Author: Hanuka, A.
Paper Title Page
THBO01 Machine Learning-Based Longitudinal Phase Space Prediction of Two-Bunch Operation at FACET-II 678
 
  • C. Emma, A.L. Edelen, M.J. Hogan, B.D. O’Shea, V. Yakimenko
    SLAC, Menlo Park, California, USA
  • A. Hanuka
    Technion, Haifa, Israel
 
  Funding: This work was supported by the U.S. Department of Energy under Contract No. DEAC02-76SF00515
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.
References:
* C. Emma, A. Edelen, M. J. Hogan, B. O’Shea, G. White, and V. Yakimenko., PRAB 21, 112802 (2018)
** A. Scheinker, A. Edelen, D. Bohler, C. Emma, A. Lutman., PRL 121, 044801 (2018)
 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2019-THBO01  
About • paper received ※ 04 September 2019       paper accepted ※ 10 September 2019       issue date ※ 10 November 2019  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)