Practical Data Analytics and Machine Learning
Get more value from your operation through data analytics, machine learning, simulation and optimisation.
Quick facts
 Duration |
 Delivery |
 Course Type |
 Next Intake |
 PD Hours |
 Language |
20 hours
|
100% online |
Short course |
TBC 2024 |
Up to 20 |
English |
Course overview
With the resources sector committed to gaining more value from data collected across mining operations and the broader business, AusIMM’s Practical Data Analytics and Machine Learning short course is designed to share practical insight into the fundamentals of data analytics, machine learning, simulation and optimisation. Designed and delivered by industry experts, the program uses real world examples and hands-on access to industry leading tools. Participants will also learn about mechanisms for keeping data private whilst participating in collaborative projects for industry-wide learning.
Course pricing
Subscribe now for updates
Earn digital credentials
Showcase your studies, validate your knowledge
Verify your new skills and knowledge with a digital badge that you can add to your LinkedIn profile, email signature, intranet, or any other online account.
Your badge links to a detailed outline of the course, showcasing and validating your new skills in a format that employers and colleagues can easily access and trust.
Who should attend?
Plant Engineers and Operators
Learn how to use data to inform business-critical activities using data already available within the business.
Operational Improvement Specialists
Audit and analyse operations to inform business cases for change.
Senior Operations and Plant Management
Learn how to use your operation’s routinely collected data to understand historical performance and inform predictions with insights for practical improvements.
Learning objectives
- Recognise the key terminology used in Data Analytics (DA) and Machine Learning (ML)
- Identify potential applications for DA and ML in mining
- Describe the characteristics and applications of mining related measurements and interpolated data, i.e. variability, uncertainty and error and when to use mining related professional judgment
- Explain the difference between ML models and traditional models for equipment process models
- Describe good practices of ML
- Develop an ML model for a processing plant operation based on a Process Historian data sample
- Utilise an ML model in a mineral processing flowsheet simulator
- Develop an understanding of use cases for simulations of minerals processing using ML models
- Discuss when ML models should be retrained with more or different data
Course structure
The five-week course is a collaborative, hands-on online learning experience, taking learners approximately 20 hours to complete. Please note the live sessions are not mandatory, the virtual classrooms will be recorded and available on the same day for participants who are unable to attend the live event. Course content includes:
- Live virtual classrooms
- Additional resources and readings (case studies, videos, articles)
- Access to hands-on learning activities using Orica’s cloud-based software
- Group discussion forums
- Learning activities in the form of short test questions
Module 1
Module 2
Module 3
Module 4
Download the course brochure
Practical Data Analytics and Machine Learning
Facilitators
Greg Shapland
Greg brings over 25 years' experience in managing and implementing systems and process improvements using mining technologies, data analytics and IT systems.
He holds a B.E. Civil (Hons) and an M.B.A. in Strategy and Finance and is an accredited Project Management Professional.
Edwin Koh
Edwin joined the IES team in summer 2018/19 to investigate the feasibility of machine learning models for minerals processing. Following success with the IES summer vacation project Edwin decided to further his studies in this area towards a PhD at UQ under Prof Geoff McLachlan and Dr Eiman Amini. In his PhD, Edwin applies state-of-the-art machine learning models in the IES platform for industry using Tensorflow. These novel methodologies have been published in various journals and conferences, establishing IES at the forefront of utilising machine learning in the minerals processing.
Eiman Amini
Eiman has worked in several countries with extensive exposure to comminution and flotation process modelling, simulation, forecasting and optimisation. Eiman also has history of working effectively in cross-functional and cross-cultural environments with consistent success in research and innovation, coaching laboratory teams and process performance improvement in research intuitions and companies such as JKMRC, SGS and Rio Tinto.
Robert Watkins
He has 20 years of experience in the software development industry, working with companies such as Mincom, Suncorp and Wotif.com to develop high-performing software solutions.
As the development lead, Robert has overseen and supported the development of the ML capabilities within IES, including the integration of ML models into the IES platform.
Nick Beaton
Nick has professional experience that spans senior appointments with Datamine, Mincom, KPMG and CAE Mining, with postings to the UK, South Africa, Germany, the USA and Switzerland. In addition to his extensive mining industry experience, Nick also worked in management consultancy in Europe, leading pan-European projects in business restructuring and ERP implementations for major manufacturing companies.
Frequently asked questions
What are the technical requirements to participate in the course? i.e. do I need a webcam, microphone, etc?
The course will be run entirely online via a cloud-based Learning Management System (LMS) which can be accessed via computer, tablet or phone. Participants will simply need to have a working Internet connection and a computer, tablet or phone with sound to access the course.
Participants will require access to Microsoft Excel and some of its add-ons in order to complete one of the learning activities for Module 1. For other modules participants will be granted temporary access to Orica's cloud-based application.
How long will the course take?
The full course is estimated to take about 20 hours of learning. Participants will have access to the course platform for five weeks to complete all modules.
How often will the courses be run?
We aim to run two intakes each year.
Do I have to attend the live sessions?
No, all virtual classrooms are recorded and made available on the learning platform for participants who are unable to attend the live session.
Will the course be delivered in other languages?
At the moment, no, but we will be looking at delivering the course in other languages in the near future.
How many PD hours do I receive for undertaking the course?
Participants can earn professional development (PD) hours for undertaking the course. One contact hour of technical content is equivalent to one PD hour.