Abstract
In order to distinguish between archaeological pottery produced in the Etruscan city of Tarquinia and pottery produced in other coeval sites, we tested several supervised learning algorithms for classification. Pottery sherds were analised by X-ray fluorescence analysis and described in the dataset by the relative concentration of nine chemical elements. The dataset was unbalanced with about one fourth of negative samples, and contained repeated measures for each fragment; the number of repeated measures for each fragment ranged between two and seven. We carried out two types of experiments which differ in the way the repeated measures are exploited. The best performing models showed good performance, in terms of accuracy, sensibility and specificity.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Depurata pottery and Bucchero are classes of Etruscan ceramics, characterized by a bulk without microscopically visible inclusions.
- 2.
We also considered a variation of this experiment in which stratification was followed by a subsampling of the available measures, so as to ensure that each fold had approximately the same length. However, given the significantly high variance of the number of measures for the various fragments, we would have obtained folds with a very small number of negative cases, with a detrimental effect on the robustness of the estimate for model generalization ability.
References
Aruga, R.: Closure of analytical chemical data and multivariate classification. Talanta 47(4), 1053–1061 (1998). https://doi.org/10.1016/S0039-9140(98)00126-X
Baxter, M.J.: A review of supervised and unsupervised pattern recognition in archaeometry. Archaeometry 48(4), 671–694 (2006). https://doi.org/10.1111/j.1475-4754.2006.00280.x
Bonizzoni, L., Galli, A., Milazzo, M.: XRF analysis without sampling of Etruscan depurata pottery for provenance classification. X-Ray Spectrom. 39(5), 346–352 (2010). https://doi.org/10.1002/xrs.1263
Bruno, P., Caselli, M., Curri, M., Genga, A., Striccoli, R., Traini, A.: Chemical characterisation of ancient pottery from south of Italy by inductively coupled plasma atomic emission spectroscopy (ICP-AES): statistical multivariate analysis of data. Analytica chimica acta 410(1–2), 193–202 (2000). https://doi.org/10.1016/S0003-2670(00)00734-0
Charalambous, E., Dikomitou-Eliadou, M., Milis, G.M., Mitsis, G., Eliades, D.G.: An experimental design for the classification of archaeological ceramic data from Cyprus, and the tracing of inter-class relationships. J. Arch. Sci. Rep. 7, 465–471 (2016). https://doi.org/10.1016/j.jasrep.2015.08.010
Ciliberto, E., Spoto, G. (eds.): Modern Analytical Methods in Art and Archaeology, Chemical Analysis, vol. 155. Wiley, Hoboken (2000)
Fermo, P., Cariati, F., Ballabio, D., Consonni, V., Bagnasco Gianni, G.: Classification of ancient Etruscan ceramics using statistical multivariate analysis of data. Appl. Phys. A 79(2), 299–307 (2004). https://doi.org/10.1007/s00339-004-2520-6
Fermo, P., Delnevo, E., Lasagni, M., Polla, S., de Vos, M.: Application of chemical and chemometric analytical techniques to the study of ancient ceramics from Dougga (Tunisia). Microchem. J. 88(2), 150–159 (2008). https://doi.org/10.1016/j.microc.2007.11.012
Hazenfratz, R., Munita, C.S., Neves, E.G.: Neural Networks (SOM) applied to INAA data of chemical elements in archaeological ceramics from central amazon. STAR Sci. Technol. Archaeol. Res. 3(2), 334–340 (2017). https://doi.org/10.1080/20548923.2018.1470218
Idjouadiene, L., Mostefaoui, T.A., Djermoune, H., Bonizzoni, L.: Application of X-ray fluorescence spectroscopy to provenance studies of Algerian archaeological pottery. X-Ray Spectrom. 48(5), 505–512 (2019). https://doi.org/10.1002/xrs.3020
Jones, R.E.: Greek and Cypriot Pottery: A Review of Scientific Studies, vol. 1. British School at Athens (1986)
Padilla, R., Van Espen, P., Torres, P.G.: The suitability of XRF analysis for compositional classification of archaeological ceramic fabric: a comparison with a previous NAA study. Analytica Chimica Acta 558(1–2), 283–289 (2006)
Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825–2830 (2011). https://jmlr.csail.mit.edu/papers/v12/pedregosa11a.html
Romano, F., Pappalardo, G., Pappalardo, L., Garraffo, S., Gigli, R., Pautasso, A.: Quantitative non-destructive determination of trace elements in archaeological pottery using a portable beam stability-controlled XRF spectrometer. X-Ray Spectrom. Int. J. 35(1), 1–7 (2006). https://doi.org/10.1002/xrs.880
Sun, H., Liu, M., Li, L., Yan, L., Zhou, Y., Feng, X.: A new classification method of ancient Chinese ceramics based on machine learning and component analysis. Ceram. Int. 46(6), 8104–8110 (2020). https://doi.org/10.1016/j.ceramint.2019.12.037
Acknowledgements
Part of this work was done while D. Malchiodi was visiting scientist at Inria Sophia-Antipolis/I3S CNRS Université Côte d’Azur (France).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zanaboni, A.M., Malchiodi, D., Bonizzoni, L., Ruschioni, G. (2022). Classification of Pottery Fragments Described by Concentration of Chemical Elements. In: Mazzeo, P.L., Frontoni, E., Sclaroff, S., Distante, C. (eds) Image Analysis and Processing. ICIAP 2022 Workshops. ICIAP 2022. Lecture Notes in Computer Science, vol 13373. Springer, Cham. https://doi.org/10.1007/978-3-031-13321-3_13
Download citation
DOI: https://doi.org/10.1007/978-3-031-13321-3_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-13320-6
Online ISBN: 978-3-031-13321-3
eBook Packages: Computer ScienceComputer Science (R0)