Decision Support System for the Prediction of Mine Fire Levels in Underground Coal Mining Using Machine Learning Approaches

This study elucidates a new idea to predict mine fire levels by employing several machine learning techniques. A total of 120 patterns of various mine fire influencing parameters, such as oxygen, nitrogen, carbon monoxide, and temperature, were compiled from the Adularya coal mine in Turkey. Techniques like t-distributed stochastic neighbor embedding (t-SNE) and k-means clustering were used to process the data, and support vector classification (SVC) was executed to predict various levels of the mine fire. The results revealed that the proposed model has higher credibility to predict the various levels of underground mine fires.