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

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.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• An Introduction to Variational Autoencoders
• A Survey of Deep Learning Techniques for Autonomous Driving
• A guide to convolution arithmetic for deep learning
• Multi-Task Learning with Deep Neural Networks: A Survey
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Machine Learning for Orders of Magnitude Speedup in Multi-Objective Optimization of Particle Accelerator Systems
• Experimental Observation of Energy Modulation in Electron Beams Passing Through Terahertz Dielectric Wakefield Structures
• Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory
• Accelerator and Beam Physics Research Goals and Opportunities

Cited by in corpus (7)

• Cheetah: Bridging the Gap Between Machine Learning and Particle Accelerator Physics with High-Speed, Differentiable Simulations
• Optimizing a Superconducting Radiofrequency Gun Using Deep Reinforcement Learning
• Mixed Diagnostics for Longitudinal Properties of Electron Bunches in a Free-Electron Laser
• The application of encoder-decoder neural networks in high accuracy and efficiency slit-scan emittance measurements
• Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal
• Adaptive Latent Space Tuning for Non-Stationary Distributions
• Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuning