Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning
Metasomatism occurs when fluid interacts with rock to add, or remove, its chemical constituents; these processes form mineral deposits where economic element(s) are concentrated into small volumes of rock. It can be difficult, or impossible, to visually determine original rock types for samples that...
Published in: | Journal of Geochemical Exploration |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier Science Bv
2018
|
Subjects: | |
Online Access: | https://doi.org/10.1016/j.gexplo.2018.01.002 http://ecite.utas.edu.au/124199 |
id |
ftunivtasecite:oai:ecite.utas.edu.au:124199 |
---|---|
record_format |
openpolar |
spelling |
ftunivtasecite:oai:ecite.utas.edu.au:124199 2023-05-15T18:44:11+02:00 Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning Hood, SB Cracknell, MJ Gazley, MF 2018 https://doi.org/10.1016/j.gexplo.2018.01.002 http://ecite.utas.edu.au/124199 en eng Elsevier Science Bv http://dx.doi.org/10.1016/j.gexplo.2018.01.002 Hood, SB and Cracknell, MJ and Gazley, MF, Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning, Journal of Geochemical Exploration, 186 pp. 270-280. ISSN 0375-6742 (2018) [Refereed Article] http://ecite.utas.edu.au/124199 Information and Computing Sciences Artificial Intelligence and Image Processing Pattern Recognition and Data Mining Refereed Article PeerReviewed 2018 ftunivtasecite https://doi.org/10.1016/j.gexplo.2018.01.002 2019-12-13T22:22:54Z Metasomatism occurs when fluid interacts with rock to add, or remove, its chemical constituents; these processes form mineral deposits where economic element(s) are concentrated into small volumes of rock. It can be difficult, or impossible, to visually determine original rock types for samples that are significantly altered, e.g., when rocks have experienced texturally destructive metasomatism or deformation. A typical solution using chemical data involves the separation and labelling of chemically distinct rocks using discrimination diagrams.However, such approaches can be subjective, and manual sample-by-sample consideration of large mining or exploration databases is untenable. Here we present an example workflow to facilitate relating rocks with similar origins but differing geological histories. We employ a combination of unsupervised and supervised machine learning algorithms to automate classification tasks typically undertaken manually by a geologist with domain expertise. In this study, data are first normalised and then clustered into natural groupings that represent protolith lithologies or rock-type subunits. These clusters are then used to inform a classification algorithm that assigns protolith equivalent labels to samples of altered rocks. Applied to problems involving large chemical datasets, machine learning provides objectivity, reproducibility and rapidity; useful advantages as compared to geostatistical domaining methods that involve manual determination and selection of geochemically similar regions. We utilise k-means++ unsupervised clustering to create objective and reproducible groupings of data points, with many geochemical variables considered simultaneously. Subsequently, Random Forests supervised classification is used to label samples while accommodating interactions and/or correlations between data points. We present a case study from the Minto Cu-Au-Ag mine, Whitehorse, Yukon, Canada. Interpretation of multi-element geochemical data using the approach that we have outlined here allows reconstruction of protolith geometry and an understanding of how rock type may have influenced later partitioning of hydrothermal fluids and ductile deformation. Article in Journal/Newspaper Whitehorse Yukon eCite UTAS (University of Tasmania) Yukon Canada Journal of Geochemical Exploration 186 270 280 |
institution |
Open Polar |
collection |
eCite UTAS (University of Tasmania) |
op_collection_id |
ftunivtasecite |
language |
English |
topic |
Information and Computing Sciences Artificial Intelligence and Image Processing Pattern Recognition and Data Mining |
spellingShingle |
Information and Computing Sciences Artificial Intelligence and Image Processing Pattern Recognition and Data Mining Hood, SB Cracknell, MJ Gazley, MF Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
topic_facet |
Information and Computing Sciences Artificial Intelligence and Image Processing Pattern Recognition and Data Mining |
description |
Metasomatism occurs when fluid interacts with rock to add, or remove, its chemical constituents; these processes form mineral deposits where economic element(s) are concentrated into small volumes of rock. It can be difficult, or impossible, to visually determine original rock types for samples that are significantly altered, e.g., when rocks have experienced texturally destructive metasomatism or deformation. A typical solution using chemical data involves the separation and labelling of chemically distinct rocks using discrimination diagrams.However, such approaches can be subjective, and manual sample-by-sample consideration of large mining or exploration databases is untenable. Here we present an example workflow to facilitate relating rocks with similar origins but differing geological histories. We employ a combination of unsupervised and supervised machine learning algorithms to automate classification tasks typically undertaken manually by a geologist with domain expertise. In this study, data are first normalised and then clustered into natural groupings that represent protolith lithologies or rock-type subunits. These clusters are then used to inform a classification algorithm that assigns protolith equivalent labels to samples of altered rocks. Applied to problems involving large chemical datasets, machine learning provides objectivity, reproducibility and rapidity; useful advantages as compared to geostatistical domaining methods that involve manual determination and selection of geochemically similar regions. We utilise k-means++ unsupervised clustering to create objective and reproducible groupings of data points, with many geochemical variables considered simultaneously. Subsequently, Random Forests supervised classification is used to label samples while accommodating interactions and/or correlations between data points. We present a case study from the Minto Cu-Au-Ag mine, Whitehorse, Yukon, Canada. Interpretation of multi-element geochemical data using the approach that we have outlined here allows reconstruction of protolith geometry and an understanding of how rock type may have influenced later partitioning of hydrothermal fluids and ductile deformation. |
format |
Article in Journal/Newspaper |
author |
Hood, SB Cracknell, MJ Gazley, MF |
author_facet |
Hood, SB Cracknell, MJ Gazley, MF |
author_sort |
Hood, SB |
title |
Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
title_short |
Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
title_full |
Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
title_fullStr |
Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
title_full_unstemmed |
Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
title_sort |
linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning |
publisher |
Elsevier Science Bv |
publishDate |
2018 |
url |
https://doi.org/10.1016/j.gexplo.2018.01.002 http://ecite.utas.edu.au/124199 |
geographic |
Yukon Canada |
geographic_facet |
Yukon Canada |
genre |
Whitehorse Yukon |
genre_facet |
Whitehorse Yukon |
op_relation |
http://dx.doi.org/10.1016/j.gexplo.2018.01.002 Hood, SB and Cracknell, MJ and Gazley, MF, Linking protolith rocks to altered equivalents by combining unsupervised and supervised machine learning, Journal of Geochemical Exploration, 186 pp. 270-280. ISSN 0375-6742 (2018) [Refereed Article] http://ecite.utas.edu.au/124199 |
op_doi |
https://doi.org/10.1016/j.gexplo.2018.01.002 |
container_title |
Journal of Geochemical Exploration |
container_volume |
186 |
container_start_page |
270 |
op_container_end_page |
280 |
_version_ |
1766234775422500864 |