Skip to content

Research at St Andrews

The application of machine learning methods to aggregate geochemistry predicts quarry source location: an example from Ireland

Research output: Contribution to journalArticlepeer-review

Standard

The application of machine learning methods to aggregate geochemistry predicts quarry source location : an example from Ireland. / Dornan, Tadhg; O'Sullivan, Gary; O'Riain, Neal; Stueeken, Eva; Goodhue, Robbie.

In: Computers & Geosciences, Vol. In press, 104495, 20.04.2020.

Research output: Contribution to journalArticlepeer-review

Harvard

Dornan, T, O'Sullivan, G, O'Riain, N, Stueeken, E & Goodhue, R 2020, 'The application of machine learning methods to aggregate geochemistry predicts quarry source location: an example from Ireland', Computers & Geosciences, vol. In press, 104495. https://doi.org/10.1016/j.cageo.2020.104495

APA

Dornan, T., O'Sullivan, G., O'Riain, N., Stueeken, E., & Goodhue, R. (2020). The application of machine learning methods to aggregate geochemistry predicts quarry source location: an example from Ireland. Computers & Geosciences, In press, [104495]. https://doi.org/10.1016/j.cageo.2020.104495

Vancouver

Dornan T, O'Sullivan G, O'Riain N, Stueeken E, Goodhue R. The application of machine learning methods to aggregate geochemistry predicts quarry source location: an example from Ireland. Computers & Geosciences. 2020 Apr 20;In press. 104495. https://doi.org/10.1016/j.cageo.2020.104495

Author

Dornan, Tadhg ; O'Sullivan, Gary ; O'Riain, Neal ; Stueeken, Eva ; Goodhue, Robbie. / The application of machine learning methods to aggregate geochemistry predicts quarry source location : an example from Ireland. In: Computers & Geosciences. 2020 ; Vol. In press.

Bibtex - Download

@article{e0e29b3336134620b164d28007558656,
title = "The application of machine learning methods to aggregate geochemistry predicts quarry source location: an example from Ireland",
abstract = "Attempts using geochemical data to classify quarry sources which provided reactive rock aggregate, composed of Carboniferous aged pyritic mudrocks and limestones, which has caused structural damage to over 12, 500 homes across Ireland have not yet succeeded. In this paper, a possible solution to this problem is found by performing machine learning models, such as Logistic regression and Random Forest, upon a geochemical dataset obtained through the scanning electron microscope energy-dispersive X-ray spectroscopy (SEM-EDS) and Laser ablation-quadrupole-inductively couple plasma mass spectrometry (LA-Q-ICPMS) of pyrite and Isotope ratio mass spectrometry (IRMS) of bulk rock aggregate, to predict quarry source location. When comparing the classification scores, the LA-Q-ICPMS dataset achieved the highest average classification score of 55.38% for Random Forest and 67.73% for Logistic regression based on 10-fold cross validation testing. As a result, this dataset was then used to classify a set of known unknown samples and achieved average classification accuracies of 40.30% for random forest and 66.80% for logistic regression, based on a systematic train-test procedure.There is scope to enhance these classification scores to an accuracy of 100% by combining the geochemical datasets together. However, due to the difficulty in linking pyrites analysed by SEM-EDS to those analysed by LA-Q-ICPMS, and relating a bulk rock analytical technique (IRMS) to mineral geochemistry (SEM-EDS, LA-Q-ICPMS), median values have to be used when combining IRMS (Fe, S) and SEM-EDS (TS and δ34S) datasets with LA-Q-ICPMS data. Therefore, if these combined datasets were used as part of an applied quarry classification system, statistically meaningful mean values taken from a near normally distributed dataset would have to be used in order to accurately represent the quarry composition.",
author = "Tadhg Dornan and Gary O'Sullivan and Neal O'Riain and Eva Stueeken and Robbie Goodhue",
note = "This publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number 13/RC/2092 and co-funded under the European Regional Development Fund and by iCRAG industry partners.",
year = "2020",
month = apr,
day = "20",
doi = "10.1016/j.cageo.2020.104495",
language = "English",
volume = "In press",
journal = "Computers & Geosciences",
issn = "0098-3004",
publisher = "Elsevier",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - The application of machine learning methods to aggregate geochemistry predicts quarry source location

T2 - an example from Ireland

AU - Dornan, Tadhg

AU - O'Sullivan, Gary

AU - O'Riain, Neal

AU - Stueeken, Eva

AU - Goodhue, Robbie

N1 - This publication has emanated from research supported in part by a research grant from Science Foundation Ireland (SFI) under Grant Number 13/RC/2092 and co-funded under the European Regional Development Fund and by iCRAG industry partners.

PY - 2020/4/20

Y1 - 2020/4/20

N2 - Attempts using geochemical data to classify quarry sources which provided reactive rock aggregate, composed of Carboniferous aged pyritic mudrocks and limestones, which has caused structural damage to over 12, 500 homes across Ireland have not yet succeeded. In this paper, a possible solution to this problem is found by performing machine learning models, such as Logistic regression and Random Forest, upon a geochemical dataset obtained through the scanning electron microscope energy-dispersive X-ray spectroscopy (SEM-EDS) and Laser ablation-quadrupole-inductively couple plasma mass spectrometry (LA-Q-ICPMS) of pyrite and Isotope ratio mass spectrometry (IRMS) of bulk rock aggregate, to predict quarry source location. When comparing the classification scores, the LA-Q-ICPMS dataset achieved the highest average classification score of 55.38% for Random Forest and 67.73% for Logistic regression based on 10-fold cross validation testing. As a result, this dataset was then used to classify a set of known unknown samples and achieved average classification accuracies of 40.30% for random forest and 66.80% for logistic regression, based on a systematic train-test procedure.There is scope to enhance these classification scores to an accuracy of 100% by combining the geochemical datasets together. However, due to the difficulty in linking pyrites analysed by SEM-EDS to those analysed by LA-Q-ICPMS, and relating a bulk rock analytical technique (IRMS) to mineral geochemistry (SEM-EDS, LA-Q-ICPMS), median values have to be used when combining IRMS (Fe, S) and SEM-EDS (TS and δ34S) datasets with LA-Q-ICPMS data. Therefore, if these combined datasets were used as part of an applied quarry classification system, statistically meaningful mean values taken from a near normally distributed dataset would have to be used in order to accurately represent the quarry composition.

AB - Attempts using geochemical data to classify quarry sources which provided reactive rock aggregate, composed of Carboniferous aged pyritic mudrocks and limestones, which has caused structural damage to over 12, 500 homes across Ireland have not yet succeeded. In this paper, a possible solution to this problem is found by performing machine learning models, such as Logistic regression and Random Forest, upon a geochemical dataset obtained through the scanning electron microscope energy-dispersive X-ray spectroscopy (SEM-EDS) and Laser ablation-quadrupole-inductively couple plasma mass spectrometry (LA-Q-ICPMS) of pyrite and Isotope ratio mass spectrometry (IRMS) of bulk rock aggregate, to predict quarry source location. When comparing the classification scores, the LA-Q-ICPMS dataset achieved the highest average classification score of 55.38% for Random Forest and 67.73% for Logistic regression based on 10-fold cross validation testing. As a result, this dataset was then used to classify a set of known unknown samples and achieved average classification accuracies of 40.30% for random forest and 66.80% for logistic regression, based on a systematic train-test procedure.There is scope to enhance these classification scores to an accuracy of 100% by combining the geochemical datasets together. However, due to the difficulty in linking pyrites analysed by SEM-EDS to those analysed by LA-Q-ICPMS, and relating a bulk rock analytical technique (IRMS) to mineral geochemistry (SEM-EDS, LA-Q-ICPMS), median values have to be used when combining IRMS (Fe, S) and SEM-EDS (TS and δ34S) datasets with LA-Q-ICPMS data. Therefore, if these combined datasets were used as part of an applied quarry classification system, statistically meaningful mean values taken from a near normally distributed dataset would have to be used in order to accurately represent the quarry composition.

U2 - 10.1016/j.cageo.2020.104495

DO - 10.1016/j.cageo.2020.104495

M3 - Article

VL - In press

JO - Computers & Geosciences

JF - Computers & Geosciences

SN - 0098-3004

M1 - 104495

ER -

Related by author

  1. Hydrothermal recycling of sedimentary ammonium into oceanic crust and the Archean ocean at 3.24 Ga

    Stueeken, E. E., Boocock, T. J., Robinson, A., Mikhail, S. & Johnson, B., 8 Apr 2021, In: Geology. First Online, 5 p.

    Research output: Contribution to journalArticlepeer-review

  2. Constraining the conditions of phosphogenesis: stable isotope and trace element systematics of Recent Namibian phosphatic sediments

    Lumiste, K., Mänd, K., Bailey, J., Stüeken, E. E., Paiste, K., Lang, L., Sepp, H., Lepland, A. & Kirsimäe, K., 31 Mar 2021, In: Geochimica et Cosmochimica Acta. In Press

    Research output: Contribution to journalArticlepeer-review

  3. MOVES IV. Modelling the influence of stellar XUV-flux, cosmic rays, and stellar energetic particles on the atmospheric composition of the hot Jupiter HD 189733b

    Barth, P., Helling, C., Stueeken, E. E., Bourrier, V., Mayne, N., Rimmer, P., Jardine, M. M., Vidotto, A., Wheatley, P. & Fares, R., 22 Dec 2020, (Accepted/In press) In: Monthly Notices of the Royal Astronomical Society. 15 p.

    Research output: Contribution to journalArticlepeer-review

  4. Sedimentology and isotope geochemistry of transitional evaporitic environments within arid continental settings: from erg to saline lakes

    Pettigrew, R. P., Priddy, C., Clarke, S. M., Warke, M. R., Stüeken, E. E. & Claire, M. W., 20 Dec 2020, In: Sedimentology. Early View

    Research output: Contribution to journalArticlepeer-review

Related by journal

  1. Dual-scale validation of a medium-resolution coastal DEM with terrestrial LiDAR DSM and GPS

    Coyeney, S., Fotheringham, A. S., Charlton, M. & McCarthy, T., Apr 2010, In: Computers & Geosciences. 36, 4, p. 489-499 11 p.

    Research output: Contribution to journalArticlepeer-review

ID: 267566802

Top