17–22 May 2026
C.I.D
Europe/Zurich timezone

6D Phase space reconstruction with Multi-Modal Convolutional Neural Network

MOP6611
18 May 2026, 16:00
2h
C.I.D

C.I.D

Deauville, France
Poster Presentation MC6.D13: Instrumentation: Artificial Intelligence Poster session

Speaker

Masao Kuriki (Hiroshima University)

Description

The six-imensional (6D) phase space distribution of beam is an extremely important indicator of beam performance and provides useful information for understanding the actual state of the accelerator. On the other hand, the beam diagnostics for the 6D phase space is generally difficult and only a projection on a 1D or 2D phase space is usually obtained. We developed an algorithm based on Convolutional Neural Network (CNN) to reconstruct the 6D phase space
with a limited number of transverse beam images in $x-y$ plane. The advantage of this method is that it does not require as many computing resources as conventional back projection techniques. In this presentation, we show through simulation that a six-dimensional phase space can be reconstructed only from 4+4 beam images. An experimental study of the 6D phase space reconstruction in KEK-ATF is also presented.

In which format do you inted to submit your paper? LaTeX

Author

Masao Kuriki (Hiroshima University)

Co-authors

Mr Lei Guo (Hiroshima University) Sayantan Mukherjee (Hiroshima University) Zachary Liptak (Hiroshima University)

Presentation materials

There are no materials yet.