Performance Evaluation of Vegetative Species for Engineered Slope Stabilization Using Finite Element Analysis Aided with Machine Learning
摘要
Physical construction techniques such as soil nails, anchors, and micropiles are widely used to ensure the stability of the slope. In recent decades, the possibility of bioengineering measures has been explored as a novel mitigation technique for slope stabilization. However, it has not been established in the field application due to a lack of technical knowledge and guidelines. The present research focused on the analysis of slope stability by employing a model that simulates vegetation root distribution through an equivalent cohesion approach. The factor of safety (FoS) calculations have been conducted using finite element analysis based PLAXIS–2D software followed by the development of ML models for the prediction of FoS. The investigation into alterations in slope stability conditions included the utilization of a combination of two plant species, P. longifolia and A. dammara, alongside C. rotundus. The findings revealed that optimal stability has been achieved when vegetation is positioned on the slope’s surface in comparison to the top. Slopes with combined vegetation exhibited enhanced stability compared to those with uniform vegetation. An inverse relationship has been observed between the FoS and the slope angle, with the FoS reaching its maximum when the specified plant species are combined. The study identified the mechanical impact of the plant root matrix system as a contributing factor to increased soil shear strength, consequently leading to improved slope stability. The density of roots within the soil mass and their tensile strength emerged as critical elements influencing the soil’s capacity to withstand shear stresses.