Predicting Beam Transmission Using 2-Dimensional Phase Space Projections Of Hadron Accelerators

TL;DR

This paper introduces a convolutional autoencoder-based method to compress 2D phase space projections from hadron accelerators and predict beam transmission, leveraging simulations and multiple projections for improved accuracy.

Contribution

It presents a novel approach combining autoencoders and phase space projections to predict beam transmission in hadron accelerators, even with non-linear distributions.

Findings

Autoencoder effectively compresses phase space data.

Method predicts beam transmission with reasonable accuracy.

Generalizes well to non-linear phase space distributions.

Abstract

We present a method to compressed the 2D transverse phase space projections from a hadron accelerator and use that information to predict the beam transmission. This method assumes that it is possible to obtain at least three projections of the 4D transverse phase space and that an accurate simulation model is available for the beamline. Using a simulated model we show that, a procedure using a convolutional autoencoder can be trained to reduce phase-space information which can later be used to predict the beam transmission. Finally, we argue that although using projections from a realistic non-linear distribution produces less accurate results, the method still generalizes well.