Enhanced prediction of copper-polymetallic deposits in the Kalatag mining district using integrated SVM and GIS technology

With the continuous depletion of shallow mineral resources, the exploration of deeper mineral deposits has become increasingly crucial for sustaining global metal supply. Traditional prospecting methods often fall short in effectively identifying and evaluating these deeper deposits due to limited data integration and analysis capabilities. In response to these challenges, our research applied the Support Vector Machine (SVM) algorithm, combined with ArcGIS, to develop a comprehensive mineral prospectivity mapping (MPM) using multi-source geological, geochemical, and geophysical data in the Kalatag mining district. Our study successfully identified several key mineralized zones, validated by cross-referencing known deposit locations and anomaly data ranges. The MPM exhibited a prediction accuracy of 92.11%, representing a notable improvement over traditional methods, such as logistic regression, which typically achieve an accuracy of around 89% under similar conditions. This enhancement in prediction capability facilitates more targeted and cost-effective exploration efforts, potentially leading to the discovery of new mineral deposits in previously underexplored deep zones. Our approach not only improves the accuracy and efficiency of mineral exploration by 3.11% but also provides a scalable framework for integrating various data types in geoscience research.