Neural network-based deconvolution for GeV-scale gamma-ray spectroscopy
High Power Laser Science and Engineering · 2026 · 14
DOI: 10.1017/hpl.2026.10142 ↗Kurz gefasst
Fachartikel in der Zeitschrift High Power Laser Science and Engineering, online erschienen am 21.04.2026. Verfasst von Zhuofan Zhang und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
High-energy gamma-ray spectroscopy is crucial for studying and advancing the application of high-energy photons in areas such as strong-field physics, high-energy-density science and laboratory astrophysics. However, high-energy gamma-ray spectroscopy in the multi-MeV to GeV range faces significant challenges in precise spectral reconstruction. This study presents a machine learning-based inversion approach that combines a spectrometer design with advanced deconvolution algorithms. We develop a gamma-ray spectrometer optimized through Monte Carlo simulations for maximum positron yield and minimal noise. A two-stage neural network framework is proposed based on the structure of the spectrometer: a denoising autoencoder suppresses statistical noise in measured positron spectra, while a U-Net architecture solves the ill-posed inverse problem to reconstruct incident gamma spectra. This approach establishes a method for gamma-ray diagnostics in strong-field quantum electrodynamics experiments and high-energy photon sources.
Zitieren
APA
Zhang, Z., Wei, M., Fleck, K., Liu, J., Tan, X., Sarri, G., & Yan, W. (2026). Neural network-based deconvolution for GeV-scale gamma-ray spectroscopy. High Power Laser Science and Engineering, 14. https://doi.org/10.1017/hpl.2026.10142
Vancouver
Zhang Z, Wei M, Fleck K, Liu J, Tan X, Sarri G, et al. Neural network-based deconvolution for GeV-scale gamma-ray spectroscopy. High Power Laser Science and Engineering. 2026;14. doi:10.1017/hpl.2026.10142
BibTeX
@article{Zhang2026,
author = {Zhang, Zhuofan and Wei, Mingxuan and Fleck, Kyle and Liu, Jun and Tan, Xinjian and Sarri, Gianluca and Yan, Wenchao},
title = {Neural network-based deconvolution for GeV-scale gamma-ray spectroscopy},
journal = {High Power Laser Science and Engineering},
year = {2026},
volume = {14},
doi = {10.1017/hpl.2026.10142}
}
EUVIMED