Rio Tinto has thrown its weight behind a multi-million-dollar research partnership with the University of Western Australia to explore AI-based solutions for automating labour-intensive geology logging activity.
More than A$6 million is expected to be spent over four years on the project, which will engage five research staff full-time. The researchers will get access to Rio Tinto’s field work and current practices to model and test machine learning-based solutions.
Dr Daniel Wedge from UWA’s Centre for Data-driven Geoscience (CDG) at the School of Earth Sciences said the centre’s expertise would be used to help Rio Tinto’s mine geologists with the challenges of accurately logging geological materials.
“Until recently, geologists, metallurgists and geotechnical engineers have had to manually interpret and record materials found in drill core samples, a procedure which can be time-consuming and challenging,” Wedge said.
“Our project will use machine learning, computer vision, spatial modelling and optimisation techniques to integrate diverse drill hole data including spectral, image, geochemistry and geophysics data to model material compositions, geomechanical proxies and their spatial distribution.”
It’s not the first time Rio Tinto and UWA have collaborated on research projects.
Rio Tinto principal, ore and product characterisation, Dr Angus McFarlane said previous alliances resulted in commercialisation of automated downhole image analysis software, and three joint patent applications on machine learning-based geology modelling.
“The UWA team has already successfully developed machine learning-based methods and tools for the analysis of stratigraphy and their material compositions for resource evaluation,” McFarlane said.
“The latest engagement will adapt and extend some of these advances for mining, the next stage of the industry workflow from resource evaluation.”
