Geological Modelling & Resource Estimation

Geological modelling and resource estimation is where AI assists a geologist’s interpretation rather than replacing it: implicit modelling software that infers lithology, structure and alteration from sparse drill data, and statistical models that predict geotechnical and recovery variables directly into a block model.

This category also covers predicting mineralogy and geometallurgical domains and the underlying statistical domaining work that groups a deposit into zones with distinct behaviour before a mine plan is built on top of it.

Statistical Analysis and Domaining

Key Takeaways Unsupervised clustering (K-means, Gaussian Mixture Models, hierarchical clustering) is now a published, credible way to define geological domains from multivariate assay/logging data. scikit-learn provides production-ready implementations of all three clustering approaches out of the …