Exploration & Target Generation on Eigenform AI Geo Tooltips

AI-Assisted Automated Mineralogy: TIMA, MLA & QEMSCAN

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

Key Takeaways

TIMA, MLA, and QEMSCAN are all SEM-based automated mineralogy platforms — they scan a polished sample, fire an electron beam, and classify every mineral grain from its X-ray spectrum, at rates up to ~100,000 grains/hour.
All three now lean on machine-learning classifiers under the hood for particle/phase identification, not just fixed spectral lookup tables.
MLA is the original platform (Thermo Fisher/FEI); QEMSCAN and Zeiss Mineralogic are close alternatives, with Mineralogic explicitly marketing AI-based deep-learning classification.
TESCAN TIMA is the newer entrant and increasingly the default choice for high-throughput exploration and geometallurgy programs.
Output feeds directly into liberation analysis, grain-size distribution, and the clay/hardness/recovery ML models used elsewhere in your geometallurgy workflow.

TL;DR

Send polished sample mounts through an automated SEM mineralogy platform (TIMA, MLA, Mineralogic, or QEMSCAN) rather than manual point-counting — the instrument’s built-in ML classifier turns raw X-ray spectra into quantitative mineral, liberation, and grain-size data in hours instead of weeks.

Airborne TMI Gravimetry Magnetometry

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

Key Takeaways

Airborne total magnetic intensity (TMI), gravity, and magnetometry survey processing is classical geophysics — Geosoft Oasis montaj (Seequent) remains the industry-standard processing software.
The AI layer is additive, not a replacement: platforms like VRIFY DORA take your processed airborne grids and fuse them with other datasets for automated target ranking.
This item is marked “Emerging” for AI relevance specifically because the fusion/interpretation layer is newer than the acquisition and processing itself.
If you’re not already using AI-driven fusion tools, your airborne survey workflow doesn’t need to change to benefit later — the processed grids are the input DORA and similar tools expect.

TL;DR

Process your airborne TMI/gravity/magnetics survey in standard software (Geosoft Oasis montaj), then optionally route the output grids into an AI fusion/targeting platform like VRIFY DORA to combine them with geochemistry and geology for automated target ranking — the acquisition side stays classical.

Analytical Methods

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

Key Takeaways

Choosing and interpreting geochemical analytical methods (aqua regia vs. multi-acid digestion, ICP-MS vs. XRF, etc.) is increasingly software-assisted rather than purely analyst judgment.
ioGAS (IMDEX) is the industry-standard platform for exploring and interpreting multivariate geochemical datasets, and now has AI/Python-scriptable extensions for pattern detection.
This is an “Emerging” AI category: ioGAS itself is mature and widely used, but the AI/ML layer on top of it (automated anomaly detection, clustering) is the newer part.
The payoff is speed — correlating thousands of multi-element assay results by hand versus in minutes with statistical tooling.

TL;DR

Use a platform like ioGAS to interactively explore and statistically interpret your multi-element geochemical dataset, then layer in Python/ML scripting for automated anomaly and pattern detection rather than eyeballing scatter plots.

Core Photography

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

Key Takeaways

High-resolution automated core photography is the raw data source that most downstream AI core-analysis tools depend on.
Corescan (now Epiroc), Datarock Core, and Minalyze all offer automated core photography systems designed to feed AI extraction pipelines.
This is a “Yes” — production-grade, already deployed across major mining companies.
Get the photography pipeline right first: every AI fracture/lithology/mineralogy tool downstream is only as good as the image quality and consistency it’s trained/run on.

TL;DR

Set up automated, standardized high-resolution core photography (via Corescan, Datarock, or Minalyze hardware) as the foundation — it’s the input every downstream AI logging, fracture-detection, and mineralogy tool depends on.

Core Scanning

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

Key Takeaways

Hyperspectral core scanning captures mineralogy and alteration information invisible to the naked eye, and it’s one of the most mature AI-adjacent technologies in exploration geology.
Leading systems: Corescan HCI-3, CSIRO/Epiroc HyLogger 4, and Minalyze MCore.
HyLogger 4 is the world’s first continuous visible-to-thermal-infrared core scanner (0.4–15 microns), adding mid-infrared for minerals invisible to earlier generations.
This is a “Yes” — deployed at national core libraries (Australia) and commercial operations, not experimental.

TL;DR

Run drill core through a hyperspectral scanner (HyLogger 4, Corescan HCI-3, or Minalyze MCore) to automatically generate mineralogy and alteration maps along the entire core length — data that would otherwise require selective, time-consuming point sampling with a spectrometer or petrographic microscope.

Density Test

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

Key Takeaways

Physical density testing (water immersion, wax coating, gas pycnometry) has no dedicated software of its own — it’s a bench measurement, not a computational one.
The AI opportunity is predicting density from cheaper, faster proxy measurements instead of running the physical test on every sample.
A January 2026 peer-reviewed study, A Multi-Proxy Framework for Predicting Ore Grindability, shows portable XRF, Leeb hardness, and hyperspectral imaging can stand in for slower physical rock-property tests with real predictive power.

TL;DR

You don’t AI-ify the density test itself — you train a regression model on hyperspectral, XRF, and hardness proxy data to predict density (and related grindability parameters) without running the physical test on every single sample.

Environmental Studies

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

Key Takeaways

Envirosuite (EVS Industrial) is the leading environmental intelligence platform used by mining operations, now owned by Ideagen.
It combines device-agnostic sensor integration with weather forecasting to predict dust, noise, vibration, and blast-fume impacts up to 72 hours ahead.
A dedicated Blasting Module forecasts blast fume, overpressure, flyrock, and vibration — directly useful for permitting-stage environmental studies.
This is “Emerging” for AI relevance: real-time monitoring is mature, but the predictive (forward-looking) forecasting layer is the newer, more AI-driven capability.

TL;DR

Feed your site’s environmental sensor network (dust, noise, vibration, water quality) into a platform like Envirosuite’s EVS Industrial, and its predictive models forecast environmental impacts up to 72 hours out — turning environmental studies from a reactive compliance exercise into a proactive planning input.

Fracture Spacing AI

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

Key Takeaways

Fracture spacing/frequency logging is one of the best-validated AI applications on the whole poster — it has a published head-to-head comparison against expert human logging.
Datarock Core (part of IMDEX) uses a neural network to detect and classify fractures directly from core photography.
The Carrapateena copper-gold mine study specifically validated this against expert geotechnical logging — a real deposit, real comparison, not a synthetic benchmark.
This is a “Yes” — the clearest example on the whole list of AI matching (not just approximating) expert human judgment in a specific geotechnical task.

TL;DR

Run core photography through Datarock Core’s neural-network fracture detection model to get automated fracture spacing/frequency logs that have been validated against expert human geotechnical logging in a real copper-gold mine study.

Geochemical Proxies

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

Key Takeaways

Geochemical proxies — patterns in multi-element data that stand in for the presence of mineralization — are one of the clearest “AI already works here” stories in exploration.
Platforms like VRIFY DORA, GeoVista AI, and OreFox train ML models on known-deposit geochemical signatures to generate prospectivity scores over new ground.
DORA has an independently-verified real-world win: it flagged the same high-grade gold discovery target at Southern Cross’s Sunday Creek project that the exploration team found on their own.
This is a “Yes” category — commercially deployed, not a research demo.

TL;DR

Train (or use a pre-trained) ML model on the geochemical signatures of known deposits, then run it over your project’s multi-element dataset to generate a prospectivity/anomaly map that prioritizes drill targets — platforms like VRIFY DORA do this out of the box.

Geophysics

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

Key Takeaways

The raw geophysics (magnetics, gravity, EM survey acquisition) is still classical, mature science — AI enters at the interpretation stage.
AI prospectivity-mapping platforms like VRIFY DORA fuse multiple geophysical layers with geochemistry and geology to rank exploration targets automatically.
DORA specifically uses a Random Forest model to assign a “prospectivity score” per grid cell after fusing ~24 derived rasters — it’s a real, deployed product, not a research prototype.
Competing platforms in this space include GeoVista AI and OreFox, which similarly apply ML to multi-dataset target generation.

TL;DR

Run your standard geophysics acquisition and processing as usual, then feed the processed grids into an AI prospectivity-mapping platform like VRIFY DORA or OreFox, which fuses them with geochemical and geological layers and ranks targets with a trained model instead of a geologist manually overlaying maps.

Handheld XRF

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

Key Takeaways

Field-portable XRF is mature hardware — Evident (formerly Olympus) Vanta Max and Bruker TITAN are the two names you’ll see everywhere.
The AI angle is onboard chemometric calibration and signal processing (e.g. Evident’s Axon technology), not a separate AI product you buy.
Vanta Max connects via Bluetooth/Wi-Fi to a cloud service (Evident Connect) and integrates directly with GIS and 3D mine-modeling software.
This is “Emerging” for AI relevance because the calibration intelligence is improving instrument-by-instrument, not because handheld XRF itself is new — it’s been standard exploration kit for over a decade.

TL;DR

Buy or rent a handheld XRF analyzer (Evident Vanta Max or Bruker TITAN), scan rock chips, drill core, or soil in the field, and let the instrument’s onboard chemometric/AI calibration return near-lab-grade elemental results in seconds — no separate software pipeline required.

Hyperspectral (Point or Scan)

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

Key Takeaways

Two flavors exist: handheld point spectrometers (fast, spot checks) and full-core imaging scanners (slow, exhaustive, image-based).
The core technology (VIS-NIR-SWIR reflectance spectroscopy) is mature and commercial; the “AI” part is mostly in the automated mineral-classification layer sitting on top of the raw spectra.
Malvern Panalytical’s ASD TerraSpec line handles the point-measurement use case; Corescan’s Hyperspectral Core Imager handles full-core scanning.
This is best treated as a data-acquisition layer, not a standalone AI product — the value shows up downstream in alteration and clay models.

TL;DR

Use a point spectrometer for quick field/spot mineral ID and a full-core hyperspectral scanner for systematic alteration mapping — then feed the spectra into a classification model to actually get AI value out of it.

Hyperspectral imaging / Spectroscopy Device

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

Key Takeaways

Portable VIS-SWIR spectrometers like the ASD TerraSpec Halo (Malvern Panalytical) identify minerals in the field or on core in seconds via spectral-library matching.
Note: as of this writing, the TerraSpec Halo itself is listed as no longer available to purchase from Malvern Panalytical — check current availability and successor products (TerraSpec 4) before specifying it for a new program.
SciAps also offers a field spectrometer line worth comparing.
The “AI” here is the spectral-matching engine comparing your field reading against a library of thousands of reference mineral spectra — genuinely ML-adjacent, but framed by vendors as spectral matching rather than a general AI model.

TL;DR

Point a portable VIS-NIR-SWIR spectrometer (ASD TerraSpec range, or a comparable current model) at a rock face, drill core, or hand sample, and its onboard spectral-library matching identifies the alteration minerals present in seconds — the same core logic that hyperspectral core-scanning platforms use, just handheld.

Informed Logging

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

Key Takeaways

“Informed” logging means the geologist (or AI system) logs new core with the benefit of prior geological/geophysical model context, not in isolation.
Datarock Core and Seequent Central’s logging module both support this by surfacing existing model context alongside new imagery.
This is a “Yes” — the underlying AI core-logging technology is production-proven; what’s new is using it context-aware rather than hole-by-hole in isolation.
The practical benefit: consistency across a drill program, since every hole gets logged against the same evolving model rather than each geologist’s independent read.

TL;DR

Pair an AI core-logging tool like Datarock Core with a centralized model platform like Seequent Central so that each new hole is logged with the benefit of everything already known about the deposit, rather than being interpreted in isolation.

LIBS

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

Key Takeaways

LIBS (Laser-Induced Breakdown Spectroscopy) detects light elements — lithium, boron, carbon, sodium, fluorine — that handheld XRF simply can’t see.
The SciAps Z-300/Z-903 is the standard handheld unit, covering the full periodic table from hydrogen to uranium.
No X-rays means no radiation licensing or travel restrictions — a real practical advantage over handheld XRF for field teams.
Primary copper-relevant use cases: lithium/REE exploration, gold pathfinder-element mapping, and total organic carbon detection (relevant for preg-robbing risk in gold-bearing systems).

TL;DR

Where handheld XRF can’t detect an element you care about (lithium, boron, carbon, sodium), reach for a handheld LIBS analyzer like the SciAps Z-300 — same field-portable form factor, different physics, and no radiation-license overhead.

Muon Tomography: AI-Powered Ore Body Imaging with REVEAL

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

Key Takeaways

This poster node maps to a real, deployed product: Ideon Technologies’ REVEAL platform.
Muon tomography uses naturally occurring cosmic-ray muons to build 3D subsurface density models — it can see through large volumes of rock that block conventional geophysics.
REVEAL is already running at Rio Tinto’s Kennecott (Bingham Canyon) copper mine, where it’s been used to refine geological models and reconcile production tonnages against the mining model.
A newer REVEAL variant does 4D monitoring of block-cave propagation, deployed at Evolution Mining’s Northparkes.

TL;DR

Deploy Ideon Technologies’ REVEAL muon detectors around your target zone; their AI-assisted inversion and interpretation pipeline turns the raw muon flux data into a 3D density model you can use to refine ore body geometry and reconcile grade/tonnage — this is a commercially deployed system at working copper mines today, not a lab concept.

Permitting

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

Key Takeaways

Environmental and social permitting is one of the slowest, most document-heavy parts of standing up a copper project — and it’s only now starting to see AI tooling.
The clearest fit is AI-assisted ESG/compliance reporting platforms (e.g. Ecodrisil ESG Xpress), which automate data collection and audit-ready disclosure rather than the legal judgment calls themselves.
This is an “Emerging” category on our tracker — there’s no dominant, mining-specific AI permitting product yet, so expect to assemble a workflow rather than buy one box.
AI’s real leverage here is turning scattered environmental, social, and hydrogeological monitoring data into structured, submission-ready documentation faster.

TL;DR

You don’t yet get an AI that files your permits for you — but you can use AI-powered ESG/compliance platforms to turn your monitoring data into audit-ready documentation much faster than manual reporting.

Petrography

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

Key Takeaways

Petrographic thin-section analysis (identifying minerals and textures under a microscope) is still overwhelmingly analyst-driven — there’s no single dominant commercial AI product yet.
Published CNN research is real and promising: concatenated convolutional neural network approaches have hit ~90% accuracy classifying rock type from plane- and cross-polarized thin-section images.
Treat this as an emerging, DIY-research capability rather than something you can buy and deploy this quarter.

TL;DR

AI-assisted petrography means training a convolutional neural network on your digitized thin-section images (plane- and cross-polarized light) to automate rock-type and mineral classification — technically proven in the literature, but not yet a packaged commercial tool.

Predicting Comminution Parameters (BWI, DWI, Ai) with Machine Learning

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

Key Takeaways

BWI (Bond Work Index), DWI (Drop Weight Index), and the Abrasion Index all still start from physical rock-breakage tests, run through JKTech’s JK Drop Weight Test / JKSimMet — the industry-standard equipment and simulation software.
2025 research validates cheaper proxies — hyperspectral imaging (HSI) and Leeb rebound hardness — predicted by ML models as low-cost stand-ins for full BWI testing.
A 2025 deep neural network approach (published in Minerals Engineering) predicts DWI/BWI from Geopyörä breakage test data trained across ~700 global ore samples, cutting lab turnaround time.
The Abrasion Index has no dedicated AI-native product yet — it rides on the same ML grindability-proxy research as BWI/DWI, making it the least mature of the three (Emerging).
None of this replaces physical testwork entirely — it reduces how many full tests you need across a deposit by predicting the rest from cheaper measurements.

TL;DR

Instead of running full Bond/drop-weight tests on every sample, run a cheap proxy measurement (hyperspectral scan or Leeb rebound hardness) on everything and a full physical test on a calibration subset, then train a regression model to predict BWI/DWI/Ai across the rest of the deposit.

Predicting Rock Strength (UCS) from Point Load Testing with AI

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

Key Takeaways

Uniaxial Compressive Strength (UCS) is the standard rock-strength measurement, but it’s a destructive, slow, sample-hungry lab test.
2025-2026 peer-reviewed studies (Nature Scientific Reports, Acta Geophysica) show ML models — SVM, Gaussian Process, ANN, XGBoost — predicting UCS directly from the much faster, cheaper Point Load Test (PLT) index with high R².
A more ambitious research direction predicts UCS continuously from measurement-while-drilling (MWD) data, Schmidt hammer readings, and P-wave velocity, with a Bayesian-optimized Random Forest reporting R²≈0.90.
This means you can potentially get a UCS estimate for every meter of every drill hole, not just the handful of intervals sent for destructive lab testing.
These are research-validated methods, not a single packaged commercial product — you’re building the regression yourself on your own PLT/UCS paired dataset.

TL;DR

Train a machine learning regressor (XGBoost, Random Forest, or Gaussian Process) on your paired PLT-index/UCS lab results, then apply it to predict UCS wherever you have PLT data (or even MWD drill data) but no destructive UCS test — turning a sparse, expensive strength dataset into a near-continuous one.

Quality Assurance and Quality Control

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

Key Takeaways

QA/QC monitoring — tracking lab standards, blanks, and duplicates for drift or contamination — is a natural home for statistical anomaly detection.
ALS QCPro and ioGAS’s QAQC modules are the standard tools, both now adding statistical/ML anomaly flagging.
This is an “Emerging” category: the underlying QC discipline is decades-old and well-standardized (ISO/IEC 17025), the ML layer on top is the new part.
The goal isn’t replacing QA/QC protocols — it’s catching drift or contamination faster than a human reviewing control charts manually would.

TL;DR

Use a platform like ALS QCPro or ioGAS’s QAQC module to track your standards/blanks/duplicates automatically, and lean on their newer statistical/ML anomaly-flagging features to catch lab drift or contamination issues faster than manual control-chart review.

Quick Geological Logging

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

Key Takeaways

First-pass (“quick”) geological logging — the initial lithology/alteration read on fresh core — is one of the more mature AI use cases in exploration.
Datarock Core and Seequent Central’s logging module both support AI-accelerated first-pass logging directly from core photography.
Datarock has processed over 30 million metres of core since 2020, turning what would be months of manual logging into hours.
This is a “Yes” — already deployed, production-grade AI, not a research prototype.

TL;DR

Feed high-resolution core photography into a tool like Datarock Core to get an automated first-pass lithology/structure log in hours instead of the days or weeks manual logging takes, then have your geologists review and refine rather than log from scratch.

Water Quality Test

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

Key Takeaways

There’s no dedicated, mining-specific AI product for water quality testing today — this is an honest gap, not an oversight.
Results still flow through standard lab LIMS platforms like LabWare.
General-purpose ML water-quality-index and anomaly-detection models exist in the broader environmental-monitoring literature, but they’re typically custom-built for a specific monitoring network rather than off-the-shelf.
If you want AI value here, expect to build (or commission) a bespoke anomaly-detection model on your own monitoring-network data — not buy a packaged tool.

TL;DR

Water quality testing itself still runs through standard lab LIMS workflows with no mining-specific AI product to plug in; if you want an AI layer, it’ll be a custom anomaly-detection model trained on your own monitoring-network time series, not an off-the-shelf purchase.

XRD

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

Key Takeaways

Classical XRD phase identification runs on Rietveld refinement — mature, accurate, but computationally slow, especially across large batches.
CNN-based deep-learning models can now identify and quantify mineral phases directly from raw XRD patterns, running orders of magnitude faster than classical Rietveld refinement (per 2024–2025 IUCr and Advanced Engineering Materials research).
Commercial (Malvern Panalytical HighScore, Bruker DIFFRAC.EVA) and open-source (Profex/BGMN, GSAS-II) Rietveld tools remain the production standard today.
Treat AI-based phase ID as emerging — worth piloting on high-throughput batches, not yet a wholesale replacement for validated Rietveld workflows.

TL;DR

Keep your core XRD phase-identification and quantification workflow on established Rietveld software (HighScore Plus, DIFFRAC.EVA, or the open-source Profex/BGMN and GSAS-II stack), and pilot CNN-based rapid phase-ID models on high-volume batches where waiting for full Rietveld refinement is the bottleneck.

XRF

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

Key Takeaways

Portable and lab-bench XRF remain the workhorse tool for rapid elemental analysis in exploration and grade control.
Leading instruments include Evident Vanta (handheld) and Bruker TITAN, plus lab-bench systems from Malvern Panalytical and Bruker.
The AI layer is “Emerging,” not built-in by default: chemometric/ML calibration models that improve accuracy on tricky matrices are increasingly available, but XRF hardware itself hasn’t fundamentally changed.
Field-portable XRF turns days-long lab turnaround into on-the-spot, if slightly less precise, elemental readings.

TL;DR

XRF hardware (handheld Vanta/TITAN units or lab-bench systems) gives you rapid elemental analysis; the AI upside comes from chemometric/ML calibration layered on top to correct for matrix effects and improve accuracy without needing a full lab digestion.