequently affected by severe landslides. The primary objective is to investigate the influence of geological parameters and slope geometry on the slope stability factor. A numerical model is developed using PLAXIS 2D, a finite element method-based geotechnical analysis software. A total of 500 cases are generated, incorporating four key input parameters: slope height (H), slope angle (β), soil cohesion (c) and internal friction angle (φ). The resulting dataset is subsequently analyzed using an Artificial Neural Network (ANN) algorithm to quantify the relative influence of each parameter on the slope safety factor. The findings reveal that slope height exerts the greatest influence on slope stability, whereas the slope angle demonstrates an insignificant effect within the study area. This paper offers a comprehensive perspective on slope stability and serves as a basis for proposing appropriate landslide mitigation strategies Lam Dong Province.