Traditional mine planning has primarily focused on economic and operational objectives, often overlooking the significant impacts of mining activities on surrounding communities. Today, it is essential for mining operations to assess their activities against sustainable mining criteria to ensure environmental and social responsibility. Blasting, an indispensable part of mining, poses substantial challenges to nearby communities due to its adverse effects, such as vibration, noise, and fly rock. This research addresses these impacts by developing a predictive framework to assess the effects of blasting, focusing on vibrations. By integrating machine learning models with data from real mining operations, this study aims to quantify and predict Peak Particle Velocity (PPV) as a key measure of blast-induced vibration in different blasting schedules. Initial efforts involve collecting data on blasting parameters such as total charge and distance to train and validate the predictive model. In this case study, a data set comprising 373 blasting events was analysed using a Deep Neural Network (DNN) model. The results revealed a strong negative correlation between PPV and scaled distance. These findings highlight the potential to embed the developed model into production scheduling, promoting sustainable mine planning that enhances community well-being while optimising Net Present Value (NPV).