cDVAE: Multimodal Generative Conditional Diffusion Guided by Variational Autoencoder Latent Embedding for Virtual 6D Phase Space Diagnostics

TL;DR

This paper introduces cDVAE, a novel generative model that accurately predicts the full 6D phase space of a particle beam from limited 2D projections, aiding in non-destructive beam diagnostics.

Contribution

The work presents a new multimodal conditional diffusion model guided by a VAE for virtual 6D phase space diagnostics, enabling accurate reconstruction from limited projections.

Findings

Successfully reconstructs all 15 2D projections of the 6D phase space.

Demonstrates high accuracy in a real accelerator setting.

Guided by both scalar parameters and images for improved precision.

Abstract

Imaging the 6D phase space of a beam in a particle accelerator in a single shot is currently impossible. Single shot beam measurements only exist for certain 2D beam projections and these methods are destructive. A virtual diagnostic that can generate an accurate prediction of a beam's 6D phase space would be incredibly useful for precisely controlling the beam. In this work, a generative conditional diffusion-based approach to creating a virtual diagnostic of all 15 unique 2D projections of a beam's 6D phase space is developed. The diffusion process is guided by a combination of scalar parameters and images that are converted to low-dimensional latent vector representation by a variational autoencoder (VAE). We demonstrate that conditional diffusion guided by VAE (cDVAE) can accurately reconstruct all 15 of the unique 2D projections of a charge particle beam's 6 phase space for the HiRES compact accelerator.