We help mining companies assess the value of sensor-based ore sorting in their operations. 
Considering a new ore sorting technology or evaluating an existing installation? Put our decades of research, consulting and practical experience in ore sorting to work for you.


We consider four pillars of ore sortability, or ore sorting amenability, to help you make a confident, data-driven decision about using ore sorting technology in your operation:
  1. Presence of ore grade heterogeneity,
  2. Availability of ore-specific sensors,
  3. Suitability of sensing system configurations
  4.  Positive economic outlook.
We use your resource data, operational data, and orebody knowledge to quantify the four pillars or sortability in your project using OreSlicer5D, our in-house software. OreSlicer5D was developed organically over time by listening to our clients and seeking the best answers about how to apply ore sorting technology in a project.


 Our services are based on the four pillars of ore sortability to support the evaluation and implementation of sensor-based sorting systems, including:

Project screening. High-level assessment of available project data to identify and rank the potential to apply ore sorting of one or more projects based on ore grade heterogeneity and ore sorter mass balance simulation. Bench-marking against similar deposit types.

Mine plan ore sorting simulation. Predicted impact of ore sorting technology on mine plan (monthly or annual basis) in terms of mass pull, metal recovery, and grade.

Ore sorting roadmap. Predicted impact of ore sorting technology on mine plan (monthly or annual basis) in terms of mass pull, metal recovery, and grade.

Test work programs. Co-ordination of test-work by third-party vendors and metallurgical labs. Incorporation of test results into the block model using OreSlicer5D.

Evaluation of sensor-based sorting installations. QA/QC of sensor data and directing sampling campaigns.

Sensor evaluation. Assessment of the expected response of single or multi-elemental sensors to your ore. We use your assay data with machine learning to predict the ability of multi-elemental sensors to classify your ore.


Stefan Nadolski
Ph.D. (Mining Eng.), P.Eng. Stefan Nadolski
Bern Klein
Ph.D. (Mining Eng.), P.Eng. Bern Klein
Ryan MacIver
Ph.D. (Mining Eng.) Ryan MacIver



    +1 604 307 7940


    Vancouver, British Columbia