Virtual Forum Series: Artificial Intelligence

April 15th 2021 (8:00am-10:30am EDT, 1:00pm-3:00pm CET, 8:00pm-10:30pm AWST)

The mining industry is increasing its use of AI to optimize processes, enhance decision-making, derive value from data, and improve safety. While there are many benefits to its implementation, it is still very new and there is a lot of work that needs to go into successful application. Planning, research, communication, and change management are all essential foundations for implementation.

Industry collaboration is essential in order to communicate the advantages of AI, as well as to establish best practices for moving forward with AI technology. During this virtual forum, the industry will come together to collaborate on the future of AI, hear from leading experts in the industry, as well as contribute input to ongoing GMG projects within the Artificial Intelligence working group.

To get involved, click “register”.


Artificial intelligence for self-learning mining complexes – mineral value chains: Concepts, advances, examples and challenges
Roussos Dimitrakopoulos, Professor and Canada Research Chair (Tier I) in Sustainable Mineral Resource Development and Optimization under Uncertainty

New digital technologies have enabled mining complexes to acquire new information on the performance of its different components and the flow of materials from mines to products. At the same time, existing complementary technologies cannot fully integrate such emerging digital information to adapt short-term production planning. A new self-learning artificial intelligence framework for a mining complex that learns, from its own experience, to adapt short-term production scheduling decisions by responding to incoming new information and quantifying related risk is presented. After providing context, several approaches are overviewed starting with early experiments based on the AlphaGo program from Google DeepMind, which is rewritten to continuously learn and adapt short-term production schedules. This is followed by feeding uncertainty models to a neural network that is trained using a policy gradient reinforcement learning algorithm to adapt the short-term flow of materials from mines to processing facilities in a mining complex. Lastly, an Actor-Critic reinforcement learning approach that jointly adapts short-term production scheduling, equipment allocation and material destination policies based on new incoming real-time information is presented. Aspects of the self-learning framework are demonstrated using examples from a copper-gold mining complex composed of two pits and multiple processing stream options.

About Roussos: Roussos Dimitrakopoulos is a professor of the Department of Mining and Materials Engineering at McGill University. He holds a Canada Research Chair (Tier I) in Sustainable Mineral Resource Development and Optimization under Uncertainty, and is director of the COSMO – Stochastic Mine Planning Laboratory ( Roussos holds a PhD from École Polytechnique de Montréal, and an MSc from the University of Alberta in Edmonton. He is also a member of GERAD – Groupe d’Études et de Recherche en Analyse des Décisions. He works on stochastic simulation and optimization as well as artificial intelligence applications in mine planning and production scheduling, along with the simultaneous optimization of industrial mining complexes and mineral value chains under uncertainty. He has published extensively, maintaining large competitive grants from the National Science and Engineering Research Council of Canada and a long-standing partnership with AngloGold Ashanti, BHP, De Beers/AngloAmerican, IAMGOLD, Kinross Gold, Newmont and Vale (COSMO Consortium) who support this research. He has taught and worked in Australia, North America, South America, Europe, the Middle East, South Africa and Japan.


Ethics in AI for Mining Industry
Abhishek Kaul, Industry Analytics Lead, IBM

AI holds great power to solve some of the most difficult and complicated mining industry problems. Although AI is delivering results, its recommendations for people-based decisions are subject to ethical considerations. As seen in the industry if AI is not ethical, companies are exposed to reputational, legal and regulatory risk. Globally, there is no commonly accepted guideline on AI in Ethics. Many technology companies, governments, multi-stakeholder organizations have published guidelines, however, adoption is voluntary. In the mining industry, many guidelines focus on sustainability and ethical code of conduct. However, as more and more AI applications get deployed in the mining industry, there needs to be a focus on defining the ethical guidelines for AI. Common themes / ethical principles emerging globally are – Transparency; Justice, fairness & equity, Non-maleficence, Responsibility & accountability and Privacy. This talk will share practical examples for ethical consideration in mining industry AI use cases from Operations, Maintenace and Safety.

About Abhishek: Abhishek Kaul is the Industry Analytics Lead at IBM Singapore. In his current role, he works closely with C-Suite Executives to advise them on AI strategy and helps them address business challenges, increase revenue, productivity and reduce cost. His recent engagements include developing intelligence products on commodity trade flows, prediction of equipment failure, optimization of maintenance/energy costs, and enhancing people safety using computer vision. Before joining the Data Analytics and AI vertical in IBM, he was the Industrial Products industry expert and served industry clients across 18 countries in designing, implementing solutions across process, technology consulting engagements. As a thought leader Abhishek has published more than 25 papers and presented in multiple international conferences in the areas of AI, data analytics, machine learning, IOT, Big data, supply chain & process reengineering. Abhishek has received MBA in Operations and Systems from IIT Kharagpur, India; received Bachelor of Engineering from Pune University, India. He is certified in CPIM (Certified in Production & Inventory Management) –APICS, USA and Stanford LEAD Certificate program in Corporate Innovation, Stanford USA.