skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine learning-based longitudinal phase space prediction of particle accelerators

Abstract

Here, we report on the application of machine learning (ML) methods for predicting the longitudinal phase space (LPS) distribution of particle accelerators. Our approach consists of training a ML-based virtual diagnostic to predict the LPS using only nondestructive linac and e-beam measurements as inputs. We validate this approach with a simulation study for the FACET-II linac and with an experimental demonstration conducted at LCLS. At LCLS, the e-beam LPS images are obtained with a transverse deflecting cavity and used as training data for our ML model. In both the FACET-II and LCLS cases we find good agreement between the predicted and simulated/measured LPS profiles, an important step towards showing the feasibility of implementing such a virtual diagnostic on particle accelerators in the future.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1]
  1. SLAC National Accelerator Lab., Menlo Park, CA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1482420
Alternate Identifier(s):
OSTI ID: 1490386
Grant/Contract Number:  
AC02-76SF00515
Resource Type:
Published Article
Journal Name:
Physical Review Accelerators and Beams
Additional Journal Information:
Journal Volume: 21; Journal Issue: 11; Journal ID: ISSN 2469-9888
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
43 PARTICLE ACCELERATORS

Citation Formats

Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., and Yakimenko, V. Machine learning-based longitudinal phase space prediction of particle accelerators. United States: N. p., 2018. Web. doi:10.1103/physrevaccelbeams.21.112802.
Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., & Yakimenko, V. Machine learning-based longitudinal phase space prediction of particle accelerators. United States. doi:10.1103/physrevaccelbeams.21.112802.
Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., and Yakimenko, V. Fri . "Machine learning-based longitudinal phase space prediction of particle accelerators". United States. doi:10.1103/physrevaccelbeams.21.112802.
@article{osti_1482420,
title = {Machine learning-based longitudinal phase space prediction of particle accelerators},
author = {Emma, C. and Edelen, A. and Hogan, M. J. and O’Shea, B. and White, G. and Yakimenko, V.},
abstractNote = {Here, we report on the application of machine learning (ML) methods for predicting the longitudinal phase space (LPS) distribution of particle accelerators. Our approach consists of training a ML-based virtual diagnostic to predict the LPS using only nondestructive linac and e-beam measurements as inputs. We validate this approach with a simulation study for the FACET-II linac and with an experimental demonstration conducted at LCLS. At LCLS, the e-beam LPS images are obtained with a transverse deflecting cavity and used as training data for our ML model. In both the FACET-II and LCLS cases we find good agreement between the predicted and simulated/measured LPS profiles, an important step towards showing the feasibility of implementing such a virtual diagnostic on particle accelerators in the future.},
doi = {10.1103/physrevaccelbeams.21.112802},
journal = {Physical Review Accelerators and Beams},
number = 11,
volume = 21,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: 10.1103/physrevaccelbeams.21.112802

Citation Metrics:
Cited by: 2 works
Citation information provided by
Web of Science

Figures / Tables:

FIG. 1 FIG. 1: Schematic of the FACET-II and LCLS electron accelerators and example LPS profiles from particle tracking simulations (FACET-II), experimental measurements (LCLS) and from the ML-based virtual diagnostic predictions. The figure highlights the similarities between the two accelerator layouts up to the BC20 chicane in FACET-II which is used tomore » increase the current from 3–4 kA to 10–200 kA.« less

Save / Share:

Works referenced in this record:

Ultralow emittance electron beams from a laser-wakefield accelerator
journal, November 2012

  • Weingartner, R.; Raith, S.; Popp, A.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 15, Issue 11
  • DOI: 10.1103/PhysRevSTAB.15.111302

Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution
journal, July 2018


Adaptive method for electron bunch profile prediction
journal, October 2015

  • Scheinker, Alexander; Gessner, Spencer
  • Physical Review Special Topics - Accelerators and Beams, Vol. 18, Issue 10
  • DOI: 10.1103/PhysRevSTAB.18.102801

Deep learning
journal, May 2015

  • LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
  • Nature, Vol. 521, Issue 7553
  • DOI: 10.1038/nature14539

Measured Emittance Dependence on the Injection Method in Laser Plasma Accelerators
journal, September 2017


Few-femtosecond time-resolved measurements of X-ray free-electron lasers
journal, April 2014

  • Behrens, C.; Decker, F. -J.; Ding, Y.
  • Nature Communications, Vol. 5, Issue 1
  • DOI: 10.1038/ncomms4762

Plasma wakefield acceleration experiments at FACET II
journal, January 2018


Neural Networks for Modeling and Control of Particle Accelerators
journal, April 2016

  • Edelen, A. L.; Biedron, S. G.; Chase, B. E.
  • IEEE Transactions on Nuclear Science, Vol. 63, Issue 2
  • DOI: 10.1109/TNS.2016.2543203

Coherent off-axis undulator radiation from short electron bunches
journal, March 2000

  • Neuman, C. P.; Graves, W. S.; O'Shea, P. G.
  • Physical Review Special Topics - Accelerators and Beams, Vol. 3, Issue 3
  • DOI: 10.1103/PhysRevSTAB.3.030701

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning
journal, June 2017

  • Sanchez-Gonzalez, A.; Micaelli, P.; Olivier, C.
  • Nature Communications, Vol. 8, Issue 1
  • DOI: 10.1038/ncomms15461

    Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.