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

Title: Bayesian Optimization of a Free-Electron Laser

Abstract

The Linac Coherent Light Source X-ray free-electron laser is a complex scienti c apparatus which changes con gurations multiple times per day, necessitating fast tuning strategies to reduce setup time for successive experiments. To this end, we employ a Bayesian approach to maximizing X- ray laser pulse energy by controlling groups of quadrupole magnets. A Gaussian process model provides probabilistic predictions for the machine response with respect to control parameters, enabling a balance of exploration and exploitation in the search for the global optimum. We show that the model parameters can be learned from archived scans, and correlations between devices can be extracted from the beam transport. Furthermore, the result is a sample-e cient optimization routine, combining both historical data and knowledge of accelerator physics to signi cantly outperform existing optimizers.

Authors:
ORCiD logo [1];  [2]; ORCiD logo [1]; ORCiD logo [1];  [1];  [1]; ORCiD logo [1];  [1];  [3];  [3];  [1]
  1. SLAC National Accelerator Lab., Menlo Park, CA (United States)
  2. SLAC National Accelerator Lab., Menlo Park, CA (United States); Univ. of California, Santa Cruz, CA (United States)
  3. Stanford Univ., CA (United States)
Publication Date:
Research Org.:
SLAC National Accelerator Lab., Menlo Park, CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC)
OSTI Identifier:
1601837
Alternate Identifier(s):
OSTI ID: 1606282
Grant/Contract Number:  
AC02-76SF00515
Resource Type:
Accepted Manuscript
Journal Name:
Physical Review Letters
Additional Journal Information:
Journal Volume: 124; Journal Issue: 12; Journal ID: ISSN 0031-9007
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
47 OTHER INSTRUMENTATION; accelerator/storage ring control systems; beam optics correction schemes; beam optics transport; optimization problems; free-electron lasers; Bayesian methods; machine learning

Citation Formats

Duris, Joseph, Kennedy, D., Hanuka, A., Shtalenkova, J., Edelen, A., Baxevanis, P., Egger, A., Cope, T., McIntire, M., Ermon, S., and Ratner, D. Bayesian Optimization of a Free-Electron Laser. United States: N. p., 2020. Web. doi:10.1103/PhysRevLett.124.124801.
Duris, Joseph, Kennedy, D., Hanuka, A., Shtalenkova, J., Edelen, A., Baxevanis, P., Egger, A., Cope, T., McIntire, M., Ermon, S., & Ratner, D. Bayesian Optimization of a Free-Electron Laser. United States. doi:https://doi.org/10.1103/PhysRevLett.124.124801
Duris, Joseph, Kennedy, D., Hanuka, A., Shtalenkova, J., Edelen, A., Baxevanis, P., Egger, A., Cope, T., McIntire, M., Ermon, S., and Ratner, D. Wed . "Bayesian Optimization of a Free-Electron Laser". United States. doi:https://doi.org/10.1103/PhysRevLett.124.124801. https://www.osti.gov/servlets/purl/1601837.
@article{osti_1601837,
title = {Bayesian Optimization of a Free-Electron Laser},
author = {Duris, Joseph and Kennedy, D. and Hanuka, A. and Shtalenkova, J. and Edelen, A. and Baxevanis, P. and Egger, A. and Cope, T. and McIntire, M. and Ermon, S. and Ratner, D.},
abstractNote = {The Linac Coherent Light Source X-ray free-electron laser is a complex scienti c apparatus which changes con gurations multiple times per day, necessitating fast tuning strategies to reduce setup time for successive experiments. To this end, we employ a Bayesian approach to maximizing X- ray laser pulse energy by controlling groups of quadrupole magnets. A Gaussian process model provides probabilistic predictions for the machine response with respect to control parameters, enabling a balance of exploration and exploitation in the search for the global optimum. We show that the model parameters can be learned from archived scans, and correlations between devices can be extracted from the beam transport. Furthermore, the result is a sample-e cient optimization routine, combining both historical data and knowledge of accelerator physics to signi cantly outperform existing optimizers.},
doi = {10.1103/PhysRevLett.124.124801},
journal = {Physical Review Letters},
number = 12,
volume = 124,
place = {United States},
year = {2020},
month = {3}
}

Works referenced in this record:

The origins of kriging
journal, April 1990


Robust simplex algorithm for online optimization
journal, October 2018


Model-independent particle accelerator tuning
journal, October 2013

  • Scheinker, Alexander; Pang, Xiaoying; Rybarcyk, Larry
  • Physical Review Special Topics - Accelerators and Beams, Vol. 16, Issue 10
  • DOI: 10.1103/PhysRevSTAB.16.102803

A Kriging-Based Approach to Autonomous Experimentation with Applications to X-Ray Scattering
journal, August 2019


First lasing and operation of an ångstrom-wavelength free-electron laser
journal, August 2010


Model-independent tuning for maximizing free electron laser pulse energy
journal, August 2019


Online optimization of storage ring nonlinear beam dynamics
journal, August 2015


Commissioning the Linac Coherent Light Source injector
journal, March 2008


A Simplex Method for Function Minimization
journal, January 1965


Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
journal, May 2012

  • Srinivas, Niranjan; Krause, Andreas; Kakade, Sham M.
  • IEEE Transactions on Information Theory, Vol. 58, Issue 5
  • DOI: 10.1109/TIT.2011.2182033

GENESIS 1.3: a fully 3D time-dependent FEL simulation code
journal, June 1999

  • Reiche, S.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 429, Issue 1-3
  • DOI: 10.1016/S0168-9002(99)00114-X

Minimization of Betatron Oscillations of Electron Beam Injected Into a Time-Varying Lattice via Extremum Seeking
journal, January 2018

  • Scheinker, Alexander; Huang, Xiaobiao; Wu, Juhao
  • IEEE Transactions on Control Systems Technology, Vol. 26, Issue 1
  • DOI: 10.1109/TCST.2017.2664728

Probabilistic programming in Python using PyMC3
journal, January 2016

  • Salvatier, John; Wiecki, Thomas V.; Fonnesbeck, Christopher
  • PeerJ Computer Science, Vol. 2
  • DOI: 10.7717/peerj-cs.55

A Differentiable Physics Engine for Deep Learning in Robotics
journal, March 2019


Taking the Human Out of the Loop: A Review of Bayesian Optimization
journal, January 2016


A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot
journal, August 2009


Kriging in the hydrosciences
journal, September 1978


Every good regulator of a system must be a model of that system †
journal, October 1970