- 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

Customized Bayesian optimization for efficient beam tuning at the facility for rare isotope beams

Kilean Hwang*, Qiang Zhao, Tong Zhang, Tomofumi Maruta, Alexander Plastun, Kei Fukushima, and Peter Ostroumov

  • *Contact author: hwang@frib.msu.edu
PDF

Phys. Rev. Accel. Beams 29, 024601 – Published 17 February, 2026

DOI: https://doi.org/10.1103/5hyd-bhpx

Abstract

Bayesian optimization (BO) has recently emerged as a powerful approach for on-line beam tuning, and it is rapidly gaining adoption across accelerator facilities due to its flexibility and efficiency in handling complex optimization tasks. At the Facility for Rare Isotope Beams, rapid and reliable tuning is essential to support the delivery of diverse ion species. To improve the practicality of BO in this setting, we implemented several enhancements, including scalarized composite objective construction for multicriteria optimization, asynchronous evaluation for better resource utilization, prior-mean-assisted optimization to accelerate convergence, and a local search strategy for rapid completion of the task. We present the details of these methods, discuss challenges-encountered, and share our experience applying them to specific beam-tuning tasks.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (28)

  1. J. Wei, H. Ao, S. Beher, N. Bultman, F. Casagrande, S. Cogan, C. Compton, J. Curtin, L. Dalesio, K. Davidson, M. Kelly, Y. Momozaki, G. Apollinari, K. Assamagan, M. Bai et al., Advances of the FRIB project, Int. J. Mod. Phys. E 28, 1930003 (2019).
  2. P. N. Ostroumov et al., Acceleration of uranium beam to record power of 10.4 kW and observation of new isotopes at Facility for Rare Isotope Beams, Phys. Rev. Accel. Beams 27, 060101 (2024).
  3. P. N. Ostroumov, F. Casagrande, K. Fukushima, K. Hwang, M. Ikegami, T. Kanemura, S.-H. Kim, S. Lidia, G. Machicoane, T. Maruta, D. Morris, A. S. Plastun, H. Ren, J. Wei, T. Xu, T. Zhang, Q. Zhao, and S. Zhao, FRIB commissioning, in Proceedings of the 15th International Conference on Heavy Ion Accelerator Technology (HIAT’22), Darmstadt, Germany, 2022 (JACoW, Geneva, Switzerland, 2022), pp. 118–123.
  4. P. N. Ostroumov, K. Fukushima, K. Hwang, T. Maruta, A. S. Plastun, J. Wei, T. Zhang, and Q. Zhao, Accelerator and beam physics challenges in support of FRIB experiments, J. Phys. Conf. Ser. 2687, 052012 (2024).
  5. P. Virtanen et al., scipy 1.0: Fundamental algorithms for scientific computing in python, Nat. Methods 17, 261 (2020).
  6. K. Hwang, A. Plastun, K. Fukushima, P. N. Ostroumov, T. Maruta, T. Zhang, and Q. Zhao, Machine-learning-assisted beam tuning at FRIB, in Proceedings of the 32nd Linear Accelerator Conference (LINAC’24), Chicago, IL, USA, 2024 (JACoW, Geneva, Switzerland, 2024).
  7. R. Roussel et al., Bayesian optimization algorithms for accelerator physics, Phys. Rev. Accel. Beams 27, 084801 (2024).
  8. J. Duris, D. Kennedy, A. Hanuka, J. Shtalenkova, A. Edelen, P. Baxevanis, A. Egger, T. Cope, M. McIntire, S. Ermon, and D. Ratner, Bayesian optimization of a free-electron laser, Phys. Rev. Lett. 124, 124801 (2020).
  9. C. E. Rasmussen and C. K. I. Williams, Gaussian Processes for Machine Learning (MIT Press, Cambridge, MA, 2006).
  10. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. (MIT Press, Cambridge, MA, 2018).
  11. J. Martinez-Marin, B. Mustapha, B. Blomberg, E. Letcher, G. Dunn, D. Stanton, and K. Bunnell, Reinforcement learning and Bayesian optimization for ion linac operations, in Proceedings of the 15th International Conference on Heavy Ion Accelerator Technology (HIAT’22), Darmstadt, Germany, 2022 (JACoW, Geneva, Switzerland, 2022), pp. 153–156.
  12. M. P. Deisenroth and C. E. Rasmussen, PILCO: A model-based and data-efficient approach to policy search, in Proceedings of the International Conference on Machine Learning (ICML 2011), Bellevue, WA, USA (2011), pp. 465–472.
  13. K. Chua, R. Calandra, R. McAllister, and S. Levine, Deep reinforcement learning in a handful of trials using probabilistic dynamics models, in Proceedings of the 32nd International Conference Neural Information Processing System (NeurIPS’18), Montréal, Canada, 2018 (2018), pp. 4759–4770, https://neurips.cc/virtual/2018/poster/11467.
  14. J. Kaiser et al., Reinforcement learning-trained optimisers and Bayesian optimisation for online particle accelerator tuning, Sci. Rep. 14, 15733 (2024).
  15. J. Kaiser, C. Xu, A. Eichler, and A. S. García, Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations, Phys. Rev. Accel. Beams 27, 054601 (2024).
  16. K. Hwang et al., Prior-mean-assisted Bayesian optimization application on FRIB front-end tuning, arXiv:2211.06400.
  17. T. Boltz, J. L. Martinez, C. Xu, K. R. L. Baker, Z. Zhu, J. Morgan, R. Roussel, D. Ratner, B. Mustapha, and A. L. Edelen, Leveraging prior mean models for faster Bayesian optimization of particle accelerators, Sci. Rep. 15, 12232 (2025).
  18. I. Kostrikov, A. Nair, and S. Levine, Offline reinforcement learning with implicit Q-learning, in Proceedings of the International Conference Learning Representations (ICLR’22) (2022), https://openreview.net/forum?id=68n2s9ZJWF8.
  19. R. Wang, D. P. Foster, and S. M. Kakade, Instabilities of offline RL with pre-trained neural representation, in Proceedings of the 38th International Conference on Machine Learning (ICML’21), edited by M. Meila and T. Zhang, Proceedings of Machine Learning Research Vol. 139 (PMLR, 2021), pp. 10837–10847, https://icml.cc/Conferences/2021.
  20. K. Hwang, J. Wan, T. Zhang, T. Maruta, Q. Zhao, A. Plastun, K. Fukushima, and P. N. Ostroumov, Machine-learning-assisted beam tuning at FRIB, in Proceedings of the 5th North American Particle Accelerator Conference (NAPAC’25), Sacramento, CA, USA, 2025 (JACoW, Geneva, Switzerland, 2025).
  21. J. Gonzalez, Z. Dai, P. Hennig, and N. Lawrence, Batch Bayesian optimization via local penalization, in Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS’16), Cadiz, Spain (2016), Vol. 51, pp. 648–657, https://proceedings.mlr.press/v51/gonzalez16a.html.
  22. D. Ginsbourger, R. L. Riche, and L. Carraro, Kriging is well-suited to parallelize optimization, in Computational Intelligence in Expensive Optimization Problems, Adaptation Learning and Optimization Vol. 2 (Springer, Berlin, Heidelberg, 2010), pp. 131–162.
  23. Y. Shen and C. Kingsford, Computationally efficient high-dimensional Bayesian optimization via variable selection, in Proceedings of the 2nd International Conference on Automated Machine Learning (AutoML’23), Proceedings of Machine Learning Research Vol. 224 (PMLR, Potsdam, Germany, 2023), pp. 15/1–27, https://2023.automl.cc/.
  24. D. Eriksson, M. Pearce, J. R. Gardner, R. D. Turner, and M. Poloczek, Scalable global optimization via local Bayesian optimization, in Proceedings of the 33rd International Conference on Neural Information Processing System, (NeurIPS’19), Vancouver, Canada, 2019 (2019), https://papers.neurips.cc/paper_files/paper/2019/hash/6c990b7aca7bc7058f5e98ea909e924b-Abstract.html.
  25. K. Hwang, A. S. Plastun, K. Fukushima, P. N. Ostroumov, T. Maruta, T. Zhang, Q. Zhao, and S. Cogan, Beam tuning at the FRIB front end using machine learning, in Proceedings of the 13th International Particle Accelerator Conference (IPAC’22), Bangkok, Thailand, 2022 (JACoW Geneva, Switzerland, 2022), pp. 983–986.
  26. P. Ostroumov, K. Hwang, A. Sheinker et al., Online autonomous tuning of the FRIB accelerator using machine learning (2023); Project proposal narrative (unpublished).
  27. P. N. Ostroumov, S. Cogan, K. Fukushima, S. Lidia, T. Maruta, A. S. Plastun, J. Wei, J. Wong, T. Yoshimoto, and Q. Zhao, Heavy ion beam acceleration in the first three cryomodules at the Facility for Rare Isotope Beams at Michigan State University, Phys. Rev. Accel. Beams 22, 040101 (2019).
  28. T. Zhang, K. Fukushima, T. Maruta, A. Plastun, K. Hwang, Q. Zhao, and P. Ostroumov, Physics application software for FRIB: From commissioning to operational excellence, in Proceedings of the 20th International Conference on Accelerator and Large Experimental Physics Control Systems (ICALEPCS’25), Chicago, IL, USA, 2025 (JACoW, Geneva, Switzerland, 2025), pp. 916–920.

Outline

Information

Phys. Rev. Accel. Beams 29, 024601– Published 17 February, 2026
  • Received 29 August 2025
  • Accepted 13 January 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