High-Resolution Image Reconstruction with Unsupervised Learning and Noisy Data Applied to Ion-Beam Dynamics for Particle Accelerators

TL;DR

This paper presents an unsupervised neural network-based method for high-resolution image reconstruction of beam halos in particle accelerators, effectively denoising noisy data and surpassing previous resolution limits.

Contribution

It introduces a novel unsupervised approach combining convolutional filtering and neural networks with early stopping, enabling high-fidelity reconstruction without training datasets.

Findings

Achieves robust denoising of low SNR beam images

Extends measurable amplitudes beyond seven standard deviations

Enables unprecedented halo resolution in beam diagnostics

Abstract

Image reconstruction in the presence of severe degradation remains a challenging inverse problem, particularly in beam diagnostics for high-energy physics accelerators. As modern facilities demand precise detection of beam halo structures to control losses, traditional analysis tools have reached their performance limits. This work reviews existing image-processing techniques for data cleaning, contour extraction, and emittance reconstruction, and introduces a novel approach based on convolutional filtering and neural networks with optimized early-stopping strategies in order to control overfitting. Despite the absence of training datasets, the proposed unsupervised framework achieves robust denoising and high-fidelity reconstruction of beam emittance images under low signal-to-noise conditions. The method extends measurable amplitudes beyond seven standard deviations, enabling unprecedented halo resolution.