Several Tree-Based Solutions for Predicting Flyrock Distance Due to Mine Blasting

Blasting operations involve some undesirable environmental issues that may cause damage to equipment and surrounding areas. One of them, probably the most important one, is flyrock induced by blasting, where its accurate estimation before operation essential identify blasting zone’s safety zone. This study introduces several tree-based solutions for an prediction flyrock. has been done using four techniques, i.e., decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), adaptive (AdaBoost). The modelling techniques was conducted with in-depth knowledge understanding their influential factors. mentioned factors were designed through use parametric investigations, which can also be utilized in other engineering fields. As a result, all models are capable enough blasting-induced prediction. However, predicted values obtained AdaBoost technique. Observed forecasted training testing phases received coefficients determination (R2) 0.99 0.99, respectively, confirm power this technique estimating Additionally, according results input parameters, powder factor had highest influence on flyrock, whereas burden spacing lowest impact