Key Takeaways

  • Sensor-based ore sorting is a mature, high-adoption category — TOMRA and Steinert together hold over 40% of the market.
  • The “AI” is in the real-time classification logic that decides, particle-by-particle, whether a rock is ore or waste based on sensor signal — this has moved well beyond simple threshold rules.
  • TOMRA’s AI-powered advancements (OBTAIN, CONTAIN) specifically target throughput (doubling sorting capacity) and fine inclusion-detection for base metal sulphides including copper.
  • This is a bulk pre-concentration step — sorting waste out before it reaches the mill — which cuts downstream energy, water, and tailings volume, not just a grade-control tool.

TL;DR

Adopting AI-driven ore sorting means installing a sensor-based sorter — TOMRA or Steinert KSS are the two dominant vendors — ahead of your mill, where AI classification software decides in real time which rocks to keep and which to reject.

How Do I Automate Ore Sorting With AI?

Ore sorting works by passing crushed material past a sensor array (most commonly X-ray transmission, XRT) that images the internal composition of each particle, then using classification software to decide instantly whether each piece is ore or waste and trigger a mechanical ejector accordingly. The “AI” component is this classification layer: rather than a simple density or brightness threshold, modern systems use learned models trained on labeled particle data to handle the messier, more ambiguous cases — fine-grained inclusions, mixed particles, ore types with subtle signal differences from waste rock.

TOMRA, which along with Steinert holds the majority of the sensor-sorting market, has pushed specifically into AI-powered capability with two named features worth knowing: OBTAIN, which can roughly double sorting capacity by speeding up the classification decision, and CONTAIN, aimed at detecting inclusion-type ores — explicitly including copper and other base-metal sulphides — where the valuable mineral is present as fine inclusions rather than a uniform composition. This matters for copper operations specifically because copper sulphide mineralization is often exactly this kind of fine-inclusion case that’s hard to sort with simpler sensor logic.

The business case is usually framed as pre-concentration: by rejecting barren waste rock before it reaches the crusher and mill, you cut the tonnage that needs grinding, the energy and water consumed doing it, and the tailings volume produced — which is a materially different value proposition than grade-control sensing further down the line (see Belt Sense / Shovel Sense). A typical adoption path is a test-center trial (TOMRA runs dedicated test centers for exactly this) using representative ore samples from your deposit, since sortability varies significantly by ore type and mineralization style.

Try It With Geocluster

Whether ore sorting makes sense for your specific deposit depends heavily on ore type, mineralization style, and grade distribution — the kind of deposit-specific evaluation Geocluster is designed to help you work through before committing to a vendor trial.