Towards latent space evolution of spatiotemporal dynamics of six-dimensional phase space of charged particle beams

TL;DR

This paper introduces a novel machine learning model combining variational autoencoders and LSTM networks to efficiently predict the complex spatiotemporal evolution of charged particle beams in accelerators, enabling faster diagnostics.

Contribution

It proposes a temporally structured VAE-LSTM model that forecasts 6D phase space dynamics, improving prediction accuracy and computational efficiency over traditional physics simulations.

Findings

Low mean squared error in predictions

High structural similarity index achieved

Effective modeling of phase space evolution

Abstract

Addressing the charged particle beam diagnostics in accelerators poses a formidable challenge, demanding high-fidelity simulations in limited computational time. Machine learning (ML) based surrogate models have emerged as a promising tool for non-invasive charged particle beam diagnostics. Trained ML models can make predictions much faster than computationally expensive physics simulations. In this work, we have proposed a temporally structured variational autoencoder model to autoregressively forecast the spatiotemporal dynamics of the 15 unique 2D projections of 6D phase space of charged particle beam as it travels through the LANSCE linear accelerator. In the model, VAE embeds the phase space projections into a lower dimensional latent space. A long-short-term memory network then learns the temporal correlations in the latent space. The trained network can evolve the phase space projections across further modules provided the first few modules as inputs. The model predicts all the projections across different modules with low mean squared error and high structural similarity index.