Figure 8 – Pre-drill estimated values and post-drill verified results for each target zone 4.2 Western Australian Orogenic Lode Gold The Australian study deposit is an underground orogenic lode gold system characterized by nuggety grade distributions and quartz-vein-hosted mineralization. Mineralized zone (MZ) logging is employed extensively for domain definition; however, MZ codes are applied across multiple pre-mineral lithological units, and both barren and bonanza-grade assays occur within short spatial intervals. Consequently, MZ classification constitutes an insufficiently reliable sole basis for grade estimation. Application of the PSA identified specific lithological and alteration codes that correlated more reliably with gold grade than MZ logging alone. When incorporated as pathfinder channels, the DL model recovered mineralized intervals that the site’s Cokriging (CIK)-based model had not identified. The improvement was most pronounced in deposit sectors where MZ logging had been applied inconsistently by different geologists over successive campaigns—zones in which the Kriging model propagated logging inconsistency as spatial noise, while the DL model, operating on PSA-screened inputs, resolved through it. Drill targeting based on the model confirmed economic gold grades in volumes the site model had classified as waste, validating the pathfinder approach in a structurally complex, nugget-effect-dominated system in which conventional domain-based estimation exhibits documented performance limitations (Glacken and Blackney, 2022; Sims, 2023). 4.3 Kazakh Orogenic Lode Gold The Kazakh study site is an orogenic lode gold deposit in western Kazakhstan, presenting the most challenging data environment of the three sites investigated. The logging database had been compiled over a more extended operational history with greater variation in geological conventions and code usage. Application of the PSA identified a smaller set of codes meeting the significance threshold than at either the Australian or Chilean deposits—a direct quantitative reflection of the reduced signal-to-noise ratio in the logging data. The DL model trained on PSA-screened inputs nonetheless outperformed the site conventional estimation in prospective blind reconciliation, though the magnitude of improvement was smaller than at the Chilean site. This outcome is consistent with the lower signal content of the available logging data. The result demonstrates both that the methodology adds value under conditions of degraded data quality and that the magnitude of that improvement scales predictably with the information content of the input data. The PSA adapts to this constraint rather than imposing uninformative inputs on the model. 4.3 Summary Across Deposits Table 4 – Cross-deposit comparison
RkJQdWJsaXNoZXIy MTM0Mzk2