| Popis: |
When extracting geo-information from geochemical data, it is essential to consider the compositional nature and geological signatures of the data. Isometric log-ratio transformation (ILR) produces an orthonormal basis of geochemical data and accounts for the compositional nature of the data. However, it still often remains difficult to interpret ILR-transformed variables because of the lack of a geological basis for a data-driven approach; therefore, it is necessary to find some geological knowledge-based criteria to help enable a more understandable interpretation following ILR transformation. Characterized by certain elements and elemental ratios, the chronological order of geological processes can be used to construct interpretable ILR transformation. This concept was applied to extract geo-information from stream sediment geochemical data in the Duolong mineral district, Tibet, China. Furthermore, the expectation-maximization (EM) algorithm modified by a minimum message length criterion (MML) was employed to investigate mixture distributions of the geochemical data. In the study area, mafic rocks with high concentrations of Cr and Ni were emplaced earlier than the porphyry Cu–Au deposits which have stable Cu/Au ratios. Based on these criteria and hierarchical cluster analysis, sequential binary partition was constructed among the Cu, Au, Cr, and Ni concentrations. The ILR-transformed variables follow either a bi-normal or tri-normal distribution, the subpopulations of which were interpreted as fingerprints inherited from mafic magmatic processes, Cu–Au hydrothermal systems, and later geological processes, respectively. The high-average subpopulation of ILR-transformed Cu corresponds to anomalies associated with the porphyry and epithermal Cu–Au systems, and two areas are predicted to have high Cu–Au mineralization potential. This study demonstrates that geological knowledge-driven ILR transformation is a promising way to efficiently extract geo-information from geochemical data. |
Full Text from ScienceDirect