Formation evaluation
Get a faster first read on rock and mineral composition, ahead of a full core-analysis program.
Composition and imaging data already exist for a sample — an automated first pass tells you what's worth a full manual workup, before that workup is scheduled.
Contact temporarily paused — finalizing data-handling registration.
Business impact
Don't wait on a full manual analysis cycle to learn a formation assumption was off.
Physical core analysis, XRD, and SEM-EDS work are accurate, but a full manual analysis cycle is slow and gets committed the moment it's scheduled. An automated computational pass on the same composition and imaging data ahead of that commitment catches a wrong formation assumption early, while it's still a modeling correction rather than a re-run lab program.
- Formation assumptions checked before, not after, a full manual analysis cycle is scheduled
- A mineralogy assumption checked before it drives lab scheduling, not after
- A faster automated first pass on composition and imaging data already on hand
How we get you there
Digital rock and mineralogical characterization — computed from composition
Rock and mineral properties are characterized computationally: pore-scale structure, modal mineralogy, and mineralogical/compositional analysis — an automated analysis layer on the composition and imaging data you already have, not a replacement for the physical instrument run that produces it.
Digital rock characterization
Pore-scale structure and porosity, characterized from segmented micro-CT pore geometry; permeability computed by pore-network flow simulation on that same geometry, not from composition.
Modal mineralogy
Automated mineral-phase identification from compositional data — a faster first read than a manual point-count.
Mineralogical & compositional analysis
Structural and compositional characterization cross-checked against named mineral references.
Computational analysis of rock and mineral composition and structure — not molecular-dynamics simulation, and not a field-scale reservoir-performance prediction.
In the published literature
Published reservoir-quality studies have used automated modal-mineralogy and digital-rock-characterization workflows — combining imaging, compositional analysis, and porosity/permeability measurement — to identify which sedimentary and diagenetic factors control reservoir quality in a given formation, ahead of a full manual core-analysis program.
Alqubalee, A., Babalola, L.O., Abdullatif, O., Makkawi, M., "Factors Controlling Reservoir Quality of a Paleozoic Tight Sandstone, Rub' al Khali Basin, Saudi Arabia," Arabian Journal for Science and Engineering, Vol. 44, Issue 7 (2019)
Where this fits
An automated analysis layer, not a lab replacement
This is an automated computational pass on the same composition and imaging data a physical core-analysis, XRD, or SEM-EDS program produces — it doesn't replace the physical sample or the instrument run that generates that data. The point is a faster first read on what that data already shows, while it's still cheap to correct a wrong assumption.
Cross-check your formation assumptions before you commit a core-analysis program.
Contact temporarily paused — finalizing data-handling registration.