Machine Learning Prediction and Interpretability Analysis of Coal and Gas Outburst

Coal and gas outbursts constitute a major hazard for mining safety, which is critical for the sustainable development of China’s energy industry. Rapid, accurate and reliable prediction is pivotal for preventing and controlling outburst incidents. Nevertheless, the mechanisms driving coal and gas outbursts involve highly complex influencing factors. By examining the attributes of these factors and their association to outburst intensity, four major geological and environmental indicators were identified. This study developed a machine learning-based prediction model for outburst risk. Five algorithms were evaluated: K-Nearest Neighbors (KNN), Back Propagation Neural Network (BPNN), Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost). Model optimization was performed via Bayesian hyperparameter (BO) tuning. Model performance was assessed by the Receiver Operating Characteristic (ROC) curve; the optimized XGBoost model demonstrated strong predictive performance. To enhance model transparency and interpretability, the SHapley Additive exPlanations (SHAP) method was implemented. The SHAP analysis identified geological structure was the most important predictive feature, providing a practical decision-support tool for mine executives to prevent and control outburst incidents.