Phase Space Reconstruction from Accelerator Beam Measurements Using Neural Networks and Differentiable Simulations

TL;DR

This paper presents a neural network-based algorithm that uses differentiable simulations to accurately reconstruct high-dimensional particle beam phase space distributions in accelerators, eliminating the need for specialized diagnostics.

Contribution

The authors introduce a novel, general-purpose method combining neural networks with differentiable particle tracking for high-dimensional phase space reconstruction without specialized diagnostics.

Findings

Accurately reconstructs 4D phase space distributions in simulation and experiment.

Provides confidence intervals for reconstructed distributions.

Enables potential 6D phase space measurements in the future.

Abstract

Characterizing the phase space distribution of particle beams in accelerators is a central part of accelerator understanding and performance optimization. However, conventional reconstruction-based techniques either use simplifying assumptions or require specialized diagnostics to infer high-dimensional ($>$ 2D) beam properties. In this Letter, we introduce a general-purpose algorithm that combines neural networks with differentiable particle tracking to efficiently reconstruct high-dimensional phase space distributions without using specialized beam diagnostics or beam manipulations. We demonstrate that our algorithm accurately reconstructs detailed 4D phase space distributions with corresponding confidence intervals in both simulation and experiment using a single focusing quadrupole and diagnostic screen. This technique allows for the measurement of multiple correlated phase spaces simultaneously, which will enable simplified 6D phase space distribution reconstructions in the future.