Hybrid GWO-XGBoost Framework for Blast-Induced Ground Vibration Prediction: Integration of Genetic Algorithm-Optimized Scaled Distance

Abstract

Blast-induced ground vibrations, commonly measured in terms of Peak Particle Velocity (PPV), can affect adjoining communities, damage structures, and undermine the integrity of rock masses.  Therefore, accurate PPV prediction is a prerequisite for making blasting sustainable and safe.  This paper introduces a novel hybrid machine learning method that integrates Extreme Gradient Boosting (XGBoost) and Grey Wolf Optimization (GWO) in predicting PPV using 88 datasets obtained at the Akdaglar Quarry, Istanbul. Nine important input parameters were taken into account, including geological aspects and blasting design.  In comparison to the traditional scaled distance, a new parameter modified scaled distance (MSD), was derived through a genetic algorithm, and showed better correlation with PPV (r = –0.869). Model performance was improved by optimal tuning of XGBoost hyperparameters through the utilization of the GWO method. The GWO-XGBoost model performed better than SVM and stand-alone XGBoost, with R = 0.9916, R² = 0.9748, RMSE = 1.0291 mm/s, and MAPE = 3.1105%. The monitoring distance and scaled distance are the most influential predictors, according to SHAP (Shapley Additive Explanations) analysis. The results demonstrate that evolutionary optimization algorithms substantially enhance PPV prediction accuracy, offering practical implications for pre-blast vibration assessment and sustainable quarry design.