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

被引：82

作者：

Sanchez-Gonzalez, A. ^{[1
]}

Micaelli, P. ^{[1
]}

Olivier, C. ^{[1
]}

Barillot, T. R. ^{[1
]}

Ilchen, M. ^{[2
,3
]}

Lutman, A. A. ^{[4
]}

Marinelli, A. ^{[4
]}

Maxwell, T. ^{[4
]}

Achner, A. ^{[3
]}

Agaker, M. ^{[5
]}

Berrah, N. ^{[6
]}

Bostedt, C. ^{[4
,7
]}

Bozek, J. D. ^{[8
]}

Buck, J. ^{[9
]}

Bucksbaum, P. H. ^{[2
,10
]}

Montero, S. Carron ^{[4
,11
]}

Cooper, B. ^{[1
]}

Cryan, J. P. ^{[2
]}

Dong, M. ^{[5
]}

Feifel, R. ^{[12
]}

Frasinski, L. J. ^{[1
]}

Fukuzawa, H. ^{[13
]}

Galler, A. ^{[3
]}

Hartmann, G. ^{[9
,14
,15
]}

Hartmann, N. ^{[4
]}

Helml, W. ^{[4
,16
]}

Johnson, A. S. ^{[1
]}

Knie, A. ^{[14
,15
]}

Lindahl, A. O. ^{[2
,12
]}

Liu, J. ^{[3
]}

Motomura, K. ^{[13
]}

Mucke, M. ^{[5
]}

O'Grady, C. ^{[4
]}

Rubensson, J. -E. ^{[5
]}

Simpson, E. R. ^{[1
]}

Squibb, R. J. ^{[12
]}

Sathe, C. ^{[17
]}

Ueda, K. ^{[13
]}

Vacher, M. ^{[18
,19
]}

Walke, D. J. ^{[1
]}

Zhaunerchyk, V. ^{[12
]}

Coffee, R. N. ^{[4
]}

Marangos, J. P. ^{[1
]}

机构：

[1] Imperial Coll London, Dept Phys, London SW7 2AZ, England

[2] SLAC Natl Accelerator Lab, Stanford PULSE Inst, Menlo Pk, CA 94025 USA

[3] European XFEL GmbH, Holzkoppel 4, D-22869 Schenefeld, Germany

[4] SLAC Natl Accelerator Lab, Linac Coherent Light Source, Menlo Pk, CA 94025 USA

[5] Uppsala Univ, Dept Phys & Astron, S-75120 Uppsala, Sweden

[6] Univ Connecticut, Dept Phys, 2152 Hillside Rd,U-3046, Storrs, CT 06269 USA

[7] Argonne Natl Lab, Lemont, IL 60439 USA

[8] Synchrotron SOLEIL, F-91192 Gif Sur Yvette, France

[9] DESY, Notkestr 85, D-22607 Hamburg, Germany

[10] Stanford Univ, Dept Phys, 382 Via Pueblo Mall, Stanford, CA 94305 USA

[11] Calif Lutheran Univ, Dept Phys, 60 West Olsen Rd, Thousand Oaks, CA 91360 USA

[12] Univ Gothenburg, Dept Phys, Origovagen 6B, S-41296 Gothenburg, Sweden

[13] Tohoku Univ, Inst Multidisciplinary Res Adv Mat, Sendai, Miyagi 9808577, Japan

[14] Univ Kassel, Inst Phys, Heinrich Plett Str 40, D-34132 Kassel, Germany

[15] Univ Kassel, CINSaT, Heinrich Plett Str 40, D-34132 Kassel, Germany

[16] Tech Univ Munich, Phys Dept E11, James Franck Str 1, D-85748 Garching, Germany

[17] Lund Univ, MAX Lab 4, Box 118, SE-22100 Lund, Sweden

[18] Imperial Coll, Dept Chem, London SW7 2AZ, England

[19] Uppsala Univ, Dept Chem Angtrom, S-75120 Uppsala, Sweden

来源：

NATURE COMMUNICATIONS | 2017年 / 8卷

基金：

英国工程与自然科学研究理事会; 欧洲研究理事会; 英国科学技术设施理事会; 瑞典研究理事会;

关键词：

NEURAL-NETWORKS; FEMTOSECOND; TIME; PHYSICS; RADIATION; COHERENT; SPECTRA;

D O I：

10.1038/ncomms15461

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

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.

引用

页数：9

共 60 条

[1]

Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265

[2]

Allaria E, 2013, NAT PHOTONICS, V7, P913, DOI [10.1038/NPHOTON.2013.277, 10.1038/nphoton.2013.277]

[3]

Allaria E, 2012, NAT PHOTONICS, V6, P699, DOI [10.1038/nphoton.2012.233, 10.1038/NPHOTON.2012.233]

[4] Control of the Polarization of a Vacuum-Ultraviolet, High-Gain, Free-Electron Laser [J].

Allaria, Enrico ;

Diviacco, Bruno ;

Callegari, Carlo ;

Finetti, Paola ;

Mahieu, Benoit ;

Viefhaus, Jens ;

Zangrando, Marco ;

De Ninno, Giovanni ;

Lambert, Guillaume ;

Ferrari, Eugenio ;

Buck, Jens ;

Ilchen, Markus ;

Vodungbo, Boris ;

Mahne, Nicola ;

Svetina, Cristian ;

Spezzani, Carlo ;

Di Mitri, Simone ;

Penco, Giuseppe ;

Trovo, Mauro ;

Fawley, William M. ;

Rebernik, Primoz R. ;

Gauthier, David ;

Grazioli, Cesare ;

Coreno, Marcello ;

Ressel, Barbara ;

Kivimaeki, Antti ;

Mazza, Tommaso ;

Glaser, Leif ;

Scholz, Frank ;

Seltmann, Joern ;

Gessler, Patrick ;

Gruenert, Jan ;

De Fanis, Alberto ;

Meyer, Michael ;

Knie, Andre ;

Moeller, Stefan P. ;

Raimondi, Lorenzo ;

Capotondi, Flavio ;

Pedersoli, Emanuele ;

Plekan, Oksana ;

Danailov, Miltcho B. ;

Demidovich, Alexander ;

Nikolov, Ivaylo ;

Abrami, Alessandro ;

Gautier, Julien ;

Luening, Jan ;

Zeitoun, Philippe ;

Giannessi, Luca .

PHYSICAL REVIEW X, 2014, 4 (04)

[5]

Altarelli M., 2006, TECH REP, V97

[6]

[Anonymous], TECHNICAL REPORT

[7]

[Anonymous], ADV APPL STAT SER, DOI DOI 10.1214/ss/1177010638

[8]

Atlas Collaboration, 2014, J INSTRUM, V9

[9] A convolutional neural network neutrino event classifier [J].

Aurisano, A. ;

Radovic, A. ;

Rocco, D. ;

Himmel, A. ;

Messier, M. D. ;

Niner, E. ;

Pawloski, G. ;

Psihas, F. ;

Sousa, A. ;

Vahle, P. .

JOURNAL OF INSTRUMENTATION, 2016, 11

[10] Searching for exotic particles in high-energy physics with deep learning [J].

Baldi, P. ;

Sadowski, P. ;

Whiteson, D. .

NATURE COMMUNICATIONS, 2014, 5

← 1 2 3 4 5 6 →