- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Improving absorption spectroscopy measurements in attosecond x-ray free-electron laser experiments using machine learning

K. Hu*, O. G. Alexander, F. Egun, and J. P. Marangos†

  • *Contact author: kaiyu.hu19@imperial.ac.uk
  • †Contact author: j.marangos@imperial.ac.uk
PDF

Phys. Rev. Research 8, 033333 – Published 18 September, 2026

DOI: https://doi.org/10.1103/8vc5-pt1f

Abstract

X-ray free-electron lasers (XFELs) provide ultrashort, high-brightness pulses for probing matter on femtosecond and attosecond timescales, but their stochastic shot-to-shot fluctuations make x-ray absorption spectroscopy (XAS) challenging, as both incident and transmitted spectra are required to be measured on the same shot. Conventional approaches that rely on averaged reference spectra have limited accuracy, and full-shot characterizations are impractical. Here, we demonstrate a machine learning approach to bypass these limitations. An artificial neural network predicts the incident spectral shape from recorded diagnostics, effectively providing the equivalent of simultaneous incident spectrum measurements based on recorded machine diagnostics. Applied to XAS of Mylar at the oxygen K-edge, the method improves the accuracy in the pre-edge region (<530.5eV), reducing the root-mean-squared error from 0.0415 to 0.0082OD (optical density). This approach remains highly robust with small target datasets and reduces experimental acquisition time, offering a strategy for more accurate XAS measurements in XFEL experiments where noninvasive, single-shot monitoring of the incident spectrum is not feasible.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (44)

  1. W. Ackermann et al., Operation of a free-electron laser from the extreme ultraviolet to the water window, Nat. Photon. 1, 336 (2007).
  2. P. Emma et al., First lasing and operation of an ångstrom-wavelength free-electron laser, Nat. Photon. 4, 641 (2010).
  3. E. Allaria et al., Highly coherent and stable pulses from the FERMI seeded free-electron laser in the extreme ultraviolet, Nat. Photon. 6, 699 (2012).
  4. T. Ishikawa et al., A compact X-ray free-electron laser emitting in the sub-ångstrom region, Nat. Photon. 6, 540 (2012).
  5. E. Allaria et al., Two-stage seeded soft-X-ray free-electron laser, Nat. Photon. 7, 913 (2013).
  6. H.-S. Kang et al., Hard X-ray free-electron laser with femtosecond-scale timing jitter, Nat. Photon. 11, 708 (2017).
  7. C. J. Milne et al., SwissFEL: The Swiss X-ray free-electron laser, Appl. Sci. 7, 720 (2017).
  8. W. Decking et al., A MHz-repetition-rate hard X-ray free-electron laser driven by a superconducting linear accelerator, Nat. Photon. 14, 391 (2020).
  9. S. E. Posen, Science opportunities and capabilities enabled by LCLS-II and LCLS-II HE, Technical Report FERMILAB-POSTER–20-005-TD, US Government Office of Science and Technology, 2020.
  10. J. Duris et al., Tunable isolated attosecond X-ray pulses with gigawatt peak power from a free-electron laser, Nat. Photon. 14, 30 (2020).
  11. S. Huang, Y. Ding, Y. Feng, E. Hemsing, Z. Huang, J. Krzywinski, A. A. Lutman, A. Marinelli, T. J. Maxwell, and D. Zhu, Terawatt-attosecond hard X-ray free-electron laser at high repetition rate, Nat. Photon. 18, 1293 (2024).
  12. S. Huang, Y. Ding, Y. Feng, E. Hemsing, Z. Huang, J. Krzywinski, A. A. Lutman, A. Marinelli, T. J. Maxwell, and D. Zhu, Generating single-spike hard X-ray pulses with nonlinear bunch compression in free-electron lasers, Phys. Rev. Lett. 119, 154801 (2017).
  13. O. Alexander et al., Attosecond impulsive stimulated X-ray Raman scattering in liquid water, Sci. Adv. 10, eadp0841 (2024).
  14. S. Li et al., Attosecond-pump attosecond-probe X-ray spectroscopy of liquid water, Science 383, 1118 (2024).
  15. T. Driver et al., Attosecond delays in X-ray molecular ionization, Nature (London) 632, 762 (2024).
  16. Z. Guo et al., Experimental demonstration of attosecond pump–probe spectroscopy with an X-ray free-electron laser, Nat. Photon. 18, 691 (2024).
  17. R. Bonifacio, L. De Salvo, P. Pierini, N. Piovella, and C. Pellegrini, Spectrum, temporal structure, and fluctuations in a high-gain free-electron laser starting from noise, Phys. Rev. Lett. 73, 70 (1994).
  18. M. Harmand, M. Cammarata, M. Chollet, A. G. Krygier, H. T. Lemke, and D. Zhu, Single-shot X-ray absorption spectroscopy at X-ray free electron lasers, Sci. Rep. 13, 18203 (2023).
  19. Y. Ding, K. L. F. Bane, W. Colocho, F. J. Decker, P. Emma, J. Frisch, M. W. Guetg, Z. Huang, R. Iverson, J. Krzywinski, H. Loos, A. Lutman, T. J. Maxwell, H. D. Nuhn, D. Ratner, J. Turner, J. Welch, and F. Zhou, Beam shaping to improve the free-electron laser performance at the Linac Coherent Light Source, Phys. Rev. Accel. Beams 19, 100703 (2016).
  20. J. L. Turner, F.-J. Decker, Y. Ding, Z. Huang, R. Iverson, J. Krzywinski, H. Loos, A. Marinelli, T. J. Maxwell, H.-D. Nuhn, D. Ratner, T. Smith, J. Welch, and F. Zhou, FEL overcompression in the LCLS, in Proceedings of the 36th International Free Electron Laser Conference (FEL2014) (JACoW Publishing, Basel, Switzerland, 2014), p. TUB03.
  21. M. Harmand, R. Coffee, M. R. Bionta, M. Chollet, D. French, J. M. Glownia, S. Lee, H. T. Lemke, D. Zhu, and D. M. Fritz, Achieving few-femtosecond time-sorting at hard X-ray free-electron lasers, Nat. Photon. 7, 215 (2013).
  22. V. Kimberg, N. Rohringer, K. Bennett, M. Kowalewski, J.-E. Rubensson, B. W. J. McNeil, I. S. Averbukh, R. Santra, and S. Mukamel, Stimulated X-ray Raman scattering: A critical assessment of the building block of nonlinear X-ray spectroscopy, Faraday Discuss. 194, 305 (2016).
  23. T. Driver et al., Attosecond transient absorption spooktroscopy: A ghost imaging approach to ultrafast absorption spectroscopy, Phys. Chem. Chem. Phys. 22, 2704 (2020).
  24. B. Cheng and D. M. Titterington, Neural networks: A review from a statistical perspective, Stat. Sci. 9, 2 (1994).
  25. K. K. Alaa El-Din, O. G. Alexander, L. J. Frasinski, F. Mintert, Z. Guo, J. Duris, Z. Zhang, D. B. Cesar, P. Franz, T. Driver, P. Walter, J. P. Cryan, A. Marinelli, J. P. Marangos, and R. Mukherjee, Efficient prediction of attosecond two-colour pulses from an X-ray free-electron laser with machine learning, Sci. Rep. 14, 7267 (2024).
  26. X. Ren, Y. Li, X. Yang, Y. Ding, Z. Huang, G. Marcus, T. Maxwell, A. Brachmann, G. Hays, R. Coffee, J. P. Cryan, J. M. Glownia, M. P. Minitti, W. F. Schlotter, D. Zhu, F. Wang, and T. Zhang, Temporal power reconstruction for an X-ray free-electron laser using convolutional neural networks, Phys. Rev. Accel. Beams 23, 040701 (2020).
  27. K. Li, G. Zhou, Y. Liu, J. Wu, M.-F. Lin, X. Cheng, A. A. Lutman, M. Seaberg, H. Smith, P. A. Kakhandiki, and A. Sakdinawat, Prediction on X-ray output of free electron laser based on artificial neural networks, Nat. Commun. 14, 7183 (2023).
  28. A. Sanchez-Gonzalez et al., Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning, Nat. Commun. 8, 15461 (2017).
  29. D. E. F. de Lima, T. Michelat, E. Sobolev, A. Davtyan, O. Turkot, F. Dall’Antonia, M. Sikorski, A. Round, R. de Wijn, J. Möller, S. Birnsteinova, R. Bean, and L. Gelisio, Core principles for machine learning at European XFEL, J. Phys.: Conf. Ser. 3010, 012138 (2025).
  30. D. E. Ferreira de Lima, A. Davtyan, J. Laksman, N. Gerasimova, T. Maltezopoulos, J. Liu, P. Schmidt, T. Michelat, T. Mazza, M. Meyer, J. Grünert, and L. Gelisio, Machine-learning-enhanced automatic spectral characterization of X-ray pulses from a free-electron laser, Commun. Phys. 7, 400 (2024).
  31. L. Breiman, Random forests, Mach. Learn. 45, 5 (2001).
  32. I. T. Jolliffe and J. Cadima, Principal component analysis: A review and recent developments, Philos. Trans. R. Soc. A 374, 20150202 (2016).
  33. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning representations by back-propagating errors, Nature (London) 323, 533 (1986).
  34. T. Korten, V. Rybnikov, P. Steinbach, and N. Mirian, Virtual pulse reconstruction diagnostic for single-shot measurement of free electron laser radiation power, Phys. Rev. Accel. Beams 28, 030703 (2025).
  35. G. Goetzke, R. Plumley, G. Hartmann, T. Maxwell, F.-J. Decker, A. Lutman, M. Dunne, D. Ratner, and J. J. Turner, Femto-PIXAR: A self-supervised neural network method for reconstructing femtosecond X-ray free electron laser pulses, Opt. Express 33, 31235 (2025).
  36. K. Dingel, T. Otto, L. Marder, L. Funke, A. Held, S. Savio, A. Hans, G. Hartmann, D. Meier, J. Viefhaus, B. Sick, A. Ehresmann, M. Ilchen, and W. Helml, Artificial intelligence for online characterization of ultrashort X-ray free-electron laser pulses, Sci. Rep. 12, 17809 (2022).
  37. F. Chollet et al., Keras, 2015, https://keras.io.
  38. V. Nair and G. E. Hinton, Rectified linear units improve restricted Boltzmann machines, in Proceedings of the 27th International Conference on Machine Learning (Omnipress, Madison, 2010), pp. 807–814.
  39. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, in Proceedings of the 3rd International Conference on Learning Representations (ICLR) (OpenReview.net, Alameda, CA, 2015).
  40. E. G. Rightor, A. P. Hitchcock, H. Ade, R. D. Leapman, S. G. Urquhart, A. P. Smith, G. Mitchell, D. Fischer, H. J. Shin, and T. Warwick, Spectromicroscopy of poly(ethylene terephthalate): Comparison of spectra and radiation damage rates in X-ray absorption and electron energy loss, J. Phys. Chem. B 101, 1950 (1997).
  41. I. Ouchi et al., Structure and core electron absorption spectra of polyester films, Jpn. J. Appl. Phys. 38, 183 (1999).
  42. T. Okajima, K. Teramoto, R. Mitsumoto, H. Oji, Y. Yamamoto, I. Mori, H. Ishii, Y. Ouchi, and K. Seki, Polarized NEXAFS spectroscopic studies of poly(butylene terephthalate), poly(ethylene terephthalate), and their model compounds, J. Phys. Chem. A 102, 7093 (1998).
  43. J. Wang, G. A. Botton, M. M. West, and A. P. Hitchcock, Quantitative evaluation of radiation damage to polyethylene terephthalate by soft X-rays and high-energy electrons, J. Phys. Chem. B 113, 1869 (2009).
  44. K. Hu, O. Alexander, F. Egun, and J. Marangos, Improving absorption spectroscopy measurements in attosecond X-ray free electron laser experiments using machine learning [Dataset], Zenodo, 2026, https://doi.org/10.5281/zenodo.20816497

Outline

Information

Phys. Rev. Research 8, 033333– Published 18 September, 2026
  • Received 16 March 2026
  • Accepted 17 August 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation