Stability estimation of Mount St. Helens using Scoops3D and ensemble learning paradigms

Abstract

This research investigates the application of ensemble-based computational paradigms to estimate the stability of Mount St. Helens. Scoops3D was initially utilized for conducting slope stability investigation, followed by computational modelling of the factor of safety (FOS) employing various influencing parameters. Four base models including AdaBoost regressor, decision tree regressor, extra tree regressor, and gradient boosting regressor, and a bagging-based ensemble learning (BG-ENSM) framework, were used for this purpose. In both seismic and non-seismic conditions, the effect of pore-pressure ratio (r_u) on the stability of Mount St. Helens was investigated in three different combinations (i.e., Cases-1, 2, and 3) with r_u = 0, r_u = 0.3, and r_u = 0 and 0.3. Post computational modelling, the outcomes of the implemented paradigms were evaluated based on several indicators. Experimental outcomes exhibit that the proposed BG-ENSM framework achieved the most desired estimation of FOS with R² of 0.9968, 0.9959, and 0.9985 against Cases-1, 2, and 3, respectively. Based on the overall results and the outcomes of parametric study, the employed BG-ENSM framework can be considered as a viable tool for stability estimation of Mount St. Helens considering the effect of r_u in seismic and non-seismic conditions.