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. 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; Nils Hartmann; W. Helml; A. S. Johnson; A. Knie; A. O. Lindahl; J. Liu; K. Motomura; M. Mucke; Caroline 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

doi:10.1038/ncomms15461

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. 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 FeifelL. J. Frasinski, H. Fukuzawa, A. Galler, G. Hartmann, Nils Hartmann, W. Helml, A. S. Johnson, A. Knie, A. O. Lindahl, J. Liu, K. Motomura, M. Mucke, Caroline 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

MAX IV Laboratory

Research output: Contribution to journal › Article › peer-review

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 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.

Original language	English
Article number	15461
Journal	Nature Communications
Volume	8
DOIs	https://doi.org/10.1038/ncomms15461
Publication status	Published - 2017 Jun 5

Subject classification (UKÄ)

Atom and Molecular Physics and Optics

Access to Document

10.1038/ncomms15461

Cite this

Sanchez-Gonzalez, A., Micaelli, P., Olivier, C., Barillot, T. R., Ilchen, M., Lutman, A., Marinelli, A., Maxwell, T., Achner, A., Agåker, M., Berrah, N., Bostedt, C., Bozek, J. D., Buck, J., Bucksbaum, P. H., Montero, S. C., Cooper, B., Cryan, J. P., Dong, M., ... Marangos, J. P. (2017). Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning. Nature Communications, 8, Article 15461. https://doi.org/10.1038/ncomms15461

@article{30cdfb2decf44c9ca6d2386934fced6a,

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

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 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.",

author = "A. Sanchez-Gonzalez and P. Micaelli and C. Olivier and Barillot, {T. R.} and M. Ilchen and A. Lutman and A. Marinelli and T Maxwell and A. Achner and M. Ag{\aa}ker and N. Berrah and C. Bostedt and Bozek, {J. D.} and J. Buck and Bucksbaum, {P. H.} and Montero, {S. Carron} and B. Cooper and Cryan, {J. P.} and M Dong and R Feifel and Frasinski, {L. J.} and H. Fukuzawa and A. Galler and G. Hartmann and Nils Hartmann and W. Helml and Johnson, {A. S.} and A. Knie and Lindahl, {A. O.} and J. Liu and K. Motomura and M. Mucke and Caroline O'Grady and Rubensson, {J E} and Simpson, {E. R.} and Squibb, {R J} and C. S{\aa}the and K. Ueda and M. Vacher and Walke, {D. J.} and V. Zhaunerchyk and Coffee, {R. N.} and Marangos, {J. P}",

year = "2017",

month = jun,

day = "5",

doi = "10.1038/ncomms15461",

language = "English",

volume = "8",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

}

Sanchez-Gonzalez, A, Micaelli, P, Olivier, C, Barillot, TR, Ilchen, M, Lutman, A, Marinelli, A, Maxwell, T, Achner, A, Agåker, M, Berrah, N, Bostedt, C, Bozek, JD, Buck, J, Bucksbaum, PH, Montero, SC, Cooper, B, Cryan, JP, Dong, M, Feifel, R, Frasinski, LJ, Fukuzawa, H, Galler, A, Hartmann, G, Hartmann, N, Helml, W, Johnson, AS, Knie, A, Lindahl, AO, Liu, J, Motomura, K, Mucke, M, O'Grady, C, Rubensson, JE, Simpson, ER, Squibb, RJ, Såthe, C, Ueda, K, Vacher, M, Walke, DJ, Zhaunerchyk, V, Coffee, RN & Marangos, JP 2017, 'Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning', Nature Communications, vol. 8, 15461. https://doi.org/10.1038/ncomms15461

TY - JOUR

T1 - Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning

AU - Sanchez-Gonzalez, A.

AU - Micaelli, P.

AU - Olivier, C.

AU - Barillot, T. R.

AU - Ilchen, M.

AU - Lutman, A.

AU - Marinelli, A.

AU - Maxwell, T

AU - Achner, A.

AU - Agåker, M.

AU - Berrah, N.

AU - Bostedt, C.

AU - Bozek, J. D.

AU - Buck, J.

AU - Bucksbaum, P. H.

AU - Montero, S. Carron

AU - Cooper, B.

AU - Cryan, J. P.

AU - Dong, M

AU - Feifel, R

AU - Frasinski, L. J.

AU - Fukuzawa, H.

AU - Galler, A.

AU - Hartmann, G.

AU - Hartmann, Nils

AU - Helml, W.

AU - Johnson, A. S.

AU - Knie, A.

AU - Lindahl, A. O.

AU - Liu, J.

AU - Motomura, K.

AU - Mucke, M.

AU - O'Grady, Caroline

AU - Rubensson, J E

AU - Simpson, E. R.

AU - Squibb, R J

AU - Såthe, C.

AU - Ueda, K.

AU - Vacher, M.

AU - Walke, D. J.

AU - Zhaunerchyk, V.

AU - Coffee, R. N.

AU - Marangos, J. P

PY - 2017/6/5

Y1 - 2017/6/5

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85020395477&partnerID=8YFLogxK

U2 - 10.1038/ncomms15461

DO - 10.1038/ncomms15461

M3 - Article

C2 - 28580940

AN - SCOPUS:85020395477

SN - 2041-1723

VL - 8

JO - Nature Communications

JF - Nature Communications

M1 - 15461

ER -

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

Abstract

Subject classification (UKÄ)

Access to Document

Other files and links

Fingerprint

Cite this