U-Net-based surrogate modeling for attosecond X-ray free-electron lasers

Wei, Yufei; Yan, Jiawei; Xu, Chenzhi; Yan, Bingyang; Deng, Haixiao

Preprint

PUBDB-2026-03544

U-Net-based surrogate modeling for attosecond X-ray free-electron lasers

Wei, Y. ; Yan, B. ; Xu, C. ; Yan, J. (Corresponding author)DESY* ; Deng, H. (Corresponding author)

2026

(2026)

This record in other databases:

Report No.: arXiv:2601.10898

Abstract: Attosecond X-ray pulse generation in modern X-ray free-electron lasers relies on strongly compressed, precisely tailored electron bunches, making accurate diagnostics and control of the two-dimensional longitudinal phase space (LPS) essential. In the self-chirping scheme, collective effects in the linac generate a strong energy chirp that is converted into high peak current through pre-undulator compression, enabling isolated attosecond pulse generation. Reliable operation of this scheme depends on precise two-dimensional LPS control and fast diagnostics. In this work, we present a U-Net-based neural-network surrogate that predicts two-dimensional LPS distributions directly from accelerator settings. The model exhibits good agreement with start-to-end simulation results. These results demonstrate the potential of neural-network surrogates to facilitate fast virtual diagnostics and provide a step toward real-time tuning in attosecond XFEL operation.[graphic not available: see fulltext][graphic not available: see fulltext]

Classification: