Predicting the Young’s Modulus of Rock Material Based on Petrographic and Rock Index Tests Using Boosting and Bagging Intelligence Techniques

Rock deformation is considered one of the essential rock properties used in designing and constructing rock-based structures, such as tunnels slopes. This study applied two well-established ensemble techniques, including boosting bagging, to artificial neural networks decision tree methods for predicting Young’s modulus material. These techniques were a dataset comprising 45 data samples from mountain range Malaysia. The final input variables these models, p-wave velocity, interlocking coarse-grained crystals quartz, dry density, Mica, selected through likelihood ratio test. In total, six models developed: standard networks, boosted bagged classification regression trees, extreme gradient trees (as tree), random forest bagging tree). performance was appraised utilizing correlation coefficient (R), mean absolute error (MAE), lift chart. findings this showed that, firstly, outperformed all developed study; secondly, models.