Optimized Data-Driven Models for Prediction of Flyrock due to Blasting in Surface Mines

Using explosive material to fragment rock masses is a common and economical method in surface mines. Nevertheless, this can lead some environmental problems the surrounding regions. Flyrock one of most dangerous effects induced by blasting which needs be estimated reduce potential risk damage. In other words, minimization flyrock sustainability surroundings environment sites. To aim, present study develops several new hybrid models for predicting flyrock. The proposed were based on cascaded forward neural network (CFNN) trained Levenberg–Marquardt algorithm (LMA), also combination least squares support vector machine (LSSVM) three optimization algorithms, i.e., gravitational search (GSA), whale (WOA), artificial bee colony (ABC). construct models, database collected from granite quarry sites, located Malaysia, was applied. prediction values then checked evaluated using statistical criteria. results revealed that all acceptable Among them, LSSVM-WOA more robust model than others predicted with high degree accuracy.