Challenges of integrating machine learning in rock engineering design

There is an increasing interest in applications of machine learning to solve mining and geotechnical problems; this is made easier thanks to user-friendly and open source machine learning codes and improved computational power. The benefit of incorporating machine learning in rock engineering design are apparent, including the reduction in the time required to sort and characterize field data and the capability to find mathematical correlations between complex sets of input data. However, there are challenges to be investigated, including the use of qualitative data. This project investigates the readiness of the technical community to integrate machine learning in rock engineering design at this time. To fully realize the potential and benefits of machine learning tools, the technical community must be willing to accept a paradigm shift in the data collection process and, if required, abandon or improve on empirical systems that are considered ‘industry standards’ by virtue of being commonly accepted despite acknowledging their limitations.

Faculty Supervisor:

Davide Elmo

Student:

Beverly Yang

Partner:

Golder Associates

Discipline:

Engineering

Sector:

University:

University of British Columbia

Program: