Evaluating Machine Learning Models for Gold Prospectivity Mapping Using Integrated Geological and Geochemical Data in Bindura

Machine learning approaches for gold prospectivity mapping in Bindura District, Zimbabwe, under severe data constraints. One-Class SVM, Isolation Forest and XGBoost were compared under identical conditions using four verified gold deposits and fourteen integrated predictor variables across 51,134 pixels (approximately 46 km2). Isolation Forest achieved the clearest spatial discrimination, identifying 6.9 km2 of high-priority exploration targets. If you use this software or dataset, please cite it as below.