Process Mineralogy Today

A discussion resource for process mineralogy using todays technologies


MinAssist Privacy Policy

Privacy is important and we respect yours.

This policy sets out our privacy practices and how we handle information we may collect from or about you when you visit

What do we capture and what for?

You may choose to provide information such as email address, name, phone number, company and so forth to MinAssist in order to:

  • subscribe to the MinAssist Newsletter;
  • download resources like digital books; or
  • make an enquiry about MinAssist’s services.

This information is used by MinAssist to:

  • respond to enquiries originating from you.
  • add you to a mailing list for newsletters and other occasional email contact. You may request at any time to be removed from this list.
  • add your to our contacts database which may result in email, postal or telephone communication. You may request at any time to be removed from this list.

Google Analytics

MInAssist also uses Google Analytics, a web analytics service. Google Analytics uses cookies, web beacons, and other means to help MInAssit analyse how users use the site. For information about Google’s Privacy Policy please refer to

Sharing of Information

MinAssist may share information under the following circumstances:

  • legal requirement - courts, administrative agencies, or other government entities.
  • organisations that may provide services to us - where relevant we may need to share some of your information to companies we engage with (for example, accountants, lawyers, business advisors, marketing service providers, debt collection service providers, equipment providers). Note that these third parties are prohibited by law or by contract from processing personal information for purposes other than those disclosed in this Privacy Policy.
  • where the information is already in the public domain.
  • business sale or merger - where contact data may be passed to new owners.


At your request, we will provide you with reasonable access to your personal information, so that you can review what we have stored and, if you choose, request corrections to it. Please request access by writing to us at the address listed in the Contact Information section below.


MinAssist combines technical and physical safeguards with employee policies and procedures to protect your information. We will use commercially reasonable efforts to protect your information.

Links to Other Websites

When you click on a link on this website that takes you to a website operated by another company, you will be subject to that company’s privacy practices.


MinAssist may amend this Privacy Policy from time to time.

Enforcement, Dispute Resolution, and Verification

Please contact us with any questions or concerns related to this Privacy Policy by using the address listed in the Contact Information section below. We will investigate and attempt to resolve complaints or disputes regarding personal information.

Contact Information

If you have questions or concerns related to this Privacy Policy, you may contact us by email at

Working with High-Dimensional Data Part 3: Geospatial Mapping and Mine Planning


In part 1 of this introductory series about working with high-dimensional data we looked at dimensionality reduction to allow the visualisation of complex data. Part 2 of the series explored the K-means clustering method as a technique to classify samples according to their geochemical characteristics. In this article we place the classified samples back into their geospatial context and use the spatial relationships between the clusters to define a behaviour profile, which is aimed at guiding critical mine planning decisions.


The example we’ve been developing in part 1 and part 2 of this series is based on chemical assays for four elements from a resource feasibility study. The first data processing step involved dimensionality reduction using multi-dimensional scaling to produce a 2D representation of the original high-dimensional chemical assay data. We then used the 2D data as input for a multi-step cluster analysis based on the K-means clustering method to classify geometallurgical domains (figure 1).

Figure 1: A 2D representation of the original high-dimensional data and the clusters/geochemical domains identified using a multi-step K-means clustering method (arbitrary dimensions on the x and y axes). The legend shows the number of samples in each cluster and their percentage of the total.


Figure 2 below is an interactive 3D graph showing the samples/clusters in their geospatial context. Samples that belong to the same geometallurgical domains have been given the same colour (see legend). It is clear that some samples that are classified into one clusters are spatially closer to or surrounded by samples from other domains. In terms of practical mining one has to consider the realistic range of characteristics of the raw material extracted from any given area of the resource. In this instance we use a simple proximity measure to reassign samples that are essentially isolated from their domains to the dominant geometallurgical domain in that area (figure 3). This process increases the geochemical variance of the domains, but also provides a more realistic estimate of feed material characteristics from the mining process.


Note: use basic mouse controls to interact with the graphs; select or deselect domains in the legend.





The data in figures 2 and 3 tell a relatively simple story. The resource is divided into four main geometallurgical domains. Domain 0 is the most valuable in this resource and occurs  predominantly at greater depths than the other clusters. Domain 3 is the least attractive in terms of its value and mineral processing complexity, while domains 1 and 2 might be considered intermediate domains in terms of their value and processing requirements. Geospatially the domains are fairly well defined, which paves the way to a mining strategy that might involve initially avoiding the areas where domain 3 is dominant and rather targeting locations where domains 1 and 2 are easily accessible. It might be that the operation needs to be careful with cash flow management during the early stages of the development; however, future access to domain 3 will project an upturn in cashflow at some later stage of the operation.


Parts 1, 2, and 3 in this blog series have introduced some of the basic principles of machine learning and its application in resource characterisation. The geochemical domains in figures 1, 2, and 3 above represent the “training data”, and in the next article (part 4) we will explore how we can use the training data to make predictions about unclassified “test samples” to estimate their metallurgical behaviour.

Share On LinkedIn

About the Author: Pieter Botha

Previous Arrow Back to all posts

Follow Blog

Subscribe to the MinAssist Newsletter group and receive notifications of new Process Mineralogy Today blog posts.

We promise not to spam you and we'll keep your email safe and secure. MinAssist may send you occassional email correspondence but you can unsubscribe at any time.