Accelerator system parameter estimation using variational autoencoded latent regression

TL;DR

This paper introduces VALeR, a novel variational autoencoder-based model that estimates accelerator system parameters from phase space projections, enabling robust, efficient, and generative analysis of high-dimensional, time-varying accelerator systems.

Contribution

The paper presents a new VAE-based latent regression approach for estimating and generating accelerator system parameters from phase space data, addressing high dimensionality and variability.

Findings

Successfully estimates system parameters from phase space projections.

Can generate new phase space projections with corresponding parameters.

Demonstrates robustness to system perturbations.

Abstract

Particle accelerators are time-varying systems whose components are perturbed by external disturbances. Tuning accelerators can be a time-consuming process involving manual adjustment of multiple components, such as RF cavities, to minimize beam loss due to time-varying drifts. The high dimensionality of the system ($\sim$100 amplitude and phase RF settings in the LANSCE accelerator) makes it difficult to achieve optimal operation. The time-varying drifts and the dimensionality make system parameter estimation a challenging optimization problem. In this work, we propose a Variational Autoencoded Latent Regression (VALeR) model for robust estimation of system parameters using 2D unique projections of a charged particle beam's 6D phase space. In VALeR, VAE projects the phase space projections into a lower-dimensional latent space, and a dense neural network maps the latent space onto the space of system parameters. The trained network can predict system parameters for unseen phase space projections. Furthermore, VALeR can generate new projections by randomly sampling the latent space of VAE and also estimate the corresponding system parameters.