Results
Validation on public datasets.
Cauldra has been trained and validated across three independent BC porphyry systems — different terranes, different operators, multiple drill seasons. 225 drillholes carried into analysis across 130,000+ metres of logged core, spanning eight drill programs. The case study below uses publicly disclosed BC ARIS drill data from a Cu-Au porphyry project across three consecutive programs. Cauldra was trained on the prior-year logging records and run on the latest program blind. The model's outputs match the geological controls documented in the operator's published assessment reports — produced from logging alone, without access to the operator's interpretation.
The model recovers the porphyry zoning framework from logging alone — productive intrusive hosts, barren post-mineral dykes, sulphide paragenesis, and alteration zoning.
-
Porphyritic diorite phases as the primary mineralised hosts.
Five intrusive lithology codes appear in the top seven predictive features — matching the productive hosts described in the operator's assessment reports.
-
Post-mineral monzonite dykes as negative grade contributors.
The paragenetic distinction between mineralised pre-mineral diorite and barren late monzonite intrusions emerges from logging alone — the same separation documented in the published interpretation.
-
Sulphide paragenesis in the documented order.
Chalcopyrite as the strongest positive sulphide signal, followed by bornite — matching the operator's stated abundance for grade-relevant sulphides.
-
Potassic and phyllic alteration as the productive assemblages.
Both rank in the top fifteen predictive features.
The geological controls on grade are learnable from standard core logging data — independently of the operator's interpretation. For an active program, that means a calibrated read on grade as logging comes in.
