Mineral Prospectivity Mapping of Porphyry Copper Deposits Based on Remote Sensing Imagery and Geochemical Data in the Duolong Ore District, Tibet

Several large-scale porphyry copper deposits (PCDs) with high economic value have been excavated in the Duolong ore district, Tibet, China. However, altitudes and harsh conditions this area make traditional exploration difficult. Hydrothermal alteration minerals related to PCDs diagnostic spectral absorption features visible–near-infrared–shortwave-infrared ranges can be effectively identified by remote sensing imagery. Mainly based on hyperspectral imagery supplemented multispectral geochemical element data, district was selected conduct data-driven PCD prospectivity modelling. A total of 11 known 17 evidential layers multisource geoscience information Cu mineralization constitute input datasets predictive models. deep learning convolutional neural network (CNN) model applied mineral mapping, its applicability tested comparison conventional machine models, such as support vector random forest. CNN achieves greatest classification performance an accuracy 0.956. This is first trial mapping combined geochemistry methods. Four metallogenic prospective sites were delineated verified through field reconnaissance, indicating that application learning-based methods prospecting proposed paper feasible utilizing big data elements.