Estimation of slope stability using ensemble-based hybrid machine learning approaches

• DOI: 10.3389/fmats.2024.1330609
• Publication Date: 2024-03-01T04:27:40Z
• Authors: Prashanth Ragam; N. Kushal Kumar; Jubilson E. Ajith; Guntha Karthik; Vivek Kumar Himanshu; Divya Sree Machup...; Bhatawdekar Rames...
• Keywords: Ensemble Learning

Mining is one of the most daunting occupations gain sector since it entails risk at any point in operation. In its operation, main focus on slope stability. To avoid failures, work should be performed line with both regulations and safety criteria. Slope stability essential mining activities owing to failure putting productivity risk. Prediction difficult because complexity traditional engineering techniques. Through study, recent technologies have helped companies predict problems quickly effectively. this current research, an ensemble machine learning intelligence algorithms was used estimate assess Factor Safety (FOS). Ostapal Chromicte Mine, India, 79 experimental occurrences were tracked gather in-the-moment field data. The available data split into training testing sets random build algorithms. five influenced factors such as unit weight, friction angle, cohesiveness, depth, well angle input variables FOS. Selected techniques Multiple Linear Regression (MLR), Decision Tree, Random Forest (RF), eXtreme Gradient Boosting (XGBoost) hybrid model combining (XGBoost-RF) developed evaluate validity efficiency created models can evaluated using standard evaluation parameters coefficient determination ( R 2 ), root mean square error (RMSE), (MSE), normalized (NRMSE), absolute percentage (MAPE) deviation (MAD). precise FOS across all discovered XGBOOST-RF model, which had a high 0.931, MSE 0.009, NRMSE 0.069, MAD 0.037, MAPE 3.581 RMSE 0.098.