Tectonic interpretation is critical to a coal mine’s safe production, and fault interpretation is an essential component of seismic tectonic interpretation. With the increasing necessity for accuracy in fault interpretation in coal mines, it is increasingly challenging to achieve greater accuracy only through traditional fault interpretation. The convolutional neural network (CNN) is a machine learning method established in recent years and it has been widely applied in coal mine fault interpretation because of its powerful feature-learning and classification capabilities. To improve the accuracy and efficiency of fault interpretation in coal mines, an automatic seismic fault identification method based on the convolutional neural network has been developed. Taking a mining area in eastern Yunnan province as an example, the CNN model realized automatic identification of faults with eight seismic attributes as feature inputs, and the model-training parameters were optimized and compared. Ten faults in the area were selected to analyze the prediction effect, and a comparative experiment was done with model structure parameters and training sets. The experimental results indicate that the training parameters have a significant influence on the training time and testing accuracy of the model, while structural parameters and training sets affect the actual prediction effect of the model. By comparison, the fault results predicted by the convolutional neural network are in good agreement with the manual interpretation, and the accuracy of the model is more than 85%, which proves that this method has certain feasibility and provides a new way to shorten the fault interpretation period and improve the interpretation accuracy.

The foundation of successful mineral exploration is precise bauxite horizon demarcation and grade estimation. Although core analysis is the industry standard method, it is costly, labor-intensive, and has a relatively low processing capacity. To overcome these limitations, this study constructed an Extreme Gradient Boosting (XGBoost) classifier based on the logging parameters of natural gamma logging (GR), natural gamma spectroscopy logging (GGL), three-lateral logging (LL3), and compensated density logging (CDN) in order to achieve the automation of ore layer identification and grade prediction. The karst-type bauxite in Lvliang, Shanxi, was used to validate the research. The model was trained using the data from four wells in Shenjiazhuang. The trained model was directly applied to a blind well in Xingxian without parameter adjustment. Strong cross-site generalization was demonstrated by horizon recognition, which achieved 98.18% accuracy, 96.62% precision, 91.49% recall, and an F1 score of 93.99%. Based on the Al/Si ratio (A/S) and the content of Al₂O₃, the grade prediction classifies the samples into three grades: high-, medium-, and low-grade. The Mean Absolute Errors (MAEs) for the prediction of high- and medium-grade subsets of Al₂O₃ were 0.906 and 1.643, respectively, and those for A/S were 1.224 and 1.146, respectively. And the coefficient of determination (R²) for each grade level was greater than 0.8. These results support XGBoost’s field applicability and resilience for intelligent bauxite exploration.