Join CSA Global Technical Director, Dr Pim van Geffen and Principal Consultant, Geostatistician Samer Hmoud, including speakers from McGill University, ALS Goldspot Discoveries Ltd, and Life Cycle Geo when they present at the CIM MTL23 Convention between April 30-1 May 2023 on an Introduction to Machine Learning and its Application across the Mine Project Life Cycle.
The annual CIM Convention is a line-up of expertly-led short courses, 3 full days of technical presentations divided into different and innovative themes, great networking opportunities, a complete student / young leaders program, and a world-renowned trade show.
The CIM EXPO, Canada’s premier mining trade show, features hundreds of companies showcasing the latest in mining equipment, tools, technology, services and products.
About the workshop
This one day introductory workshop is designed for professionals working in all stages of the mine project life cycle. Participants will be introduced to machine learning methods that can be applied to exploration, mine to mill optimization, and environmental planning. Practical demonstrations using python and/or Orange will be performed using mostly geochemical datasets.
Date
Sunday 30 April | 9.00am to 4.30pm
Where
Room 510A
Morning session
Practical application of machine learning across the mine project life cycle will be featured. Case studies will emphasize methodology, pitfalls to consider, challenges and successes of employing advanced methods.
- 9:00-9:15 Introduction
- 9:15-10:00 Machine learning: Exploration Applications (Britt Bluemel)
- 10:00-10:15 Coffee break
- 10:15-11:00 Machine learning Geometallurgical Applications (Pim van Geffen)
- 11:00-11:45 Machine learning Environmental Applications (Tom Meuzelaar)
- 11:45-12:00 Q&A
Afternoon session:
Data management and machine learning concepts will be introduced at a high-level and framed within the context of the mine project life cycle. The workshop will highlight techniques that help improve accuracy and efficiency of algorithms and/or workflows including best practices. Practical exercises will use either python in Google Colab environment.
Topics covered
- Introduction to Statistics – emphasis on compositional datasets
- Introduction to Machine learning – Supervised and Unsupervised
- Dimensionality reduction
- Decision Trees
- Algorithms – Clustering/Regression/Classification
- Model evaluations – Feature engineering, model metrics
The session will end with a panel Q&A with all the presenters of the short course.
Short Course Objectives
To provide participants with hands on examples of employing machine learning techniques across a mine project life cycle.
Target Audience
Mining professionals working in all stages of the mine project life cycle and students.
Dr Pim van Geffen
Technical Director
Pim is a professional geoscientist with more than 15 years’ experience in mineral exploration and mining across the globe. He is a leader in the fields of geochemistry and geometallurgy in the Americas and is passionate about innovation and improved business practice in the sector. Across exploration to operations, closure and remediation, Pim focuses on rock-property data integration and process optimization throughout the mining value chain. He sees tremendous potential value in unlocking hidden information through geoscientific data gathered and not used to its full potential to characterize ore and waste, minimize operational risk, and maximize return. Pim has been a significant contributor across the industry; having delivered a plethora of public short courses and conference talks on geochemical data analysis and its geomet applications. He has provided in-house training to mining companies and academic institutions on ioGAS software, portable X-ray fluorescence analysis and infrared reflectance spectroscopy, and has served as a guest lecturer at the University of British Columbia and Queen’s University.
Samer Hmoud
Principal Consultant, Geostatistician
Samer has 10 years experience as a resource geologist and geostatistician, exploration geologist, and hydrogeologist. He is a specialist in application of advanced geostatistics to Mineral Resource estimation and has experience with a wide range of deposit types. Samer is skilled in identifying the right estimation strategy and potential issues of concern for each project and has extensive experience with non-linear geostatistics and conditional simulations for resource estimation, model validation, risk analysis, multivariate geostatistical modeling, and drillhole spacing studies. He has deep understanding of the transition from resources to reserves and the need to tailor resource estimation to this purpose, and in his current PhD study is assessing the implications of blast movement on dig limit optimization under geological uncertainty in open pit mines. Samer also has expertise in applying machine learning techniques to geology and resource estimation.