Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal

Abstract

Charged particle dynamics under the influence of electromagnetic fields is a challenging spatiotemporal problem. Many high performance physics-based simulators for predicting behavior in a charged particle beam are computationally expensive, limiting their utility for solving inverse problems online. The problem of estimating upstream six-dimensional phase space given downstream measurements of charged particles in an accelerator is an inverse problem of growing importance. This paper introduces a reverse Latent Evolution Model (rLEM) designed for temporal inversion of forward beam dynamics. In this two-step self-supervised deep learning framework, we utilize a Conditional Variational Autoencoder (CVAE) to project 6D phase space projections of a charged particle beam into a lower-dimensional latent distribution. Subsequently, we autoregressively learn the inverse temporal dynamics in the latent space using a Long Short-Term Memory (LSTM) network. The coupled CVAE-LSTM framework can predict 6D phase space projections across all upstream accelerating sections based on single or multiple downstream phase space measurements as inputs. The proposed model also captures the aleatoric uncertainty of the high-dimensional input data within the latent space. This uncertainty, which reflects potential uncertain measurements at a given module, is propagated through the LSTM to estimate uncertainty bounds for all upstream predictions, demonstrating the robustness of the LSTM against in-distribution variations in the input data.

arXiv admin note: text overlap with arXiv:2403.13858

References in corpus (24)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Machine Learning in Nuclear Physics
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Bayesian optimization of a free-electron laser
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
• Teaching the Incompressible Navier-Stokes Equations to Fast Neural Surrogate Models in 3D
• Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratory
• Phase Space Reconstruction from Accelerator Beam Measurements Using Neural Networks and Differentiable Simulations
• High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks
• Physics-Based Deep Neural Networks for Beam Dynamics in Charged Particle Accelerators
• Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities
• Transverse phase space tomography in the CLARA accelerator test facility using image compression and machine learning
• Uncertainty Quantification for Virtual Diagnostic of Particle Accelerators
• Multi-Objective Bayesian Active Learning for MeV-ultrafast electron diffraction
• Uncertainty Aware ML-based surrogate models for particle accelerators: A Study at the Fermilab Booster Accelerator Complex
• Virtual-Diagnostic-Based Time Stamping for Ultrafast Electron Diffraction
• Predicting the transverse emittance of space charge dominated beams using the phase advance scan technique and a fully connected neural network
• Review of Time Series Forecasting Methods and Their Applications to Particle Accelerators
• Robust Errant Beam Prognostics with Conditional Modeling for Particle Accelerators
• Identification of Magnetic Field Errors in Synchrotrons based on Deep Lie Map Networks