EIS toolkit

This study addresses imbalanced data challenges in Mineral Prospectivity Mapping (MPM) using geophysical data from Lapland, Finland. It applies data-level imbalanced handling techniques and algorithm-level threshold adjustments to improve model predictions of rare mineral deposits. The performance of four ML models—MLP, RF, DT, and LR—was evaluated. The MLP model achieved the best accuracy (97.13%) on balanced data using synthetic oversampling.