BCGS Technical Talk – August 12, 2019
Speaker: Professor Eun-Jung Holden, University of Western Australia
Title: Developing Data Science Applications in Geosciences: An End-User Focused Approach
Date/Time: Monday, August 12, 2019 @ 4:30pm PST
Location: 4th Floor Conference Room, Room 451, 409 Granville St. (UK Building at Granville and Hastings), Vancouver
Developing Data Science Applications in Geosciences: An End-User Focused Approach
Professor Eun-Jung Holden, Geodata Algorithms Team, UWA
Understanding complex subsurface geology is a challenging task where interpretations are performed using diverse types of geoscientific data. The Geodata Algorithms Team at UWA has been working closely with the minerals industry for the past 12 years and developed machine-assisted solutions to improve the efficiency and the robustness of geological interpretation. This talk will present a number of applications of automated image analysis and machine learning, which were developed by the team in recent years in partnership with mining companies. They include drillhole data analysis and integration methods which are currently used by industry end-users; on-going research on advanced drillhole data visualisation and interpolation methods; and on-going development a geological knowledge mining system for exploration reports using text mining.
Professor Holden received her BSc, MSc and PhD in computer science from the University of Western Australia. Her postgraduate and postdoctoral research focused on developing visualization, automated image analysis and machine learning techniques for hand gesture recognition. Then in 2006, she made a transition to geoscience and now leads the Geodata Algorithms Team at UWA. The team effectively spans the boundaries of computational science and geoscience and links academia and industry. Three suites of their data analytics algorithms were commercialized, namely CET Grid Analysis and CET Porphyry Detection extensions for Geosoft’s Oasis Montaj; and Image Structure and Interpretation module for Advanced Logic Technology (ALT)’s WellCAD, which are marketed and licensed by Geosoft (based in Canada) and ALT (based in Luxembourg) respectively. She is currently leading the UWA-Rio Tinto Iron Ore data fusion projects which aim to achieve machine-assisted modelling of geology/resource through transformational and interpretive data science solutions. Her research team won the UWA Vice Chancellor Award in Impact and Innovation in 2015.