Austin, James, Gazley, Michael, Birchall, Renee, Patterson, Ben, Stromberg, Jessica, Willams, Morgan, Björk, Andreas, Gras, Monica Le, Shelton, Tina, Dhnaram, Courteney, Lisitsin, Vladimir, Schlegel, Tobias, McFarlane, Helen, and Walshe, John
Recent decades have seen an exponential rise in the application of machine learning in geoscience. Fundamental differences distinguish geoscience data from most other data types. Geoscience datasets are typically multi-dimensional, and contain 1-D (drillholes), 2-D (maps or cross-sections), and 3-D volumetric and point data (models/voxels). Geoscience data quality is a product of its resolution and the precision of the methods used to acquire it. The dimensionality, resolution, and precision of each layer within a geoscience dataset translates to limitations in spatiality, scale and uncertainty of resulting interpretations. Historically, geoscience datasets were overlaid cartographically, to incorporate subjective, experience-driven knowledge, and variances in scale, and resolution. The nuances and limitations that underpin the reliability of automated interpretation are well understood by geoscientists, but are rarely appropriately transferred to data science. However, for true integration of geoscience data, such issues cannot be overlooked without consequence. To apply data analytics to complex geoscience data (e.g., hydrothermal mineral systems) effectively, methodologies must be used that characterise the system quantitatively, using collocated analyses, at a common scale. This paper provides research and exploration insights from an innovative district-wide, scale-integrated, geoscience data project, which analysed 1,590 samples from 23 mineral deposits and prospects across the Cloncurry District, Queensland, Australia. Ten different analytical techniques, including density, magnetic susceptibility, remanent magnetisation, anisotropy of magnetic susceptibility, radiometrics, conductivity, scanning electron microscopy (SEM)-based automated mineralogy, geochemistry, and short-wave infrared (SWIR) hyperspectral data with 561 columns of scale-integrated data (+2151 columns of SWIR). All data were collected on 2 cm x 2.5 cm sample cylinders; a scale at which the confidence in coupling of data from techniques can be high. These data are integrated by design, to eliminate the need to downscale coarser measurements via assumptions, inferences, inversions, and interpolations. This scale-consistent approach is critical to the quantitative characterisation of mineral systems and has numerous applications to mineral exploration, such as linking alteration paragenesis with structural controls and petrophysical zonation. [ABSTRACT FROM AUTHOR]