Data Analytics to Aid Decision Making in the Mining Industry

Machine learning (ML) has become an indispensable tool in the mining industry, significantly enhancing operational efficiency, ensuring safety, and optimizing resource management. Its ability to process and analyze large datasets is pivotal in facilitating informed decision-making and reducing operational costs. This project leverages data analytics to augment mining operations planning, with two primary objectives:
1. Optimal Drilling Locations in Greenfield Exploration: The project aims to identify the most promising sites for drilling bore holes in unexplored (greenfield) areas, as well as predicting the viability of the nearby location using data from existing (brownfield) mines. By analyzing the geological data of current mines, ML algorithms can predict potential mineral deposits in nearby areas. This not only streamlines exploration efforts but also increases the chances of discovering viable mining sites, thereby reducing financial and environmental risks associated with exploratory drilling.
2. Predicting Economic Value of Current Mines: Another crucial aspect of this project is to predict the economic potential of operational mines based on historical data. By analyzing past performance, geological data, and market trends, ML models can forecast the future profitability of a mine. This prediction aids in strategic planning, resource allocation, and investment decisions.

Faculty Supervisor:

John Braun

Student:

Partner:

Genesis AI Corporation

Discipline:

Computer science

Sector:

Mining; Forestry; Natural Resources

University:

The University of British Columbia - Okanagan

Program: