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.