Six-Dimensional Phase Space Reconstruction with Multimodal CNN
Abstract The information on phase space in all six dimensions is required for various accelerator experiments. We developed an algorithm based on Convolutional Neural Network (CNN) that can be used instead of the traditional back projection techniques because it is less computationally intensive and has a simple architecture. Our method has shown consistency with the simulation, and we plan to validate it on data taken at the KEK–Superconducting RF Test Facility (STF).
Authors
- Naoto Yamamoto (ORCID: https://orcid.org/0000-0003-0613-5451)
- Miki Kurata
- Sandip Mukherjee
- H. Hayano (ORCID: https://orcid.org/0000-0002-8474-7560)
- Z. Liptak (ORCID: https://orcid.org/0000-0002-6491-8131)
- M. Kuriki (ORCID: https://orcid.org/0000-0003-0812-8028)
- Masafumi Fukuda (ORCID: https://orcid.org/0000-0001-6649-0610)
- Kazuhiko Yamamoto (ORCID: https://orcid.org/0000-0003-0529-4055)
- Xinzhe Jin (ORCID: https://orcid.org/0009-0007-3611-1553)
- Katsuhiko Sakaue
Institutions
- Hiroshima University (JP)
- High Energy Accelerator Research Organization (JP)
- The University of Tokyo (JP)
- Tsukuba International University (JP)
Publication Details
- Journal
- Journal of Physics Conference Series
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1088/1742-6596/3094/1/012013
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00