Nature Communications (Jun 2017)
Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning
- A. Sanchez-Gonzalez,
- P. Micaelli,
- C. Olivier,
- T. R. Barillot,
- M. Ilchen,
- A. A. Lutman,
- A. Marinelli,
- T. Maxwell,
- A. Achner,
- M. Agåker,
- N. Berrah,
- C. Bostedt,
- J. D. Bozek,
- J. Buck,
- P. H. Bucksbaum,
- S. Carron Montero,
- B. Cooper,
- J. P. Cryan,
- M. Dong,
- R. Feifel,
- L. J. Frasinski,
- H. Fukuzawa,
- A. Galler,
- G. Hartmann,
- N. Hartmann,
- W. Helml,
- A. S. Johnson,
- A. Knie,
- A. O. Lindahl,
- J. Liu,
- K. Motomura,
- M. Mucke,
- C. O’Grady,
- J-E Rubensson,
- E. R. Simpson,
- R. J. Squibb,
- C. Såthe,
- K. Ueda,
- M. Vacher,
- D. J. Walke,
- V. Zhaunerchyk,
- R. N. Coffee,
- J. P. Marangos
Affiliations
- A. Sanchez-Gonzalez
- Department of Physics, Imperial College London
- P. Micaelli
- Department of Physics, Imperial College London
- C. Olivier
- Department of Physics, Imperial College London
- T. R. Barillot
- Department of Physics, Imperial College London
- M. Ilchen
- Stanford PULSE Institute, SLAC National Accelerator Laboratory
- A. A. Lutman
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- A. Marinelli
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- T. Maxwell
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- A. Achner
- European XFEL GmbH
- M. Agåker
- Department of Physics and Astronomy, Uppsala University
- N. Berrah
- Department of Physics, University of Connecticut
- C. Bostedt
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- J. D. Bozek
- Synchrotron SOLEIL, L’Orme des Merisiers, Saint Aubin
- J. Buck
- Deutsches Elektronen-Synchrotron DESY
- P. H. Bucksbaum
- Stanford PULSE Institute, SLAC National Accelerator Laboratory
- S. Carron Montero
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- B. Cooper
- Department of Physics, Imperial College London
- J. P. Cryan
- Stanford PULSE Institute, SLAC National Accelerator Laboratory
- M. Dong
- Department of Physics and Astronomy, Uppsala University
- R. Feifel
- Department of Physics, University of Gothenburg
- L. J. Frasinski
- Department of Physics, Imperial College London
- H. Fukuzawa
- Institute of Multidisciplinary Research for Advanced Materials, Tohoku University
- A. Galler
- European XFEL GmbH
- G. Hartmann
- Deutsches Elektronen-Synchrotron DESY
- N. Hartmann
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- W. Helml
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- A. S. Johnson
- Department of Physics, Imperial College London
- A. Knie
- Institut für Physik und CINSaT, Universität Kassel
- A. O. Lindahl
- Stanford PULSE Institute, SLAC National Accelerator Laboratory
- J. Liu
- European XFEL GmbH
- K. Motomura
- Institute of Multidisciplinary Research for Advanced Materials, Tohoku University
- M. Mucke
- Department of Physics and Astronomy, Uppsala University
- C. O’Grady
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- J-E Rubensson
- Department of Physics and Astronomy, Uppsala University
- E. R. Simpson
- Department of Physics, Imperial College London
- R. J. Squibb
- Department of Physics, University of Gothenburg
- C. Såthe
- MAX IV Laboratory, Lund University
- K. Ueda
- Institute of Multidisciplinary Research for Advanced Materials, Tohoku University
- M. Vacher
- Department of Chemistry, Imperial College
- D. J. Walke
- Department of Physics, Imperial College London
- V. Zhaunerchyk
- Department of Physics, University of Gothenburg
- R. N. Coffee
- Linac Coherent Light Source, SLAC National Accelerator Laboratory
- J. P. Marangos
- Department of Physics, Imperial College London
- DOI
- https://doi.org/10.1038/ncomms15461
- Journal volume & issue
-
Vol. 8,
no. 1
pp. 1 – 9
Abstract
X-ray free-electron lasers, important light sources for materials research, suffer from shot-to-shot fluctuations that necessitate complex diagnostics. Here, the authors apply machine learning to accurately predict pulse properties, using parameters that can be acquired at high-repetition rates.
