Machine learning in resource geology – why data quality is critical

Consultants in the mining industry have the opportunity to visit interesting deposits all over the world. Each deposit has its own set of challenges to face when it comes to defining and understanding the deposit geology and the economics to make it viable for extraction. Some of the challenges can include appropriate data capture, sampling techniques, structural characteristics, geochemistry, geophysics, lithology definition, and economic boundaries. It is essential that the practices used at each deposit (eg drilling, sampling, geological modelling, resource estimation etc) are documented and the results obtained are robust and defensible. The Competent Person is not always aware of instances where their resource estimation practices have not been substantiated. ‘You don’t know what you don’t know’ is a phrase frequently used during a mineral resource audit. Technical work to substantiate drilling, sampling, density, assaying, geological modelling and estimation processes is not always completed. Audited Competent Persons often comment: • ‘I was unaware that this was required.’ • ‘I have not had training in this area and do not know how to complete the checks required.’ • ‘This is how we’ve always done it.’ Examples of audits where it was found that geological practices were not substantiated are examined here. A discussion is included on why substantiation of these practices is important, and potential reasons as to why there are instances of unsubstantiated processes and practices are discussed.