This content will become publicly available on November 6, 2020
Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources
Abstract
Synchrotron light sources, arguably among the most powerful tools of modern scientific discovery, are presently undergoing a major transformation to provide orders of magnitude higher brightness and transverse coherence enabling the most demanding experiments. In these experiments, overall source stability will soon be limited by achievable levels of electron beam size stability, presently on the order of several microns, which is still 1–2 orders of magnitude larger than already demonstrated stability of source position and current. Until now source size stabilization has been achieved through corrections based on a combination of static predetermined physics models and lengthy calibration measurements, periodically repeated to counteract drift in the accelerator and instrumentation. In this paper, we now demonstrate for the first time how the application of machine learning allows for a physics- and model-independent stabilization of source size relying only on previously existing instrumentation. Such feed-forward correction based on a neural network that can be continuously online retrained achieves source size stability as low as 0.2 μm (0.4%) rms, which results in overall source stability approaching the subpercent noise floor of the most sensitive experiments.
- Authors:
-
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Univ. of California, Berkeley, CA (United States). Dept. of Chemistry
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
- OSTI Identifier:
- 1573250
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Physical Review Letters
- Additional Journal Information:
- Journal Volume: 123; Journal Issue: 19; Journal ID: ISSN 0031-9007
- Publisher:
- American Physical Society (APS)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 43 PARTICLE ACCELERATORS; synchrotron light source; storage ring; beam dynamics; insertion device compensation; machine learning
Citation Formats
Leemann, S. C., Liu, S., Hexemer, A., Marcus, M. A., Melton, C. N., Nishimura, H., and Sun, C. Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources. United States: N. p., 2019.
Web. doi:10.1103/PhysRevLett.123.194801.
Leemann, S. C., Liu, S., Hexemer, A., Marcus, M. A., Melton, C. N., Nishimura, H., & Sun, C. Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources. United States. doi:10.1103/PhysRevLett.123.194801.
Leemann, S. C., Liu, S., Hexemer, A., Marcus, M. A., Melton, C. N., Nishimura, H., and Sun, C. Wed .
"Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources". United States. doi:10.1103/PhysRevLett.123.194801.
@article{osti_1573250,
title = {Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources},
author = {Leemann, S. C. and Liu, S. and Hexemer, A. and Marcus, M. A. and Melton, C. N. and Nishimura, H. and Sun, C.},
abstractNote = {Synchrotron light sources, arguably among the most powerful tools of modern scientific discovery, are presently undergoing a major transformation to provide orders of magnitude higher brightness and transverse coherence enabling the most demanding experiments. In these experiments, overall source stability will soon be limited by achievable levels of electron beam size stability, presently on the order of several microns, which is still 1–2 orders of magnitude larger than already demonstrated stability of source position and current. Until now source size stabilization has been achieved through corrections based on a combination of static predetermined physics models and lengthy calibration measurements, periodically repeated to counteract drift in the accelerator and instrumentation. In this paper, we now demonstrate for the first time how the application of machine learning allows for a physics- and model-independent stabilization of source size relying only on previously existing instrumentation. Such feed-forward correction based on a neural network that can be continuously online retrained achieves source size stability as low as 0.2 μm (0.4%) rms, which results in overall source stability approaching the subpercent noise floor of the most sensitive experiments.},
doi = {10.1103/PhysRevLett.123.194801},
journal = {Physical Review Letters},
number = 19,
volume = 123,
place = {United States},
year = {2019},
month = {11}
}
Free Publicly Available Full Text
This content will become publicly available on November 6, 2020
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
DLSR design and plans: an international overview
journal, August 2014
- Hettel, Robert
- Journal of Synchrotron Radiation, Vol. 21, Issue 5
First optics and beam dynamics studies on the MAX IV 3 GeV storage ring
journal, March 2018
- Leemann, S. C.; Sjöström, M.; Andersson, Å.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 883
Chemical composition mapping with nanometre resolution by soft X-ray microscopy
journal, September 2014
- Shapiro, David A.; Yu, Young-Sang; Tyliszczak, Tolek
- Nature Photonics, Vol. 8, Issue 10
Jamming Behavior of Domains in a Spiral Antiferromagnetic System
journal, May 2013
- Chen, S. -W.; Guo, H.; Seu, K. A.
- Physical Review Letters, Vol. 110, Issue 21
Design and performance of the ALS diagnostic beamline
journal, September 1996
- Renner, T. R.; Padmore, H. A.; Keller, R.
- Review of Scientific Instruments, Vol. 67, Issue 9
NEXAFS microscopy and resonant scattering: Composition and orientation probed in real and reciprocal space
journal, February 2008
- Ade, Harald; Hitchcock, Adam P.
- Polymer, Vol. 49, Issue 3
New directions in X-ray microscopy
journal, July 2011
- Falcone, Roger; Jacobsen, Chris; Kirz, Janos
- Contemporary Physics, Vol. 52, Issue 4
A new bend-magnet beamline for scanning transmission X-ray microscopy at the Advanced Light Source
journal, June 2002
- Warwick, Tony; Ade, Harald; Kilcoyne, David
- Journal of Synchrotron Radiation, Vol. 9, Issue 4
Interferometer-controlled scanning transmission X-ray microscopes at the Advanced Light Source
journal, February 2003
- Kilcoyne, A. L. D.; Tyliszczak, T.; Steele, W. F.
- Journal of Synchrotron Radiation, Vol. 10, Issue 2
Local correction schemes to counteract insertion device effects
journal, July 2008
- Chrin, J.; Schmidt, T.; Streun, A.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 592, Issue 3
Vertical emittance reduction and preservation in electron storage rings via resonance driving terms correction
journal, March 2011
- Franchi, A.; Farvacque, L.; Chavanne, J.
- Physical Review Special Topics - Accelerators and Beams, Vol. 14, Issue 3
Coupling control and optimization at the Canadian Light Source
journal, June 2018
- Wurtz, W. A.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 892
Analyses for a planar variably-polarizing undulator
journal, August 1994
- Sasaki, Shigemi
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 347, Issue 1-3
Multilayer feedforward networks are universal approximators
journal, January 1989
- Hornik, Kurt; Stinchcombe, Maxwell; White, Halbert
- Neural Networks, Vol. 2, Issue 5
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Improving Touschek lifetime in ultralow-emittance lattices through systematic application of successive closed vertical dispersion bumps
journal, June 2016
- Breunlin, J.; Leemann, S. C.; Andersson, Å.
- Physical Review Accelerators and Beams, Vol. 19, Issue 6
Backpropagation Applied to Handwritten Zip Code Recognition
journal, December 1989
- LeCun, Y.; Boser, B.; Denker, J. S.
- Neural Computation, Vol. 1, Issue 4
Cross-Validatory Choice and Assessment of Statistical Predictions
journal, January 1974
- Stone, M.
- Journal of the Royal Statistical Society: Series B (Methodological), Vol. 36, Issue 2