CSA Global is proud to be sponsoring, exhibiting and presenting at this year’s inaugural AusIMM Mineral Resource Estimation Conference between 24-25 May, 2023 in Perth, Western Australia.
Principal Data Scientist, Matthew Nimmo will present on ‘Machine Learning and Artificial Intelligence for resource estimation: What could possibly go wrong? Nothing! Everything!’ during the Geostatistics and Machine Learning Session on Day 1.
The conference will attract geologists from Australia and abroad with an aim to showcase leading best practice, case studies and research on mineral resource estimation and the software applications required.
Meet CSA Global at Booth 7!
Abstract
Machine Learning (ML), Artificial Intelligence (AI), and Swarm Intelligence (SI) techniques are extremely powerful tools for building predictive and generative models. ML can be used for building highly accurate regression and classification models. But without careful data science and statistical analysis, a regression or classification model could be highly biased and completely wrong – and we may not even realize. An example rock density estimation task will be used to illustrate the potential gains and possible pitfalls in using ML and AI in Mineral Resource estimation. What could possibly go wrong?
Nothing! For most simple regression or classification problems, very little. For density estimation, using the global mean may be all that is possible, but the resource classification would need to reflect the uncertainty in global estimation of tonnage.
Everything! From data collection and measurement, from selecting ML and AI techniques and designing the analysis workflow to our own cognitive bias. The things that could go wrong are vast and may include but not limited to asking the wrong question, not asking questions, data bias, measurement errors, insufficient data coverage, not collecting the right variables, not collecting enough observations, collecting clustered samples, unbalanced data, filtering out data without reason (outliers), clipping data (outliers), relying on automatic feature selection, including irrelevant variables, excluding relevant variables, geological interpretation, changing context, blindly following best practice, splitting small datasets, sub-setting large datasets, using the wrong tool for the task, insufficient budget to complete the analysis, not allowing enough time for testing and experimentation (the science), focusing too much on building the model (the engineering), not learning from the data, our assumptions, our preconceptions, and our skill. This paper will explore the question of how training regression models to predict rock density are affected by gaps in the data (missing observations and missing variables). What could possibly go wrong?
Presenter
Principal Data Scientist
Matthew Nimmo
Matthew has nearly 30 years’ experience as a geologist in mining, resource estimation, and applied data analytics. He has broad experience in applied statistics, geostatistics and data wrangling, with his primary expertise in geology and mineral resource estimation. As an experienced data scientist, Matthew is highly skilled in extracting practical meaning and predictive relationships from complex and diverse multivariable data. Matthew’s work has supported geometallurgical studies and a diverse range of resource estimation and mining projects. Matthew has consulted on mines in Australia and overseas including Indonesia, South and North America, Russia, and Africa.