Mineral Resource Estimation

Automated workflow for a mineral resource model development for value estimation purposes.

This example demonstrates the application of machine learning to automate the resource model development. Machine learning is applied to the traditionally manual tasks of geological formation, domain identification, and validation of the block model mineralogy.
The steps demonstrated in the example are:
- Data Import
- Data Validation or QAQC
- Determining the Geological Domains using Unsupervised Machine Learning Techniques
- Resource estimation using Conditional Simulation
- Validation of the estimated blocks using models of each Geological Domain. Models are generated using Supervised Machine Learning Techniques
The work was presented in the following publication:
- S.Oliver, D Willingham, "Maximise Orebody Value through the Automation of Resource Model Development Using Machine Learning", GEOMET 2016
A case study based on drill hole data from a Western Australian iron ore deposit (Government of Western Australia, Department of Mines and Petroleum, 2015) is used to demonstrate the application of machine learning in this process.
To get started:
- Upzip the ResourceEstimation.zip
- Navigate to the folder that contains the source files
- Open and run ResourceEstimationStartHere.m