Beverly is a MASc student at the University of British Columbia studying the feasibility of integrating machine learning techniques with rock engineering design under the supervision of Dr. Davide Elmo (UBC) and Dr. Doug Stead (SFU). She received her Bachelor of Applied Science in Geological Engineering from the University Waterloo, where she worked at Golder Associates Ltd. (now a member of WSP) as a co-op student in both their Geotechnical Engineering group and Mine Stability West group. During her last co-op term, she received an NSERC USRA to work with Prof. Davide Elmo, where she used discrete fracture network modelling to examine rock quality designation and its implications in rock engineering design. The results of this work are summarized in a paper that was accepted for publication in the ARMA 2020 conference proceedings. In her spare time, she enjoys reading, running, and baking.
Project: Examining the Feasibility of Integrating Machine Learning Techniques in Rock Engineering Design
The past decade has seen an increased interest in the application of machine learning to mining and geotechnical engineering in the mineral resources development sector. However, given the challenging nature of designing in rock and the empirical approach to design, the question then arises as to whether machine learning is applicable to geotechnical engineering design at this time. The main goals of this research are:
- Examining the feasibility of integrating machine learning in geotechnical engineering design, with an emphasis on the rock mass characterization and classification systems; and
- Examining the readiness of the technical community to adopt a paradigm shift in the data collection process.
The outcomes of this research will benefit the mineral resources sector in BC by improving the efficiency of the exploration and design process and improving the accuracy of the design. Ultimately, this will result in improved sustainability during mineral exploration and mine design.