Training Programmes
Professional courses and executive masterclasses in AI for geosciences, AI for metallurgists, AI for geometallurgists, mineral resource estimation, geostatistics, prospectivity mapping and metal accounting.
Training that builds capability, not only awareness.
Courses can be delivered as one-day executive masterclasses, two-day professional short courses, three- to five-day technical bootcamps, online live courses, in-house corporate training or dataset-based implementation workshops.
Open each course for details.
The accordion sections can later become standalone course pages with agendas, prerequisites, fees and booking forms.
Who should attend: Exploration geologists, mine geologists, resource geologists, GIS analysts, geochemists, remote-sensing specialists and technical leaders.
What the course covers
- Machine learning concepts for geoscientists
- Data quality, bias and uncertainty in geological datasets
- Geochemical anomaly detection
- Mineral prospectivity mapping
- Remote sensing and spectral data workflows
- Explainable AI and model validation
- Hands-on Python demonstrations
Outcome: Participants learn how to design, evaluate and communicate AI workflows that remain geologically meaningful.
Who should attend: Metallurgists, process engineers, plant superintendents, laboratory managers, consultants and postgraduate students.
What the course covers
- Plant and testwork data preparation
- Regression and classification for recovery, grade and throughput
- Experimental design and optimisation
- Process monitoring and anomaly detection
- Model interpretation for plant decisions
- Python examples for flotation, leaching and comminution
Outcome: Participants learn practical AI and statistical workflows for plant diagnostics, testwork interpretation and process optimisation.
Who should attend: Geometallurgists, resource geologists, metallurgists, mineralogists, mine planners and technical managers.
What the course covers
- Building geometallurgical datasets
- Linking geology, mineralogy and processing response
- Ore-domain and process-domain design
- Predictive modelling of recovery and throughput
- Geometallurgical block-model attributes
- Uncertainty, variability and plant feedback loops
Outcome: Participants learn how to turn orebody knowledge into practical models for planning, processing and value management.
Who should attend: Resource geologists, exploration geologists, mine geologists, mineral-resource managers, mining engineers and consultants.
What the course covers
- QAQC, compositing, capping and support
- Geological domaining and estimation domains
- EDA, variography and spatial continuity
- Kriging and alternative estimation methods
- Block-model validation and classification
- Reconciliation and uncertainty
Outcome: Participants gain a step-by-step understanding of mineral-resource estimation and model defensibility.
Who should attend: Geologists, engineers, metallurgists, data scientists and technical professionals working with spatial data.
What the course covers
- Spatial data concepts
- Change of support and declustering
- Variograms and covariance
- Estimation versus simulation
- Kriging concepts
- Uncertainty visualisation
- Spreadsheet and Python exercises
Outcome: Participants learn geostatistics as a practical decision-support discipline rather than a purely mathematical subject.
Who should attend: Exploration teams, GIS specialists, geochemists, structural geologists, remote-sensing analysts and exploration managers.
What the course covers
- Mineral systems thinking
- Predictor maps and evidence layers
- Spatial feature engineering
- Knowledge-driven and data-driven prospectivity methods
- Target ranking and uncertainty
- Communication of targets to decision-makers
Outcome: Participants learn how to move from scattered datasets to transparent, ranked and defensible exploration targets.
Who should attend: Metallurgists, metal accountants, plant managers, mine technical teams, financial controllers and audit/risk teams.
What the course covers
- Metal-accounting principles and governance
- Sampling, measurement and mass-balance logic
- Mine-to-plant and plant-to-product reconciliation
- Common sources of metal loss and reporting error
- Audit trails, controls and month-end adjustments
- Improvement roadmap design
Outcome: Participants learn how to evaluate and improve metal-accounting systems, reconciliation controls and reporting confidence.
Who should attend: Executives, technical managers, innovation teams, digital-transformation leads, regulators and boards.
What the course covers
- Where AI creates value in mining
- Where AI creates risk
- Data and model governance
- Human-in-the-loop decision-making
- Explainability, auditability and procurement
- Implementation roadmap design
Outcome: Participants leave with a practical executive framework for adopting AI without losing technical accountability.