Using Convolutional Neural Networks to Accelerate 3D Coherent Synchrotron Radiation Computations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leon, Christopher, Anisimov, Petr M., Yampolsky, Nikolai, Scheinker, Alexander
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909535804850176
author Leon, Christopher
Anisimov, Petr M.
Yampolsky, Nikolai
Scheinker, Alexander
author_facet Leon, Christopher
Anisimov, Petr M.
Yampolsky, Nikolai
Scheinker, Alexander
contents Calculating the effects of Coherent Synchrotron Radiation (CSR) is one of the most computationally expensive tasks in accelerator physics. Here, we use convolutional neural networks (CNN's), along with a latent conditional diffusion (LCD) model, trained on physics-based simulations to speed up calculations. Specifically, we produce the 3D CSR wakefields generated by electron bunches in circular orbit in the steady-state condition. Two datasets are used for training and testing the models: wakefields generated by three-dimensional Gaussian electron distributions and wakefields from a sum of up to 25 three-dimensional Gaussian distributions. The CNN's are able to accurately produce the 3D wakefields $\sim 250-1000$ times faster than the numerical calculations, while the LCD has a gain of a factor of $\sim 34$. We also test the extrapolation and out-of-distribution generalization ability of the models. They generalize well on distributions with larger spreads than what they were trained on, but struggle with smaller spreads.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09551
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Using Convolutional Neural Networks to Accelerate 3D Coherent Synchrotron Radiation Computations
Leon, Christopher
Anisimov, Petr M.
Yampolsky, Nikolai
Scheinker, Alexander
Accelerator Physics
Calculating the effects of Coherent Synchrotron Radiation (CSR) is one of the most computationally expensive tasks in accelerator physics. Here, we use convolutional neural networks (CNN's), along with a latent conditional diffusion (LCD) model, trained on physics-based simulations to speed up calculations. Specifically, we produce the 3D CSR wakefields generated by electron bunches in circular orbit in the steady-state condition. Two datasets are used for training and testing the models: wakefields generated by three-dimensional Gaussian electron distributions and wakefields from a sum of up to 25 three-dimensional Gaussian distributions. The CNN's are able to accurately produce the 3D wakefields $\sim 250-1000$ times faster than the numerical calculations, while the LCD has a gain of a factor of $\sim 34$. We also test the extrapolation and out-of-distribution generalization ability of the models. They generalize well on distributions with larger spreads than what they were trained on, but struggle with smaller spreads.
title Using Convolutional Neural Networks to Accelerate 3D Coherent Synchrotron Radiation Computations
topic Accelerator Physics
url https://arxiv.org/abs/2503.09551