University Of Tasmania

File(s) under permanent embargo

Unsupervised clustering of continental-scale geophysical and geochemical data using Self-Organising Maps

conference contribution
posted on 2023-05-23, 17:48 authored by Matthew CracknellMatthew Cracknell, Anya ReadingAnya Reading
Self-Organising Maps is a data-driven approach for exploring and analysing disparate, high-dimensional data. In this experiment Self-Organising Maps is used to cluster remotely sensed geophysical and geochemical data covering the Australian continent into geologically meaningful groups. Our analysis of SOM derived clusters indicates the Australian continent can be represented by five generalised geochronological domains. These geochronological domains contain a number of lithologies symbolising bedrock and regolith units with distinct characteristics.


Australian Research Council

AMIRA International Ltd

ARC C of E Industry Partner $ to be allocated

Anglo American Exploration Philippines Inc

AngloGold Ashanti Australia Limited

Australian National University

BHP Billiton Ltd

Barrick (Australia Pacific) PTY Limited

CSIRO Earth Science & Resource Engineering

Mineral Resources Tasmania

Minerals Council of Australia

Newcrest Mining Limited

Newmont Australia Ltd

Oz Minerals Australia Limited

Rio Tinto Exploration

St Barbara Limited

Teck Cominco Limited

University of Melbourne

University of Queensland

Zinifex Australia Ltd


Publication title

Proceedings of the 3rd Australian Regolith Geoscientists Association Conference


VNL Wong




School of Natural Sciences


Australian Regolith Geoscientists Association

Place of publication


Event title

3rd Australian Regolith Geoscientists Association Conference

Event Venue

Bunbury, Australia

Date of Event (Start Date)


Date of Event (End Date)


Repository Status

  • Restricted

Socio-economic Objectives

Expanding knowledge in the earth sciences

Usage metrics

    University Of Tasmania