A new method for calculating failure probability of landslide based on ANN and a convex set model

Calculating the failure probability of a landslide is important in engineering related to geological process and geomorphological evolution. Strength parameters of a soil (i.e., cohesion and internal friction angle) are regarded as uncertain-but-bounded parameters. In this study, a new method is proposed for computing the landslide failure probability based on a convex set model and artificial neural network (ANN). In the new method, ANN is used to determine the limit state function of landslide stability, and the failure probability is determined using a simple iterative algorithm. The new method was applied to calculate the failure probability of the Gufenping landslide in Nanjiang, Sichuan, China. The results calculated using a Monte Carlo simulation (MCS) method confirmed that the new method accurately and quickly obtains the failure probability of a landslide. Additionally, compared with the two-dimensional calculation method, the one-dimensional analysis method overestimates the failure probability of the landslide. The results of single factor and global sensitivity analysis indicate that the average of internal friction angle is the main factor affecting the stability of the landslide. It is easy to calculate failure probability of landslides using the novel method than using the conventional methods.

Automated summary

Calculating the failure probability of landslides is crucial in engineering, and a new method using a convex set model and artificial neural network (ANN) has been proposed in this study. The new method was successfully applied to calculate the failure probability of the Gufenping landslide in Sichuan, China, with results confirming its accuracy and efficiency compared to conventional methods. The main factor affecting landslide stability was identified as the average internal friction angle through sensitivity analysis.