Encoding PGAA spectra as images for material classification with convolutional neural networks
Journal of Radioanalytical and Nuclear Chemistry · 2025-07 · 334 (7) · 4919-4932
DOI: 10.1007/s10967-025-10165-4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Radioanalytical and Nuclear Chemistry, online erschienen am 27.05.2025. Verfasst von Nathan A Mahynski und 4 weiteren Autor:innen. Beteiligte Einrichtung: Chemical Sciences Division, National Institute of Standards and Technology, Gaithersburg, MD 20899-8320, USA. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intramural NIST DOC.
Abstract (Originalsprache)
We trained deep convolutional neural networks (CNN) to classify a material based on its prompt gamma ray activation analysis (PGAA) spectrum. We focused on two dimensional (2D) models to leverage abundant open-source models pre-trained on other computer vision tasks for transfer learning. This allows models to be built with a relatively small number of trainable parameters. Moreover, CNNs can be explained naturally using class activation maps and can be equipped with out-of-distribution tests to identify materials which were not present in its training set. Together, these features suggest such models may be excellent candidates for automated material identification in real-world scenarios.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Chemical Sciences Division, National Institute of Standards and Technology, Gaithersburg, MD 20899-8320, USA.
Förderung
- Intramural NIST DOC
Zitieren
APA
Mahynski, N. A., Sheen, D. A., Paul, R. L., Chen-Mayer, H. H., & Shen, V. K. (2025). Encoding PGAA spectra as images for material classification with convolutional neural networks. Journal of Radioanalytical and Nuclear Chemistry, 334(7), 4919-4932. https://doi.org/10.1007/s10967-025-10165-4
Vancouver
Mahynski NA, Sheen DA, Paul RL, Chen-Mayer HH, Shen VK. Encoding PGAA spectra as images for material classification with convolutional neural networks. Journal of Radioanalytical and Nuclear Chemistry. 2025;334(7):4919-4932. doi:10.1007/s10967-025-10165-4
BibTeX
@article{Mahynski2025,
author = {Mahynski, Nathan A and Sheen, David A and Paul, Rick L and Chen-Mayer, H Heather and Shen, Vincent K},
title = {Encoding PGAA spectra as images for material classification with convolutional neural networks},
journal = {Journal of Radioanalytical and Nuclear Chemistry},
year = {2025},
volume = {334},
number = {7},
pages = {4919--4932},
doi = {10.1007/s10967-025-10165-4}
}
EUVIMED