Geological Modelling & Resource Estimation on Eigenform AI Geo Tooltips

AI-Assisted Implicit Geological Modelling (Lithology, Structure, Alteration & Ore Zones)

Mon, 21 Sep 2026 00:00:00 +0800

Key Takeaways

Lithology, structure, alteration, ore/minezone, and geotechnical domaining are all built in the same implicit-modelling suites — Leapfrog Geo, Datamine Studio RM, and Vulcan — so the AI story for all five is largely the same tool wearing different hats.
Seequent’s Driver module is the clearest mainstream AI feature here: it clusters and classifies drillhole/assay data to speed up implicit lithology and alteration-proxy modelling.
Structural modelling has a genuinely emerging research edge: a 2026 paper, Implicit Structural Modeling via Generative Diffusion Frameworks, uses diffusion models to handle complex fault geometry that traditional implicit methods struggle with — but it’s not in commercial tools yet.
Alteration/proxy modelling increasingly leans on hyperspectral (SWIR) data run through scikit-learn-style classifiers before the results even reach the implicit-modelling package.
Geotechnical domaining rides the same implicit-modelling backbone, with ML regression on RQD/RMR data as an emerging (not yet standard) add-on.

TL;DR

Build your lithology, structural, alteration, ore/minezone, and geotechnical models in Leapfrog Geo, Datamine, or Vulcan as usual — but turn on Seequent’s Driver module for ML-assisted clustering/classification, and feed hyperspectral or automated-mineralogy data into a classifier upstream of the model where you can, since that’s where most of the near-term AI gains live.

Predicting Geotechnical & Recovery Variables in Your Block Model with ML

Mon, 21 Sep 2026 00:00:00 +0800

Key Takeaways

RQD, fracture frequency, point-load strength, clay content, comminution hardness (BWI/DWI), and metal recovery (Cu, Mo, Au, Ag) can all be estimated with machine learning instead of relying purely on sparse physical test coverage.
Computer-vision models (e.g. CNN-based “K-Net” pipelines) now read RQD and fracture frequency directly from core photographs, cutting manual logging variance.
Published copper-recovery models (XGBoost/Random Forest/ANN) have delivered real production gains — a Cerro Verde case study reported +6.5% Cu production from ML-driven recovery prediction.
Most of these submodels aren’t a single commercial product — they’re scikit-learn/XGBoost regressions trained on your own assay + geological + lab-test database, then interpolated into the block model like any other estimated variable.
Maturity varies: RQD/recovery models are proven in production; PLT-model prediction is still mostly a custom, in-house build (Emerging).

TL;DR

Train gradient-boosted or neural-network regressors on your existing lab-test results (RQD, PLT, BWI/DWI, clays, recovery) against geology/alteration/mineralogy features, then krige or interpolate the model’s predictions the same way you would a raw assay — giving every block an estimated geotechnical/metallurgical value instead of only the handful with physical tests.

Predicting Mineralogy and Geometallurgical Domains with ML

Mon, 21 Sep 2026 00:00:00 +0800

Key Takeaways

Both calculated mineralogical models and geometallurgical (geomet) models are, in practice, regression/classification problems trained on automated-mineralogy data — not distinct disciplines requiring separate tooling.
QEMSCAN, MLA, and TIMA supply the ground-truth mineral abundance and texture data that feeds the models.
scikit-learn and XGBoost are the standard open-source libraries for building the regression/classification layer — recovery, hardness, throughput, and mineral-abundance predictions are commonly built as gradient-boosted regressions.
Leapfrog’s Geomet extension folds these predictions back into the same 3D block model as your geology, so geomet variables interpolate alongside grade.
This is confirmed, currently-used practice (ai_relevant: Yes) — not speculative.

TL;DR

Train a gradient-boosted regression (XGBoost or scikit-learn) on your QEMSCAN/MLA/TIMA automated-mineralogy results and metallurgical test data, then interpolate the model’s predictions into your block model via Leapfrog’s Geomet extension to get spatially continuous mineralogy and geomet domains.

Statistical Analysis and Domaining

Mon, 21 Sep 2026 00:00:00 +0800

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 box.
GeostatsPy bridges the gap between clustering output and the geostatistical workflows (variography, estimation) that consume domains.
This is an open-source, code-first workflow — there’s no single commercial “AI domaining button” yet; you’re building a pipeline, not buying one.

TL;DR

Replace or supplement manual/visual geological domaining with unsupervised clustering (K-means/GMM via scikit-learn) run on your multivariate assay, geochemical, and logging data, then pass the resulting domains into GeostatsPy for the downstream geostatistical work.