A supervised multiclass framework for mineral classification of Iberian beads
PLOS ONE · 2024
DOI: 10.1371/journal.pone.0302563 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Daniel Sanchez-Gomez und 8 weiteren Autor:innen. Beteiligte Einrichtung: Centro de Arqueologia da Universidade de Lisboa (UNIARQ), Lisbon, Portugal. Hauptthemen laut MEDLINE: Minerals. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and Technology, Fundação para a Ciência e a Tecnologia, Fundação para a Ciência e Tecnologia de Portugal.
Abstract (Originalsprache)
Research on personal adornments depends on the reliable characterisation of materials to trace provenance and model complex social networks. However, many analytical techniques require the transfer of materials from the museum to the laboratory, involving high insurance costs and limiting the number of items that can be analysed, making the process of empirical data collection a complicated, expensive and time-consuming routine. In this study, we compiled the largest geochemical dataset of Iberian personal adornments ( n = 1243 samples) by coupling X-ray fluorescence compositional data with their respective X-ray diffraction mineral labels. This allowed us to develop a machine learning-based framework for the prediction of bead-forming minerals by training and benchmarking 13 of the most widely used supervised algorithms. As a proof of concept, we developed a multiclass model and evaluated its performance on two assemblages from different Portuguese sites with current mineralogical characterisation: Cova das Lapas ( n = 15 samples) and Gruta da Marmota ( n = 10 samples). Our results showed that decisión-tres based classifiers outperformed other classification logics given the discriminative importance of some chemical elements in determining the mineral phase, which fits particularly well with the decision-making process of this type of model. The comparison of results between the different validation sets and the proof-of-concept has highlighted the risk of using synthetic data to handle imbalance and the main limitation of the framework: its restrictive class system. We conclude that the presented approach can successfully assist in the mineral classification workflow when specific analyses are not available, saving time and allowing a transparent and straightforward assessment of model predictions. Furthermore, we propose a workflow for the interpretation of predictions using the model outputs as compound responses enabling an uncertainty reduction approach currently used by our team. The Python-based framework is packaged in a public repository and includes all the necessary resources for its reusability without the need for any installation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centro de Arqueologia da Universidade de Lisboa (UNIARQ), Lisbon, Portugal.
- Dpto. de Prehistoria y Arqueología, Universidad de Sevilla, Seville, Spain.
- Instituto de Ciencia de Materiales de Sevilla, Universidad de Sevilla- Consejo Superior de Investigaciones Científicas, Seville, Spain.
- Dpto. de Química Inorgánica, Universidad de Sevilla, Seville, Spain.
- Institut d'Arqueologia, Universitat de Barcelona, Barcelona, Spain.
- Cuerpo de Profesores de Enseñanza Secundaria, Gobierno de Cantabria, Cantabria, Spain.
ORCID-Profile: Daniel Sanchez-Gomez, José Ángel Garrido-Cordero, Galo Romero-García
Förderung
- Ministry of Science and Technology
- Fundação para a Ciência e a Tecnologia
- Fundação para a Ciência e Tecnologia de Portugal
Zitieren
APA
Sanchez-Gomez, D., Odriozola Lloret, C. P., Sousa, A. C., Garrido-Cordero, J. Á., Romero-García, G., Martínez-Blanes, J. M., Edo I Benaiges, M., Villalobos-García, R., & Gonçalves, V. S. (2024). A supervised multiclass framework for mineral classification of Iberian beads. PLOS ONE. https://doi.org/10.1371/journal.pone.0302563
Vancouver
Sanchez-Gomez D, Odriozola Lloret CP, Sousa AC, Garrido-Cordero JÁ, Romero-García G, Martínez-Blanes JM, et al. A supervised multiclass framework for mineral classification of Iberian beads. PLOS ONE. 2024. doi:10.1371/journal.pone.0302563
BibTeX
@article{SanchezGomez2024,
author = {Sanchez-Gomez, Daniel and Odriozola Lloret, Carlos P and Sousa, Ana Catarina and Garrido-Cordero, José Ángel and Romero-García, Galo and Martínez-Blanes, José María and Edo I Benaiges, Manel and Villalobos-García, Rodrigo and Gonçalves, Victor S},
title = {A supervised multiclass framework for mineral classification of Iberian beads},
journal = {PLOS ONE},
year = {2024},
doi = {10.1371/journal.pone.0302563}
}
EUVIMED