The Predictive Geometallurgy Research Group

Ore bodies are variable in nature, and their locations can only be accessed through sampling, leading to uncertainty about their properties. The rapid development of artificial intelligence, however, presents an opportunity for the minerals industry by significantly improving the performance of mining projects through the reduction of resource consumption (water, energy, equipment, and labour), thereby improving mining sustainability (see Figure 1). Machine learning is being incorporated into Earth science problems, but it is not yet fully integrated into the geometallurgical workflows that model and optimize the performance of physical and chemical processes involved in the extraction (mining) and recovery (mineral processing and metallurgy) of minerals and metals. As well, deep learning is rapidly developing, but has not yet been explored in the mining field. In times of increasing water and energy scarcity, this research provides a unique and novel approach to significantly impact the decision-making processes in mining by offering systems workflows that predict and optimize the mining, mineral processing, and metallurgical processes.