LINAC2026 - 33rd Linear Accelerator Conference

Two-stage Convolutional Neural Network for pseudo six-dimensional phase space reconstruction

Not scheduled

2h

Daejeon Convention Center

Poster Presentation MC1.A01: Beam Dynamics, beam simulations, beam transport Poster Session

Speaker

Zachary Liptak (Hiroshima University)

Description

In particle accelerators, full knowledge of the six-dimensional (6D) beam phase space is crucial but difficult to obtain with conventional beam diagnostics. We have developed a two-stage convolutional neural network (CNN) that reconstructs the 6D phase space from only sixteen transverse x − y screen images taken at a place with dispersion by different phase space rotation angles. With these images, we reconstruct the 6D phase space distribution at the cathode surface and visualize it as 15 two-dimensional images covering all pairwise coordinate combinations. Compared to existing 6D beam imaging measurement techniques such as tomography, it significantly reduces measurement time and required computational resources, enabling the provision of a more practical 6D phase space measurement method.

Funding Agency

This work is partly supported by JSPS KAKENHI Grant Numbers JP20H01934.