Search

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

The chemical compositions of zircons have been used as magma fertility indicators for porphyry copper mineralization potential. Here, we trained and tested two machine learning (ML) models: support vector machines and random forest to classify the metallogenic fertility (fertile vs. unfertile) based on igneous zircon chemistry. Both models achieved good classification accuracy (~ 93%) against the testing dataset, suggesting the feasibility and effectiveness of using the ML methods to discriminate whether zircons are from fertile or unfertile magmas. The feature importance analysis of the RF classifiers identified that the most important parameters of fertile magma are Eu, Ce, and Dy, further validating previous studies of the genesis of porphyry copper deposit-related magma. As a case study, we predicted the metallogenic fertility of the detrital zircons in the eastern Gangdese belt in southern Tibet by applying the ML models trained by igneous zircon labeled data. Our ML models suggest that the magmas that formed after 50 Ma, especially from 30 to 10 Ma, have higher fertile percentages. Taking this together with the local singularity analysis of detrital zircon U–Pb ages, we suggest that magmatic flare-ups with high FP and singularity index values are more favorable for porphyry copper formation. Our ML models and defined FP may help reveal temporal variation of the favorability for porphyry copper formation. [ABSTRACT FROM AUTHOR]

Abstract: Identifying geochemical anomalies from background is a fundamental task in exploration geochemistry. The Gangdese mineral district in western China has complex geochemical surface expression due to complex geological background and was chosen as a study area for recognition of the spatial distribution of geochemical elements and separating anomalies from background using stream sediment geochemical data. The results illustrate that weak anomalies are hidden within the strong variance of background and are not well identified by means of inverse distance weighted; neither are they clearly identified by the C–A method if this method is applied to the whole study area. On the other hand, singularity values provide new information that complements use of original concentration values and can quantify the properties of enrichment and depletion caused by mineralization. In general, producing maps of singularities can help to identify relatively weak metal concentration anomalies in complex geological regions. Application of singularity mapping technique in Gangdese district shows local anomalies of Cu are not only directly associated with known deposits in the central part of the study area, but also with E–W and N–E oriented faults in the north of the study area. Both types of anomalies should be further investigated for undiscovered Cu mineral deposits. [Copyright &y& Elsevier]