Mining is a critical industry that provides essential minerals and resources for modern society. Despite its benefits, the industry is also recognized as one of the most dangerous occupations, with geotechnical hazards being a primary concern. This study introduces the hazard recognition in underground mines application (HUMApp), a mobile application developed to enhance safety within underground mines by efficiently identifying geotechnical hazards, specifically focusing on roof falls. Employing a convolutional neural network (CNN), HUMApp achieved an accuracy of 90%, with recall and F1-score also reaching 90%, reflecting its high reliability in hazard detection. The application's effectiveness was validated against expert assessments, showing significant agreement in identifying critical hazards. This validation highlights HUMApp's potential to enhance proactive risk management in underground mining. This paper details each step of HUMApp's development, from dataset preparation and model training to performance evaluation and application design, showcasing a scalable solution adaptable to various mining environments.
Keywords: deep learning; mine safety; vision-based detection.