Mineral quantification at deposit scale using drill-core hyperspectral data: A case study in the Iberian Pyrite Belt

• Published in: Ore geology reviews Vol. 139; p. 104514
• Main Authors: De La Rosa, Roberto, Khodadadzadeh, Mahdi, Tusa, Laura, Kirsch, Moritz, Gisbert, Guillem, Tornos, Fernando, Tolosana-Delgado, Raimon, Gloaguen, Richard
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021
• Subjects: 3D modelling; Dictionary learning; Drill-cores; Hyperspectral data; Machine learning; Mineral quantification; Mineral quantification; Hyperspectral data; Drill-cores; 3D modelling; Dictionary learning; Machine learning
• ISSN: 0169-1368; 1872-7360
• DOI: 10.1016/j.oregeorev.2021.104514

[Display omitted] •Machine learning workflow to quantify minerals using drill-core hyperspectral data.•Mineral quantification in a 3D environment for vectoring towards mineralization.•Dictionary learning technique to exploit co-register SEM-MLA with hyperspectral data.•Mineral assemblages and chemical composition multi-scaled across the whole deposit.•3D modelling from hyperspectral drill-core data. Drill-core analysis is paramount for the characterization of deposits in mineral exploration. Over the past years, the use of hyperspectral (HS) sensors has rapidly increased to improve the reliability and efficiency of core logging. However, scanning drill-core samples of an entire mineral deposit entails several complex challenges, from transport logistics to large scale data management and analysis. Hence, academic studies on new applications of drill-core HS data at a mineral deposit scale remain rare. We present a semi-automated workflow for large scale interpretation of HS data, founded on a novel approach of mineral mapping based on a supervised dictionary learning technique. This approach exploits the complementary information from scanning electron microscopy based automated mineralogy and hyperspectral imaging techniques for estimating mineral quantities along all boreholes. We propose that it is effectively possible to propagate the mineral quantification to the entire borehole from small samples with high resolution mineralogical information strategically selected throughout the deposit. We showcase this approach on data acquired in the Elvira shale-hosted volcanogenic massive sulphide (VMS) deposit located at the Iberian Pyrite Belt (IPB), where 7000 m of drill-core were acquired along 80 boreholes. Resulting maps provide insights on the controls on the mineral assemblages and chemical composition of specific minerals across the whole volume at several spatial scales, from large scale variations within apparently homogeneous black shales to small scale mineral composition variations, of potential use as vectors towards mineralization. This approach adds value to the core data, allowing for a better understanding of the geological setting of the Elvira deposit and providing valuable insights for future exploration targeting in the region. This approach based on machine learning can easily be transposed to different ore deposits with a limited input from a geologist.