University of Tasmania
Browse
132180 - A speedy update on machine learning applied to bedrock mapping using geochemistry or geophysics.pdf (915.3 kB)

A speedy update on machine learning applied to bedrock mapping using geochemistry or geophysics: examples from the Pacific Rim (and nearby)

Download (915.3 kB)
conference contribution
posted on 2023-05-23, 14:05 authored by Shawn Hood, Gazley, MF, Matthew CracknellMatthew Cracknell, Shaun BarkerShaun Barker, Anya ReadingAnya Reading

Artificial Intelligence (AI) has numerous and varied definitions, leading to confusion and disagreement about what it represents, and how it relates to mineral exploration. A general definition is most effective: AI is the artificial machine-based reproduction of tasks inspired by, or conventionally accomplished by humans (or other animals) using their natural intelligence. The form of AI applied to mineral exploration is called ‘Domain Specific AI’; it is task-oriented and includes decades-old approaches to software automation and statistical modelling.

A core skill of experienced economic geologists is pattern recognition. This might include field-based work (e.g., recognising groupings of rock types, alteration minerals, or mineral textures related to mineralisation) or laboratory-based work (e.g., identifying groups of similar analyses from geochemical assays, or categorising spectral data from remote sensing devices). Machine learning (ML) is a subfield of AI that specialises in pattern recognition and is defined as any computer program that improves its performance at some task through experience or iteration. ML is well-studied and has routinely been applied towards mineral exploration over five decades. ML can automate parts of mineral exploration workflows, e.g., mapping or modelling geology, and can improve results by making them more objective, repeatable, or efficient.

This extended abstract briefly gives three examples of ML used to improve the interpretation of rock type in a mineral exploration or mining area, using geochemical or geophysical data.

History

Publication title

Proceedings of the 2019 Mineral Systems of the Pacific Rim Congress (PACRIM 2019)

Pagination

58-61

ISBN

9781925100808

Department/School

School of Natural Sciences

Publisher

AusIMM

Place of publication

Australia

Event title

Mineral Systems of the Pacific Rim Congress 2019 (PACRIM 2019)

Event Venue

Auckland, New Zealand

Date of Event (Start Date)

2019-04-03

Date of Event (End Date)

2019-04-05

Rights statement

Copyright unknown

Repository Status

  • Open

Socio-economic Objectives

Mineral exploration not elsewhere classified

Usage metrics

    University Of Tasmania

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC