Development of an Optimized Regression Model to Predict Blast-Driven Ground Vibrations

Ground vibrations caused by blasting operations in cement canisters is among the main mining issues that cause significant disruptions to nearby buildings and infrastructure. This research was performed a limestone quarry situated southeast of Helwan City, Egypt, investigate impact ground motion vibration due blast action rocks. To reduce environmental blasting, continuous monitoring, accurate medium's peak particle velocity (PPV) assessment are required. Recently, machine learning (ML) models employed diverse applications. The default hyperparameters such must be modified fit problem concerned. optimization for ML impacts model's performance efficiency. In this research, different regression implemented predicting PPV values. A dataset representing 1438 incidents area built utilized evaluate considered models. incorporates relationship amplitude both explosive charge weight per delay distance from blast. predictive models' output has been evaluated using root-mean-squared error (RMSE) coefficient determination ($R^{2}$ ). divided into training testing data produce statistically results make more representative avoid overfitting. test acts as proxy any new prediction. There evidence higher developed Decision Trees model with lowest RMSE highest $R^{2}$ on data. decision tree is, therefore, an acceptable algorithm construction other areas conditions identical those Helwan. Finally, comparative experimental have shown optimized can predict values lower errors greater prediction accuracy.