1. CONTEXT AND PROBLEM STATEMENT The mining industry faces a structural supply deficit that shows no signs of abating. Demand for copper, gold, and other critical minerals continues to increase, driven by electrification programs, infrastructure investment, and the energy transition, while the pipeline of greenfield discoveries remains insufficient to meet projected demand. This dynamic exerts simultaneous pressure on two strategic fronts: the discovery of new deposits and the optimization of economic recovery from existing operations. Both imperatives carry substantial cost. Greenfield exploration entails elevated geological risk and protracted development timelines. Brownfield expansion at operating mines presents comparatively lower geological risk, yet remains capital-intensive. The economic return on any given drill program is, in large measure, a function of target selection quality prior to mobilization of drilling equipment. Meters drilled into non-economic material represent both direct capital losses and opportunity costs incurred at the expense of higher-confidence targets elsewhere. The resource estimation methodologies that underpin the majority of targeting decisions have remained fundamentally unchanged for several decades. Ordinary Kriging and its variants constitute the industry standard (Glacken and Blackney, 2022). These approaches perform reliably under conditions of dense drill spacing and spatially continuous mineralization, but exhibit welldocumented limitations in deposit geometries that are increasingly characteristic of contemporary mining operations: structurally controlled systems, nuggety grade distributions, and ore bodies in which economic value is concentrated in discrete high-grade domains surrounded by marginal or barren rock. As a linear spatial interpolator, Kriging is inherently smoothing in its estimation behavior. In deposits where grade continuity is poor and economic value is concentrated rather than distributed, this averaging characteristic constitutes a limitation with material consequences for mine planning (Glacken and Blackney, 2022). A secondary, underappreciated problem relates to data utilization. Operating mines routinely collect extensive geological logging data—lithology, alteration, mineralization codes, geotechnical parameters—for every meter of drill core recovered. The preponderance of this information is used, at most, for structural domain definition before being archived. Additionally, at many underground operations, substantial portions of drillhole databases remain unassayed as a cost-saving activity: core visually classified as barren during logging is frequently excluded from resource model construction entirely, despite its spatial information content regarding deposit geometry and host rock architecture. ML and DL architectures are technically capable of working with heterogeneous data of this kind. Neural networks accommodate non-linear relationships, process mixed data types, and identify spatial patterns that linear estimation methods cannot capture (Goodfellow, Bengio and Courville, 2016; Dumakor-Dupey and Arya, 2021). However, direct application of these techniques to geological modelling is not trivial. Finite computational resources, overfitting risks, inconsistencies in geological core logs, assay bias, and the inherent subjectivity of visual core logging each introduce substantive complications. The predictive utility of individual geological log codes for grade estimation is not a priori knowable; among economically informative codes,
RkJQdWJsaXNoZXIy MTM0Mzk2