Dump slope stability analysis using artificial intelligence

Abstract

The fourth industrial revolution has introduc ed several rapidly progressive technologies like big data analytics, the internet of things, simulation, autonomous robots, cloud computing and artificial intelligence. It has reduced the effort and processing time in the manufacturing/production industry through new emerging technologies. In this study, artificial intelligence has been adopted to forecast the stability of multi bench dump slope structure with ease and minimum interval. The supervised machine learning methodbased Decision Tree, Gradient Boosting, Multi-variate Nonlinear, Random Forest and Support Vector Machine soft computing models are deployed to assess the dump slope stability. Numerical modelling has been used to generate error-free datasets for the training and testing of models. Hyperparameter tuning has been done to optimize the performance of the machine learning models. The performance of the models has been analyzed based on the Coefficient of Determination and the Root Mean Square error. The study outcomes reveal that the Multivariate Nonlinear regression model predicts the stability of dump slope structure with better accuracy for the considered datasets. It yields a coefficient of determination of 95.4%, while the root mean square error is only 4.6%. © 2022, Books and Journals Private Ltd.. All rights reserved.