Abstract
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.