EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Two-Stage Convolutional Neural Network for Pseudo-6D Phase-Space Reconstruction

S Mukherjee, M Kuriki, Z J Liptak, H Hayano, M Kurata, N Terunuma, T Okugi, Y Yamamoto

Progress of Theoretical and Experimental Physics · 04.06.2026 · 2026 (6)

DOI: 10.1093/ptep/ptag086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Progress of Theoretical and Experimental Physics, online erschienen am 14.05.2026. Verfasst von S Mukherjee und 7 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SCOAP.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In particle accelerators, broad characterization of the 6D beam phase space is crucial but difficult to obtain with conventional beam diagnostics. We develop a two-stage convolutional neural network that reconstructs the 6D phase space from only 16 transverse $x\text{-}y$ screen images taken at a place with dispersion by different phase-space rotation angles. The model is trained with simulation data for the KEK-Accelerator Test Facility (ATF) injector with ASTRA. The real-space images in the chicane orbit at the KEK-ATF injector were acquired by varying the RF phase of the RF electron gun and the solenoid magnetic field. From these data, we reconstructed a pseudo-6D phase-space distribution at the cathode surface, expressed through 15 2D distributions covering all pairwise coordinate combinations. The time width and spatial spread of the electron beam at the cathode showed values consistent with the measured values at KEK-ATF. Compared to existing 6D beam imaging measurement techniques such as tomography, it significantly reduces measurement time and necessary computational resources, enabling the provision of a more practical 6D phase-space measurement method.

Förderung

  • SCOAP

Zitieren

APA

Mukherjee, S., Kuriki, M., Liptak, Z. J., Hayano, H., Kurata, M., Terunuma, N., Okugi, T., & Yamamoto, Y. (2026). Two-Stage Convolutional Neural Network for Pseudo-6D Phase-Space Reconstruction. Progress of Theoretical and Experimental Physics, 2026(6). https://doi.org/10.1093/ptep/ptag086

Vancouver

Mukherjee S, Kuriki M, Liptak ZJ, Hayano H, Kurata M, Terunuma N, et al. Two-Stage Convolutional Neural Network for Pseudo-6D Phase-Space Reconstruction. Progress of Theoretical and Experimental Physics. 2026;2026(6). doi:10.1093/ptep/ptag086

BibTeX
@article{Mukherjee2026,
  author = {Mukherjee, S and Kuriki, M and Liptak, Z J and Hayano, H and Kurata, M and Terunuma, N and Okugi, T and Yamamoto, Y},
  title = {Two-Stage Convolutional Neural Network for Pseudo-6D Phase-Space Reconstruction},
  journal = {Progress of Theoretical and Experimental Physics},
  year = {2026},
  volume = {2026},
  number = {6},
  doi = {10.1093/ptep/ptag086}
}
Kostenlos starten →