Using recent integrated ML case studies from Peru, Chile and the Fennoscandian Shield, Ben presents some of the challenges and key innovations being developed for making mineral discoveries.
The mining industry faces significant exploration challenges - with current global mineral inventories being unlikely to meet the predicted metal requirements, and the trend towards deeper exploration and declining grades.
Traditional approaches have typically relied on manual, expert-driven methods in GIS - which have been time-consuming and reliant on expert knowledge, which can be skewed by various biases.
Artificial intelligence, specifically machine learning (ML), is now more commonly being applied to help improve data processing and manage risks. In the mineral prospectivity space, ML can rapidly integrate and interrogate a wide range of datasets, which overcomes challenges, including human bias and the need to analyse large and varied datasets.
Learn about the role of AI use in mining, including ML in exploration mineral prospectivity mapping, as well as integrating more traditional knowledge-based (fuzzy logic) methods.
First presented and in partnership with Critical Minerals Association Australia.
