Transfer learning empowers material Z classification with muon tomography
Nuclear Science and Techniques · 2026-05 · 37 (5)
DOI: 10.1007/s41365-026-01901-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Nuclear Science and Techniques, online erschienen am 09.02.2026. Verfasst von Hao-Chen Wang und 14 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben.
Abstract (Originalsprache)
Cosmic-ray muon sources exhibit distinct scattering angle distributions when interacting with materials of different atomic numbers (Z values), facilitating the identification of various Z-class materials, particularly radioactive high-Z nuclear elements. Most traditional identification methods are based on complex statistical iterative reconstruction or simple trajectory approximation. Supervised machine learning methods offer some improvement but rely heavily on prior knowledge of the target materials, significantly limiting their practical applicability in detecting concealed materials. To the best of our knowledge, this is the first study to introduce transfer learning into muon tomography. We propose two lightweight neural network models for fine-tuning and adversarial transfer learning, utilizing muon scattering data of bare materials to predict the Z-class of materials coated by typical shieldings (e.g., aluminum or polyethylene), simulating practical scenarios such as cargo inspection and arms control. By introducing a novel inverse cumulative distribution-based sampling method, more accurate scattering angle distributions could be obtained from the data, leading to an improvement of nearly 4% in prediction accuracy compared with the traditional random sampling-based training. When applied to coated materials with limited labeled or even unlabeled muon tomography data, the proposed method achieved an overall prediction accuracy exceeding 96%, with high-Z materials reaching nearly 99%. The simulation results indicate that transfer learning improves the prediction accuracy by approximately 10% compared to direct prediction without transfer. This study demonstrates the effectiveness of transfer learning in overcoming the physical challenges associated with limited labeled/unlabeled data and highlights the promising potential of transfer learning in the field of muon tomography.
Zitieren
APA
Wang, H., Zhang, Z., Yu, P., Bao, Y., Zhai, J., Xu, Y., Deng, L., Xiao, S., Zhang, X., Yu, Y., He, W., Chen, L., Zhang, Y., Yang, L., & Sun, Z. (2026). Transfer learning empowers material Z classification with muon tomography. Nuclear Science and Techniques, 37(5). https://doi.org/10.1007/s41365-026-01901-w
Vancouver
Wang H, Zhang Z, Yu P, Bao Y, Zhai J, Xu Y, et al. Transfer learning empowers material Z classification with muon tomography. Nuclear Science and Techniques. 2026;37(5). doi:10.1007/s41365-026-01901-w
BibTeX
@article{Wang2026,
author = {Wang, Hao-Chen and Zhang, Zhao and Yu, Pei and Bao, Yu-Xin and Zhai, Jia-Jia and Xu, Yu and Deng, Li and Xiao, Sa and Zhang, Xue-Heng and Yu, Yu-Hong and He, Wei-Bo and Chen, Liang-Wen and Zhang, Yu and Yang, Lei and Sun, Zhi-Yu},
title = {Transfer learning empowers material Z classification with muon tomography},
journal = {Nuclear Science and Techniques},
year = {2026},
volume = {37},
number = {5},
doi = {10.1007/s41365-026-01901-w}
}
EUVIMED