Artificial neural network for high-throughput ...
Type de document :
Article dans une revue scientifique: Article original
DOI :
URL permanente :
Titre :
Artificial neural network for high-throughput spectral data processing in LIBS imaging: application to archaeological mortar
Auteur(s) :
Herreyre, Nicolas [Auteur]
Archéologie et Archéométrie [ArAr]
Institut Lumière Matière [Villeurbanne] [ILM]
Cormier, A. [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Hermelin, Sylvain [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Oberlin, Christine [Auteur]
Archéologie et Archéométrie [ArAr]
Schmitt, Anne [Auteur]
Archéologie et Archéométrie [ArAr]
Thirion-Merle, Valerie [Auteur]
Archéologie et Archéométrie [ArAr]
Borlenghi, Aldo [Auteur]
Archéologie et Archéométrie [ArAr]
Prigent, Daniel [Auteur]
Direction Régionale des Affaires Culturelles Pays de la Loire [DRAC - Pays de la Loire]
Coquidé, Catherine [Auteur]
Institut national de recherches archéologiques préventives [Inrap]
Archéologie et Archéométrie [ArAr]
Valois, Antoine [Auteur]
Institut national de recherches archéologiques préventives [Inrap]
Dujardin, Christophe [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Dugourd, Philippe [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Duponchel, Ludovic [Auteur]
Laboratoire Avancé de Spectroscopie pour les Intéractions la Réactivité et l'Environnement (LASIRE) - UMR 8516
Comby-Zerbino, Clothilde [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Motto-Ros, Vincent [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Archéologie et Archéométrie [ArAr]
Institut Lumière Matière [Villeurbanne] [ILM]
Cormier, A. [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Hermelin, Sylvain [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Oberlin, Christine [Auteur]
Archéologie et Archéométrie [ArAr]
Schmitt, Anne [Auteur]
Archéologie et Archéométrie [ArAr]
Thirion-Merle, Valerie [Auteur]
Archéologie et Archéométrie [ArAr]
Borlenghi, Aldo [Auteur]
Archéologie et Archéométrie [ArAr]
Prigent, Daniel [Auteur]
Direction Régionale des Affaires Culturelles Pays de la Loire [DRAC - Pays de la Loire]
Coquidé, Catherine [Auteur]
Institut national de recherches archéologiques préventives [Inrap]
Archéologie et Archéométrie [ArAr]
Valois, Antoine [Auteur]
Institut national de recherches archéologiques préventives [Inrap]
Dujardin, Christophe [Auteur]

Institut Lumière Matière [Villeurbanne] [ILM]
Dugourd, Philippe [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Duponchel, Ludovic [Auteur]

Laboratoire Avancé de Spectroscopie pour les Intéractions la Réactivité et l'Environnement (LASIRE) - UMR 8516
Comby-Zerbino, Clothilde [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Motto-Ros, Vincent [Auteur]
Institut Lumière Matière [Villeurbanne] [ILM]
Titre de la revue :
Journal of Analytical Atomic Spectrometry
Numéro :
38
Pagination :
730-741
Date de publication :
2023
Mot(s)-clé(s) en anglais :
LIBS elemental imaging
artificial neural network
archaeological mortar
LIBS data processing
artificial intelligence
artificial neural network
archaeological mortar
LIBS data processing
artificial intelligence
Discipline(s) HAL :
Chimie
Sciences de l'Homme et Société/Archéologie et Préhistoire
Sciences de l'Homme et Société/Archéologie et Préhistoire
Résumé en anglais : [en]
With the development of micro-LIBS imaging, the ever-increasing size of datasets (sometimes >1 million spectra) makes the processing of spectral data difficult and time consuming. Advanced statistical methods have become ...
Lire la suite >With the development of micro-LIBS imaging, the ever-increasing size of datasets (sometimes >1 million spectra) makes the processing of spectral data difficult and time consuming. Advanced statistical methods have become necessary to process these data, but most of them still require strong expertise and are not adapted to fast data treatment or a high throughput analysis. To address these issues, we evaluate, in the present work, the use of an artificial neural network (ANN) for LIBS imaging spectral data processing for the identification of different mineral phases in archaeological lime mortar. Common in ancient architecture, this building material is a complex mixture of lime with one or more aggregates, some components of which are of the same chemical nature (e.g. calcium carbonates). In this study, we trained an artificial neural network (ANN) for automatic detection of different phases in these complex samples. The training of such a predictive model was made possible by building a LIBS dataset of more than 1300 reference spectra, obtained from various selected materials that may be present in mortars. The ANN parameters (pre-treatment of data, number of neurons and of iterations) were optimized to ensure the best recognition of mortar components, while avoiding overtraining. The results demonstrate a fast and accurate identification of each component. The use of an ANN appears to be a strong means to provide an efficient, fast and automated LIBS characterization of archaeological mortar, a concept that could later be generalized to other samples and other scientific fields and methods.Lire moins >
Lire la suite >With the development of micro-LIBS imaging, the ever-increasing size of datasets (sometimes >1 million spectra) makes the processing of spectral data difficult and time consuming. Advanced statistical methods have become necessary to process these data, but most of them still require strong expertise and are not adapted to fast data treatment or a high throughput analysis. To address these issues, we evaluate, in the present work, the use of an artificial neural network (ANN) for LIBS imaging spectral data processing for the identification of different mineral phases in archaeological lime mortar. Common in ancient architecture, this building material is a complex mixture of lime with one or more aggregates, some components of which are of the same chemical nature (e.g. calcium carbonates). In this study, we trained an artificial neural network (ANN) for automatic detection of different phases in these complex samples. The training of such a predictive model was made possible by building a LIBS dataset of more than 1300 reference spectra, obtained from various selected materials that may be present in mortars. The ANN parameters (pre-treatment of data, number of neurons and of iterations) were optimized to ensure the best recognition of mortar components, while avoiding overtraining. The results demonstrate a fast and accurate identification of each component. The use of an ANN appears to be a strong means to provide an efficient, fast and automated LIBS characterization of archaeological mortar, a concept that could later be generalized to other samples and other scientific fields and methods.Lire moins >
Langue :
Anglais
Audience :
Non spécifiée
Vulgarisation :
Non
Établissement(s) :
ENSCL
CNRS
Centrale Lille
Univ. Artois
Université de Lille
CNRS
Centrale Lille
Univ. Artois
Université de Lille
Collections :
Équipe(s) de recherche :
Propriétés magnéto structurales des matériaux (PMSM)
Date de dépôt :
2024-02-21T17:12:04Z
2024-02-27T08:39:20Z
2024-02-27T08:39:20Z
Fichiers
- d2ja00389a.pdf
- Non spécifié
- Accès libre
- Accéder au document