Probabilistic slope stability assessment of laterite borrow pit using artificial neural network

Assessment of slope stability of abandoned laterite borrow pits in residential areas is highly desirable as the consequence of its failure could be fatal. This study applied artificial neural network (ANN) to conduct probabilistic slope stability assessments of the borrow pits. To determine the corresponding factor of safety (FOS), random shear strength parameters, slope geometry, structure load on the slope and structure distance from the slope crest were used as inputs infinite-difference numerical simulations. The FOS was combined with ANN techniques to derive a mathematical model for predicting the failure probability. The effects of variability of soil shear strength parameters and cross-correlation between the parameters on the probability of slope failure were examined. Results showed that the performance level of the pit slopes was hazardous. Variability in shear strength parameters significantly influenced the slope stability, while negative correlation coefficients between the parameters reduced the probability of the slope failure.

Automated summary

This study applied artificial neural network (ANN) to conduct probabilistic slope stability assessments of abandoned laterite borrow pits. The results showed that the performance level of the pit slopes was hazardous, with significant influence of variability in shear strength parameters on slope stability, while negative correlation coefficients between the parameters reduced the probability of slope failure.