An Artificial Neural Network-Based Approach to Predict Blast-Induced Ground Vibrations in Open Cast Coal Mine— A Case Study

This study aims to assess and predict blast-induced ground vibrations of opencast coal mine. The analysis was carried out using two methods i.e. the widely employed empirical vibration predictor known as the USBM (United States Bureau of Mines) equation, and a machine learning model called the artificial neural network (ANN). A dataset including 38 blast vibration recordings was collected and used for the development of an ANN model. Additionally, these datasets were employed to evaluate the site determination constants of the empirical vibration predictor. A total of 27 recordings of blast-induced ground vibrations were gathered from the same opencast coal mine in order to assess the effectiveness of both models. The output (dependent variable) for both models is the peak particle velocity. The effectiveness of the prediction model was evaluated by using commonly used statistical measures, namely the coefficient of determination ( $$R^{2}$$ ). Consequently, the ANN model that was built exhibited more precision in comparison to the existing empirical model. The ANN model exhibited a strong positive relationship between the observed and anticipated peak particle velocity values, as shown by the coefficient of determination ( $$R^{2}=0.84$$ ).