- Letter
- Open Access
Single-waveform time-series modeling via kernel-based dynamic mode decomposition for real-time dynamics reconstruction
Phys. Rev. Accel. Beams 29, L072001 – Published 31 July, 2026
DOI: https://doi.org/10.1103/vbnq-lj9j
Abstract
Real-time monitoring and predictive modeling of complex accelerator subsystems demand data-efficient approaches that can capture essential dynamics from minimal measurements. This study introduces a framework based on kernel-based dynamic mode decomposition that constructs surrogate dynamical models from a single reference waveform, enabling accurate time-series reconstruction with substantially reduced data requirements compared to conventional methods. The approach formulates the system dynamics as a continuous ordinary differential equation (ODE) in a delay-embedded phase space, where a sparse dictionary and polynomial kernel provide both computational efficiency and physics-aligned interpretability through the underlying ODE structure. The method is validated on three beam kicker systems and two pulse-forming network (PFN) modulator systems at the Stanford Synchrotron Radiation Lightsource (SSRL) at SLAC, demonstrating accurate waveform reconstruction using only one training waveform per system. A comparative study against exponential smoothing and linear trend models confirms the method’s superior predictive capability, particularly in extrapolative tail regions. These results establish a lightweight, scalable foundation for real-time waveform monitoring, anomaly detection, and potential integration into broader facility-level digital twin frameworks in accelerator science and beyond.
Physics Subject Headings (PhySH)
Article Text
References (18)
- A. Edelen, N. Neveu, M. Frey, Y. Huber, C. Mayes, and A. Adelmann, Machine learning for orders of magnitude speedup in multiobjective optimization of particle accelerator systems, Phys. Rev. Accel. Beams 23, 044601 (2020).
- A. A. Mishra, A. Edelen, A. Hanuka, and C. Mayes, Uncertainty quantification for deep learning in particle accelerator applications, Phys. Rev. Accel. Beams 24, 114601 (2021).
- 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).
- A. Hanuka, X. Huang, J. Shtalenkova, D. Kennedy, A. Edelen, Z. Zhang, V R. Lalchand, D. Ratner, and J. Duris, Online tuning and light source control using a physics-informed Gaussian process, Phys. Rev. Accel. Beams 24, 072802 (2021).
- J. Kaiser, C. Xu, A. Eichler, and A. Santamaria Garcia, Bridging the gap between machine learning and particle accelerator physics with high-speed, differentiable simulations, Phys. Rev. Accel. Beams 27, 054601 (2024).
- R. Roussel et al., Bayesian optimization algorithms for accelerator physics, Phys. Rev. Accel. Beams 27, 084801 (2024).
- A. Scheinker, A. Edelen, D. Bohler, C. Emma, and A. Lutman, Demonstration of model-independent control of the longitudinal phase space of electron beams in the Linac-Coherent Light Source with femtosecond resolution, Phys. Rev. Lett. 121, 044801 (2018).
- C. Emma, A. Edelen, M. J. Hogan, B. O’Shea, G. White, and V. Yakimenko, Machine learning-based longitudinal phase space prediction of particle accelerators, Phys. Rev. Accel. Beams 21, 112802 (2018).
- P. J. Schmid, Dynamic mode decomposition of numerical and experimental data, J. Fluid Mech. 656, 5 (2010).
- J. N. Kutz, S. L. Brunton, B. W. Brunton, and J. L. Proctor, Dynamic Mode Decomposition: Data-Driven Modeling of Complex Systems (SIAM, Philadelphia, 2016), https://doi.org/10.1137/1.9781611974508.
- M. O. Williams, I. G. Kevrekidis, and C. W. Rowley, A data-driven approximation of the Koopman operator: Extending dynamic mode decomposition, J. Nonlinear Sci. 25, 1307 (2015).
- S. L. Brunton, J. L. Proctor, and J. N. Kutz, Discovering governing equations from data by sparse identification of nonlinear dynamical systems, Proc. Natl. Acad. Sci. U.S.A. 113, 3932 (2016).
- P. J. Baddoo, B. Herrmann, B. J. McKeon, and S. L. Brunton, Kernel learning for robust dynamic mode decomposition: Linear and nonlinear disambiguation optimization, Proc. R. Soc. A 478, 20210830 (2022).
- F. Takens, Detecting strange attractors in turbulence, in Dynamical Systems and Turbulence, Warwick 1980, edited by D. Rand and L. S. Young, Lecture Notes in Mathematics Vol. 898 (Springer, Berlin, 1981), pp. 366–381.
- K. Willcox and B. Segundo, The role of computational science in digital twins, Nat. Comput. Sci. 4, 147 (2024).
- National Academies of Sciences, Engineering, and Medicine, Foundational Research Gaps and Future Directions for Digital Twins (National Academies Press, Washington, DC, 2024), 10.17226/26894.
- L. Ljung, System Identification: Theory for the User, 2nd ed. (Prentice Hall, 1999).
- F. Wang, SingleWaveReconstructionData, SLAC National Accelerator Laboratory, https://github.com/slaclab/SingleWaveReconstructionData (2026).
