Implementation of Surrogate Models for the Analysis of Slope Problems

Numerical modeling is increasingly used to analyze practical rock engineering problems. The geological strength index (GSI) a critical input for many However, no available method allows the quantification of GSI parameters, and engineers must consider range values. As projects progress, these ranges can be narrowed down. Machine learning (ML) algorithms have been coupled with numerical create surrogate models. concept models aligns well deductive nature data availability in projects. In this paper, we demonstrated use two common slope stability problems: (1) determining maximum stable depth vertical excavation (2) allowable angle fixed height. Compared support vector machines K-nearest algorithms, random forest model performs best on set 800 problems discussed paper. For all models, regression-type outperform classification Once confirmed preform accurately, instantaneous predictions achieved according any parameters. This capability investigate impact narrowing estimation.