Application of Logistic Regression and Weights of Evidence Methods for Mapping Volcanic-Type Uranium Prospectivity

Pucheng district is a part of the Wuyi Mountain polymetallic metallogenic belt, which constituted by Archean-Proterozoic metamorphic basements and Mesozoic volcanic-sedimentary covers. Uranium deposits are formed as volcanic-hosted structural controls. In this study, hybrid data-driven methods logistic regression (LR) weights evidence (WofE) were applied for mineral potential mapping uranium in district. Evidential layers such volcanic stratum, structure, igneous rock, alteration radioactive anomaly used prospectivity analyses. The results show that can not only measure relative importance each type geological feature controls but also delineate prospective grounds exploration. receiver operating characteristics (ROC) curve under ROC (AUC) to performance models. models highly capable because AUC close 1. more than 90% known occur regions with high probability. LR performs little better WofE area. confirmed there significant mineralization further