Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

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

Sanchez-Gonzalez, A. ; Micaelli, P. ; Olivier, C. ; Barillot, T. R. ; Ilchen, M. ; Lutman, A. ; Marinelli, A. ; Maxwell, T ; Achner, A. and Agåker, M. LU , et al. (2017) In Nature Communications 8.
Abstract

Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy, we can accurately predict X-ray properties for... (More)

Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy, we can accurately predict X-ray properties for every shot using only parameters that are easily recorded at high-repetition rate, by training a model on a small set of fully diagnosed pulses. This opens the door to fully realizing the promise of next-generation high-repetition rate X-ray lasers.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Nature Communications
volume
8
article number
15461
publisher
Nature Publishing Group
external identifiers
  • scopus:85020395477
  • wos:000402745000001
  • pmid:28580940
ISSN
2041-1723
DOI
10.1038/ncomms15461
language
English
LU publication?
yes
id
30cdfb2d-ecf4-4c9c-a6d2-386934fced6a
date added to LUP
2017-06-27 10:44:28
date last changed
2023-09-21 08:32:20
@article{30cdfb2d-ecf4-4c9c-a6d2-386934fced6a,
  abstract     = {{<p>Free-electron lasers providing ultra-short high-brightness pulses of X-ray radiation have great potential for a wide impact on science, and are a critical element for unravelling the structural dynamics of matter. To fully harness this potential, we must accurately know the X-ray properties: intensity, spectrum and temporal profile. Owing to the inherent fluctuations in free-electron lasers, this mandates a full characterization of the properties for each and every pulse. While diagnostics of these properties exist, they are often invasive and many cannot operate at a high-repetition rate. Here, we present a technique for circumventing this limitation. Employing a machine learning strategy, we can accurately predict X-ray properties for every shot using only parameters that are easily recorded at high-repetition rate, by training a model on a small set of fully diagnosed pulses. This opens the door to fully realizing the promise of next-generation high-repetition rate X-ray lasers.</p>}},
  author       = {{Sanchez-Gonzalez, A. and Micaelli, P. and Olivier, C. and Barillot, T. R. and Ilchen, M. and Lutman, A. and Marinelli, A. and Maxwell, T and Achner, A. and Agåker, M. and Berrah, N. and Bostedt, C. and Bozek, J. D. and Buck, J. and Bucksbaum, P. H. and Montero, S. Carron and Cooper, B. and Cryan, J. P. and Dong, M and Feifel, R and Frasinski, L. J. and Fukuzawa, H. and Galler, A. and Hartmann, G. and Hartmann, Nils and Helml, W. and Johnson, A. S. and Knie, A. and Lindahl, A. O. and Liu, J. and Motomura, K. and Mucke, M. and O'Grady, Caroline and Rubensson, J E and Simpson, E. R. and Squibb, R J and Såthe, C. and Ueda, K. and Vacher, M. and Walke, D. J. and Zhaunerchyk, V. and Coffee, R. N. and Marangos, J. P}},
  issn         = {{2041-1723}},
  language     = {{eng}},
  month        = {{06}},
  publisher    = {{Nature Publishing Group}},
  series       = {{Nature Communications}},
  title        = {{Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning}},
  url          = {{http://dx.doi.org/10.1038/ncomms15461}},
  doi          = {{10.1038/ncomms15461}},
  volume       = {{8}},
  year         = {{2017}},
}