- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Accelerators and Beams

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

Using convolutional neural networks to accelerate three-dimensional coherent synchrotron radiation computations

Christopher Leon*, Petr M. Anisimov, Nikolai Yampolsky, and Alexander Scheinker

  • *Contact author: cleon@lanl.gov
PDF

Phys. Rev. Accel. Beams 28, 110701 – Published 4 November, 2025

DOI: https://doi.org/10.1103/2v1x-c97j

Abstract

Calculating the effects of coherent synchrotron radiation (CSR) is one of the most computationally expensive tasks in accelerator physics. Here, we use convolutional neural networks (CNNs), along with a latent conditional diffusion (LCD) model, trained on physics-based simulations to speed up calculations. Specifically, we produce the 3D CSR wakefields generated by electron bunches in circular orbit in the steady-state condition. Two datasets are used for training and testing the models: wakefields generated by three-dimensional Gaussian electron distributions and wakefields from a sum of up to 25 three-dimensional Gaussian distributions. The CNNs are able to accurately produce the 3D wakefields ∼250–1000 times faster than the numerical calculations, while the LCD achieves a gain of a factor of ∼34. We also test the extrapolation and out-of-distribution generalization ability of the models. They generalize well on distributions with larger spreads than what they were trained on but struggle with smaller spreads.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (54)

  1. Y. S. Derbenev, J. Rossbach, E. L. Saldin, and V. D. Shiltsev, Microbunch radiative tail—head interaction, DESY, Report No. PRINT-98-023.
  2. C. E. Mayes, Computational approaches to coherent synchrotron radiation in two and three dimensions, J. Instrum. 16, P10010 (2021).
  3. Christopher Mayes, ChristopherMayes/pycsr3d: pycsr3d version 0.2.0, Zenodo, 2021, 10.5281/zenodo.5496096.
  4. Alfred Liénard, Champ électrique et Magnétique Produit Par Une Charge électrique Concentrée en Un Point et Animée d’un Mouvement Quelconque (G. Carré et C. Naud, Paris, France, 1898).
  5. Emil Wiechert, Elektrodynamische elementargesetze, Ann. Phys. (Berlin), 309, 667 (1901).
  6. John David Jackson, Classical Electrodynamics (American Association of Physics Teachers, New York, NY, 1999).
  7. J. C. Baez, Struggles with the continuum, arXiv:1609.01421.
  8. G. Stupakov and P. Emma, CSR wake for a short magnet in ultrarelativistic limit, in Proceedings of the 8th European Particle Accelerator Conference, Paris, France (2002), Report No. SLAC-PUB-9242.
  9. B. E. Carlsten and T. O. Raubenheimer, Emittance growth of bunched beams in bends, Phys. Rev. E 51, 1453 (1995).
  10. E. L. Saldin, E. A. Schneidmiller, and M. V. Yurkov, On the coherent radiation of an electron bunch moving in an arc of a circle, Nucl. Instrum. Methods Phys. Res., Sect. A 398, 373 (1997).
  11. Michael Borland, elegant: A flexible SDDS-compliant code for accelerator simulation, Technical Report, Argonne National Laboratory, Argonne, IL, 2000, 10.2172/761286.
  12. M. Borland, Simple method for particle tracking with coherent synchrotron radiation, Phys. Rev. ST Accel. Beams 4, 070701 (2001).
  13. M. Dohlus and T. Limberg, csrtrack: Faster calculation of 3-D CSR effects, in Proceedings of the 2004 FEL Conference (2004), https://proceedings.jacow.org/f04/papers/MOCOS05/MOCOS05.PDF.
  14. M. Dohlus and T. Limberg, csrtrack Version 1.2 User’s Manual (DESY, Hamburg, Germany, 2007).
  15. C. Huang, T. J. T. Kwan, and B. E. Carlsten, Two dimensional model for coherent synchrotron radiation, Phys. Rev. ST Accel. Beams 16, 010701 (2013).
  16. C. E. Mitchell, J. Qiang, R. D. Ryne, B. E. Carlsten, and N. A. Yampolsky, Large-scale simulation of synchrotron radiation using a Lienard-Wiechert approach, Conf. Proc. C 1205201, 1689 (2012), https://proceedings.jacow.org/IPAC2012/papers/tuppp036.pdf?n=IPAC2012/papers/TUPPP036.pdf.
  17. R. Ryne, B. Carlsten, C. Mitchell, and J. Qiang, Self-consistent modeling using a Lienard-Wiechert particle-mesh method, in Proceedings of the 9th International Particle Accelerator Conference (IPAC2018), Vancouver, BC, Canada (JACoW, Geneva, Switzerland, 2018), 10.18429/JACoW-IPAC2018-THPAK044.
  18. Alexander Novokhatski, Coherent Synchrotron Radiation: Theory and Simulations (Citeseer, Menlo Park, CA, 2012).
  19. A. D. Brynes, P. Smorenburg, I. Akkermans, E. Allaria, L. Badano, S. Brussaard, M. Danailov, A. Demidovich, G. De Ninno, D. Gauthier et al., Beyond the limits of 1D coherent synchrotron radiation, New J. Phys. 20, 073035 (2018).
  20. Y. Cai, Coherent synchrotron radiation by electrons moving on circular orbits, Phys. Rev. Accel. Beams 20, 064402 (2017).
  21. Y. Cai and Y. Ding, Three-dimensional effects of coherent synchrotron radiation by electrons in a bunch compressor, Phys. Rev. Accel. Beams 23, 014402 (2020).
  22. Y. Cai, Two-dimensional theory of coherent synchrotron radiation with transient effects, Phys. Rev. Accel. Beams 24, 064402 (2021).
  23. E. D. Courant and H. S. Snyder, Theory of the alternating gradient synchrotron, Ann. Phys. (N.Y.) 3, 1 (1958).
  24. G. Stupakov and G. Penn, Classical Mechanics and Electromagnetism in Accelerator Physics (Springer, New York, 2018), ISBN [Amazon][WorldCat], 10.1007/978-3-319-90188-6.
  25. H. Xu, P. M. Anisimov, L. D. Duffy, and Q. R. Marksteiner, Comparison study on first bunch compressor schemes by conventional and double C-chicane for MaRIE XFEL, in Proceedings of the 5th International Particle Accelerator Conference (NAPAC2022), Albuquerque, NM, USA (JACoW, Geneva, Switzerland, 2022), TUPA72, 10.18429/JACoW-NAPAC2022-TUPA72.
  26. Haoran Xu, Petr M. Anisimov, Bruce E. Carlsten, Leanne D. Duffy, Quinn R. Marksteiner, and River R. Robles, X-ray free electron laser accelerator lattice design using laser-assisted bunch compression, Appl. Sci. 13, 2285 (2023).
  27. Yann LeCun, Bernhard Boser, John S. Denker, Donnie Henderson, Richard E. Howard, Wayne Hubbard, and Lawrence D. Jackel, Backpropagation applied to handwritten zip code recognition, in Neural Computation (MIT Press, Cambridge, MA, 1989), Vol. 1, pp. 541–551.
  28. A. Scheinker and R. Pokharel, Physics-constrained 3D convolutional neural networks for electrodynamics, APL Mach. Learn. 1, 026109 (2023).
  29. C. Leon and A. Scheinker, Physics-constrained machine learning for electrodynamics without gauge ambiguity based on Fourier transformed Maxwell’s equations, Sci. Rep. 14, 14809 (2024).
  30. A. Edelen, C. Emma, C. Mayes, and R. Roussel, Neural network solver for coherent synchrotron radiation wakefield calculations in accelerator-based charged particle beams, in Proceedings of the 13th International Particle Accelerator Conference (IPAC2022), Bangkok, Thailand (JACoW, Geneva, Switzerland, 2022), WEPOMS013, 10.18429/JACoW-IPAC2022-WEPOMS013.
  31. R. Robles, A. Edelen, W. Lou, C. Mayes, and R. Roussel, Efficient computation of two-dimensional coherent synchrotron radiation with neural networks, in Proceedings of the 14th International Particle Accelerator Conference (IPAC2023), Venice, Italy (JACoW, Geneva, Switzerland, 2023), WEPA105, 10.18429/JACoW-IPAC2023-WEPA105.
  32. J. P. Gonzalez-Aguilera, R. Roussel, A. Edelen, and Y. K. Kim, Detailed characterization of coherent synchrotron radiation effects using generative phase space reconstruction, in Proceedings of the 15th International Particle Accelerator Conference (IPAC2024), Nashville, TN (JACoW, Geneva, Switzerland, 2024), WEPG94, 10.18429/JACoW-IPAC2024-WEPG94.
  33. Olaf Ronneberger, Philipp Fischer, and Thomas Brox, U-Net: Convolutional networks for biomedical image segmentation, in Proceedings of the Part III Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany (Springer, New York, 2015), pp. 234–241.
  34. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA (2016), 10.1109/CVPR.2016.90.
  35. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, Attention is all you need, arXiv:1706.03762.
  36. Jonathan Ho, Ajay Jain, and Pieter Abbeel, Denoising diffusion probabilistic models, Adv. Neural Inf. Process. Syst. 33, 6840 (2020), https://proceedings.neurips.cc/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf.
  37. Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P. Kingma, pixelcnn++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications, arXiv:1701.05517.
  38. Yuxin Wu and Kaiming He, Group normalization, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 3–19, https://openaccess.thecvf.com/content_ECCV_2018/html/Yuxin_Wu_Group_Normalization_ECCV_2018_paper.html.
  39. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer, High-resolution image synthesis with latent diffusion models, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 10684–10695, https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html.
  40. A. Scheinker, cDVAE: VAE-guided diffusion for particle accelerator beam 6D phase space projection diagnostics, Sci. Rep. 14, 29303 (2024).
  41. A. Scheinker, Conditional guided generative diffusion for particle accelerator beam diagnostics, Sci. Rep. 14, 19210 (2024).
  42. L. Wang, G. Aarts, and K. Zhou, Diffusion models as stochastic quantization in lattice field theory, J. High Energy Phys. 05 (2024) 060.
  43. J. Sohl-Dickstein, E. A. Weiss, N. Maheswaranathan, and S. Ganguli, Deep unsupervised learning using nonequilibrium thermodynamics, arXiv:1503.03585.
  44. Nvidia, Get started with deep learning performance, https://docs.nvidia.com/deeplearning/performance/dl-performance-getting-started/index.html [Accessed: July 19, 2024].
  45. A. L. Maas, A. Y. Hannun, A. Y. Ng et al., Rectifier nonlinearities improve neural network acoustic models, in Proceedings of the ICML, Atlanta, GL (2013), Vol. 30, p. 3, https://robotics.stanford.edu/~amaas/papers/relu_hybrid_icml2013_final.pdf.
  46. P. Ramachandran, B. Zoph, and Q. V. Le, Searching for activation functions, arXiv:1710.05941.
  47. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  48. S. L. Smith, P. J. Kindermans, C. Ying, and Q. V. Le, Don’t decay the learning rate, increase the batch size, arXiv:1711.00489.
  49. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin et al., tensorflow: Large-scale machine learning on heterogeneous systems, https://tensorflow.org (2015).
  50. Y. S. Derbenev, J. Rossbach, E. L. Saldin, and V. D. Shiltsev, Microbunch radiative tail—head interaction, DESY, Report No. TESLA-FEL 1995-05, 1995, 10.3204/PUBDB-2018-04128.
  51. Y. S. Derbenev and V. D. Shiltsev, Transverse effects of microbunch radiative interaction, SLAC National Accelerator Laboratory (SLAC), Reports No. SLAC-PUB-7181, No. FERMILAB-TM-1974, 10.2172/251656.
  52. J. Wu, P. Emma, and Z. Huang, Coherent synchrotron radiation as a diagnostic tool for the LCLS longitudinal feedback system, Conf. Proc. C 0505161, 428 (2005), https://proceedings.jacow.org/p05/PAPERS/TOAC005.PDF.
  53. J. Seok, M. Chung, M. Conde, G. Ha, and J. Power, Double-horn suppression in EEX based bunch compression, in Proceedings of the 4th North American Particle Accelerator Conference, Lansing, MI, USA (JACoW, Geneva, Switzerland, 2019), 10.18429/JACoW-NAPAC2019-TUPLM16.
  54. Z. Li, N. B. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuart, and A. Anandkumar, Fourier neural operator for parametric partial differential equations, in Proceedings of the International Conference on Learning Representations (2021), https://iclr.cc/virtual/2021/poster/3281.

Outline

Information

Phys. Rev. Accel. Beams 28, 110701– Published 4 November, 2025
  • Received 5 January 2025
  • Accepted 14 October 2025
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