157 Figure 4 – Extreme Gradient Boosting (XGB) and LightGBM (LGB) ML Models Figure 5 – K-Nearest Neighbors (KNN) and Support Vector Regression (SVR) ML Models 3. RESULTS The integrated and standardized workflow successfully generates mineral prospectivity models for the Arequipa region using a normalized 500 × 500 m spatial grid. The unified feature space (0–1 scaled variables) enabled consistent comparison among heuristic and machine learning methods. The comparative analysis (Table 1) revealed clear performance differentiation among models. The Support Vector Regression (SVR) model achieved the highest explanatory capacity (R² = 0.7764), indicating its ability to capture a substantial portion of spatial variability in mineralization occurrence. In binary classification, SVR reached a precision of 0.9800 and the highest F1-score (0.6667), reflecting an effective balance between precision and recall under a conservative threshold (0.7200). Its recall (0.5000) indicates that the model prioritizes certainty over exhaustiveness, favoring high-confidence target delineation while minimizing false positives, and suggesting suitability for cost-sensitive exploration contexts where overdrilling is a critical risk. Despite higher absolute regression errors (MAE and RMSE) relative to other models, attributable to broader score dispersion, SVR achieved superior classification reliability under optimized thresholding. Extreme Gradient Boosting (XGB) demonstrated the strongest discriminative capacity (AUC = 0.9989) and complete recall (1.0000), successfully classifying all mineralized cells in the validation dataset. However, its precision (0.0036) was low under the selected classification threshold (0.0040), indicating substantial false positives. This behavior reflects strong ranking performance but sensitivity to threshold selection in strongly imbalanced class conditions. The limited number of known deposits relative to non-
RkJQdWJsaXNoZXIy MTM0Mzk2