Key Takeaways

  • Textural analysis, grain size analysis, and mineral mapping run on the same automated-mineralogy and hyperspectral imaging stack: TESCAN TIMA, Zeiss Mineralogic, and Corescan for core-scale hyperspectral work.
  • These platforms increasingly use CNN-based classifiers rather than fixed spectral lookup tables to resolve grain boundaries and mixed-pixel mineralogy.
  • Output feeds two downstream uses directly: comminution/liberation modeling (how finely you need to grind to liberate value minerals) and geometallurgical domaining.
  • This is a mature, commercially deployed capability (ai_relevant: Yes across all three) — not a research prototype.
  • Malvern Panalytical’s Morphologi line is a relevant alternative specifically for particle-scale grain-size distribution work outside the SEM-based platforms.

TL;DR

Run polished samples or drill core through an automated SEM mineralogy platform (TIMA, Mineralogic) or hyperspectral core scanner (Corescan) to get quantitative texture, grain-size, and mineral-map data with built-in ML-based classification, rather than manual petrographic description.

How Do I Analyze Ore Texture, Grain Size and Mineral Mapping With AI?

Textural analysis, grain size analysis, and mineral mapping are three views of the same underlying image data, which is why they run on the same instrument stack rather than needing separate tools. TESCAN TIMA and Zeiss Mineralogic are the primary automated-SEM platforms: they raster an electron beam across a polished mount, collect an EDS spectrum at each point, and classify the mineral phase — the same underlying data that produces mineral maps also produces grain-boundary segmentation (for grain size) and textural relationships (intergrowth, alteration halos, mineral association patterns).

What makes this “AI” rather than just automated imaging is the classification step: modern platforms use trained neural-network classifiers to resolve ambiguous or mixed-pixel spectra — a grain boundary where the electron beam catches two minerals at once, for instance — more reliably than the fixed spectral lookup tables older systems relied on. Mineralogic explicitly markets this as deep-learning-based classification, and it matters most in fine-grained or texturally complex ore where manual point-counting would either miss detail or take prohibitively long.

For core-scale rather than polished-mount-scale work, Corescan’s hyperspectral imaging line scans whole drill core directly, extracting mineralogical and textural information from reflectance spectra without needing to cut and mount samples — useful for rapid, non-destructive screening across a whole hole before deciding which intervals warrant detailed SEM mineralogy. Malvern Panalytical’s Morphologi instruments are a relevant complement specifically for particle-scale grain size distribution work (useful downstream of crushing/grinding, where you’re characterizing product size rather than in-situ ore texture).

The practical payoff of all three: grain size and liberation data tell you how finely you need to grind ore to expose value minerals for flotation (directly informing comminution circuit design), while textural and mineral-map data feed geometallurgical domaining — grouping the deposit into zones with similar processing behavior. This is a mature capability across the board; you’re choosing between well-established commercial instruments, not evaluating unproven technology.

Try It With Geocluster

The real work is connecting texture/grain-size/mineral-map results back to your block model and geometallurgical domains so they inform actual mine planning decisions — exactly the kind of cross-dataset research Geocluster is built to support. If you’re building geometallurgical domains from automated mineralogy data, Geocluster can help connect the pieces.