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

Title: Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources

Journal Article · · Physical Review Letters
 [1];  [2];  [1];  [1];  [1];  [1];  [1]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Univ. of California, Berkeley, CA (United States). Dept. of Chemistry
+ Show Author Affiliations

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. 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.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES); USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1573250
Alternate ID(s):
OSTI ID: 1581385
Journal Information:
Physical Review Letters, Vol. 123, Issue 19; ISSN 0031-9007
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 24 works
Citation information provided by
Web of Science

References (19)

Design and performance of the ALS diagnostic beamline journal September 1996
New directions in X-ray microscopy journal July 2011
Deep learning journal May 2015
Chemical composition mapping with nanometre resolution by soft X-ray microscopy journal September 2014
Coupling control and optimization at the Canadian Light Source journal June 2018
Multilayer feedforward networks are universal approximators journal January 1989
First optics and beam dynamics studies on the MAX IV 3 GeV storage ring
  • Leemann, S. C.; Sjöström, M.; Andersson, Å.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 883 https://doi.org/10.1016/j.nima.2017.11.072
journal March 2018
Local correction schemes to counteract insertion device effects
  • 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 https://doi.org/10.1016/j.nima.2008.04.016
journal July 2008
Improving Touschek lifetime in ultralow-emittance lattices through systematic application of successive closed vertical dispersion bumps journal June 2016
Cross-Validatory Choice and Assessment of Statistical Predictions journal January 1974
A new bend-magnet beamline for scanning transmission X-ray microscopy at the Advanced Light Source journal June 2002
Vertical emittance reduction and preservation in electron storage rings via resonance driving terms correction journal March 2011
Jamming Behavior of Domains in a Spiral Antiferromagnetic System journal May 2013
NEXAFS microscopy and resonant scattering: Composition and orientation probed in real and reciprocal space journal February 2008
DLSR design and plans: an international overview journal August 2014
Analyses for a planar variably-polarizing undulator journal August 1994
Backpropagation Applied to Handwritten Zip Code Recognition journal December 1989
First Optics and Beam Dynamics Studies on the MAX IV 3 GeV Storage Ring text January 2017
Deep Learning text January 2018

Cited By (2)

Machine learning for beam dynamics studies at the CERN Large Hadron Collider
  • Arpaia, P.; Azzopardi, G.; Blanc, F.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 985 https://doi.org/10.1016/j.nima.2020.164652
journal January 2021
High-fidelity Prediction of Megapixel Longitudinal Phase-Space Images of Electron Beams Using Encoder-Decoder Neural Networks text January 2021

Similar Records

Related Subjects

43 PARTICLE ACCELERATORS
synchrotron light source
storage ring
beam dynamics
insertion device compensation
machine learning