Machine learning approach to monitoring and decarbonizing mineral processes

Within Canada’s commitment to the 2030 Agenda for Sustainable Development, a pivotal goal involves taking immediate action to combat climate change and its far-reaching effects. The specified target is a 40% to 45% reduction in the country’s total greenhouse gas (GHG) emissions below 2005 levels by 2030. To transition away from fossil fuels and embrace renewable energy sources, a strategic combination of solar and wind power,
coupled with energy storage solutions like lithium-ion batteries, emerges as a transformative approach.
While this renewable energy transition holds immense promise for long-term carbon emissions reduction, it is imperative to address and mitigate the environmental impacts associated with the production of these batteries. The proposed research seeks to refine mineral processing activities by leveraging machine learning, aiming to decrease carbon emissions significantly. The focus is on developing a versatile machine learning model designed to optimize energy consumption in processing plants, thereby bolstering the production of essential minerals for lithium-ion batteries in Canada. This innovative strategy not only aligns with the nation’s commitment to GHG reduction targets but also underscores a commitment to sustainable practices in resource extraction.

Faculty Supervisor:

Yuksel Asli Sari

Student:

Partner:

Emily Thorn Corthay Inc.

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

Queen's University

Program: