High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks

TL;DR

This paper presents a neural network-based data-driven approach for high-fidelity, megapixel longitudinal phase-space image prediction of electron beams in large-scale facilities, outperforming existing methods and enabling scalable modeling.

Contribution

It introduces a novel encoder-decoder neural network model trained solely on experimental data for accurate phase-space image prediction without prior physical knowledge.

Findings

Model achieves high-fidelity megapixel image predictions.

Outperforms existing phase-space modeling methods.

Demonstrates scalability and interpretability across different setups.

Abstract

Modeling of large-scale research facilities is extremely challenging due to complex physical processes and engineering problems. Here, we adopt a data-driven approach to model the longitudinal phase-space diagnostic beamline at the photoinector of the European XFEL with an encoder-decoder neural network model. A deep convolutional neural network (decoder) is used to build images measured on the screen from a small feature map generated by another neural network (encoder). We demonstrate that the model trained only with experimental data can make high-fidelity predictions of megapixel images for the longitudinal phase-space measurement without any prior knowledge of photoinjectors and electron beams. The prediction significantly outperforms existing methods. We also show the scalability and interpretability of the model by sharing the same decoder with more than one encoder used for different setups of the photoinjector, and propose a pragmatic way to model a facility with various diagnostics and working points. This opens the door to a new way of accurately modeling a photoinjector using neural networks and experimental data. The approach can possibly be extended to the whole accelerator and even other types of scientific facilities.