Automation of Mineral Resource Model Development Using Machine Learning and High-Performance Computing

Date Time
9 Nov 2020
8:30 PM EST

Overview

Creating mineral resources models is a labor-intensive task that requires inputs from geology, mining, metallurgical and commercial disciplines. It requires thousands of samples from hundreds of drill holes to be verified, and then grouped into geological domains. Subsequently, to model the resource a block model is created, blocks estimated, uncertainty quantified, and then the resource is valued. This session explores how MATLAB’s Machine Learning, and High-Performance Computing capabilities can automate and speed-up parts of this process.

This session will:

  • Automate mineral resource domaining using unsupervised machine learning techniques.
  • Estimate blocks and quantify uncertainty using conditional simulation.
  • Accelerate the computationally intensive simulations by using high-performance computing techniques such as parallel computing and GPU.
  • Validate estimated blocks using supervised machine learning techniques.

Go to Mining Seminar Series Overview page

About the Presenter

Samuel Oliver is a consultant engineer from MathWorks who specializes in helping organizations improve their operations and logistics through statistical analysis, along with predictive modelling and simulation. Solutions provided typically include the integration of modern IT technologies to support data analytics, data science, big data, cloud, with more traditional OT or process industry production technologies. He has gained extensive experience over the last 7 years working on a broad range of problems with customers in Iron-Ore, Copper and Gold mining across the value chain. Prior to joining MathWorks, Sam work in the automotive industry developing advanced dynamic control systems. He received an M.Eng.Sc. in mechatronics, a B.Eng. in mechanical and manufacturing, and a B.Sc. in computer science from the University of Melbourne, Australia.

Emmanuel is an application engineer at MathWorks who first joined the company as a training engineer. He taught several MATLAB, Simulink and SImscape courses as well as specialized topics such as machine learning, statistics, optimization, image processing and parallel computing. Prior to joining MathWorks, he was a Lecturer in Mechatronic Engineering at the University of Wollongong. He holds a PhD in Mechanical Engineering from Virginia Tech. He also worked as a Systems / Controls Engineer at Cummins Engine Company and as a research assistant in several research institutions in California and Virginia.

You are already signed in to your MathWorks Account. Please press the "Submit" button to complete the process.