Key Takeaways
- “Informed” core logging means the geologist (or AI system) logs new core with the benefit of prior geological and 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 is consistency across a drill program, since every hole gets logged against the same evolving model rather than each geologist’s independent read.
TL;DR
For informed core logging with AI, let a tool like Datarock Core produce a standardized first-pass log from core photos. Then review that log inside a shared model platform like Seequent Central, with the current 3D model and earlier holes on screen. Each new hole is interpreted against everything already known, not in isolation.
What Is Informed Core Logging?
Core logging is the systematic description of drill core: rock type, alteration, mineralization, structure and geotechnical properties, recorded metre by metre. It is the primary geological dataset behind every model and resource estimate.
Informed logging solves a subtle but important problem. A geologist logging hole 40 of a drill program should ideally have holes 1 to 39 and the evolving geological model in front of them. In practice, however, logging often happens hole by hole and shift by shift, with limited time to cross-reference prior results. That’s how inconsistency creeps into a logging dataset over a long campaign. Different geologists may also call the same unit by different names, weeks or months apart.
How Do I Improve Core Logging With AI?
The workflow has three layers: an automated first pass, a shared model, and a review step that brings them together.
Automate the first-pass core logging
Datarock Core’s AI logging extracts geological and geotechnical features directly from core photography. It reads rock type, structure and fracture frequency as a standardized first pass. Unlike manual logging, that read doesn’t degrade in consistency over a long, multi-geologist program. High-quality images matter here, so a disciplined core photography routine is the foundation.
Keep the model in view
Next, layer the output on top of Seequent Central. Central keeps the evolving 3D geological model, prior logging and drillhole data centralized and visible to the whole team. That gives you the “informed” part: new core gets logged with the model in view, not blind.
Review AI core logging against context
In practice, core photography flows into Datarock for automated first-pass logging. That output lands in Central alongside the existing geological model. Geologists then review and adjust the AI log with the broader model context on screen, rather than working from a printed log sheet at the core shed.
The result is a logging dataset that’s both faster to produce and more internally consistent across a long drill program. That matters a lot when different geologists log different holes weeks or months apart.
How Informed Logging Connects to the Deposit Model
Informed logging is a feedback loop. Consistent logs make a better geological model. In turn, a better model gives more useful context for the next hole. Over a campaign, that loop tightens the interpretation faster than hole-by-hole logging can.
This is also where it differs from quick geological logging, which focuses on speed at the rig. Informed logging focuses on consistency with the model. The consistent logs then feed AI-assisted implicit geological modelling, which builds lithology, structure and alteration volumes directly from drillhole data.
However, context can also bias. A geologist who sees the model may log what the model predicts rather than what the core shows. Therefore, treat unexpected intervals as signals worth checking, not errors to smooth away.
FAQs
What is the difference between informed and standard core logging?
Standard core logging describes each hole largely on its own. Informed core logging puts the current geological model and earlier holes in front of the geologist while they log. The goal is consistent interpretation across the whole drill program.
Which tools support informed core logging?
Datarock Core provides AI-generated first-pass logs from core imagery. Seequent Central keeps the geological model, prior logs and drillhole data in one shared place. Together they let geologists review new logs with the model in view.
Does AI replace the geologist in core logging?
No. AI produces a standardized first draft of features like rock type and fracture frequency. Geologists still review, correct and interpret that log. The main gain is consistency and speed, not removing expert judgement.
Can showing the model bias the logging?
Yes, it can. A geologist may lean toward what the model already predicts. Good practice is to log what the core shows and flag disagreements with the model, because those are often where the interpretation needs updating.
Try It With Geocluster
Keeping the context behind informed logging up to date is a research-synthesis task in its own right. It covers the latest interpretation, comparable deposits and relevant literature. Geocluster is built to help geoscience teams pull that context together quickly.
