Physics-guided deep learning for high resolution X-ray free-electron laser imaging

Imperfections in X-ray free-electron laser (XFEL) imaging systems can limit their performance, especially in High Energy Density (HED) or Inertial Fusion Energy (IFE)-relevant experiments that are typically single shot, by introducing structured, non-stationary features that overlap with the signal of interest. When the X-ray transmission is reconstructed by typical flat-field normalization, even small shot-to-shot drift of structured features imprints residual patterns onto transmission maps, degrading signal visibility and biasing measurements such as electron density, velocity and feature sizes. We investigate this limitation by modeling the artifacts as a separable feature layer and training a U-Net architecture to estimate and infer them directly from the experimental data. We compare our method against Fourier filtering, phase cross-correlation (PCC), and more advanced procedures like Dynamic Flat-Field Normalization (DFFN) to evaluate artifact suppression capability and signal preservation in the reconstructed transmission maps. In multiple synthetic injection tests, our Physics-Guided Deep Learning approach is able to obtain an improvement in mean Structural Similarity Index (SSIM) from 0.345 to 0.906 and from 0.0679 to 0.945, while better preserving filament profiles and reducing degradation of the filament signal during artifact suppression. Additionally, we utilize deep ensembles to obtain predictive epistemic uncertainty estimates for the U-Net based reconstruction, to ensure Out Of Distribution (OOD) robustness for this procedure.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-17
DOI
https://doi.org/10.1038/s41598-026-80553-7
Primary Topic
Advanced X-ray Imaging Techniques
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Physics-guided deep learning for high resolution X-ray free-electron laser imaging

Marc Welch, Andrea Zabala, R. N. Ettelbrick, Meriame Berboucha et al.
2 links
Scientific Reports
Advanced X-ray Imaging Techniques
article

Physics-guided deep learning for high resolution X-ray free-electron laser imaging

Marc Welch, Andrea Zabala, R. N. Ettelbrick, Meriame Berboucha, P. Neumayer, Gourab Chatterjee, Mickael Grech, Bob Nagler, Dimitri Khaghani, Shao Xian Lee, Nick Czapla, Eric Flint Cunningham, Nina A. Boiadjieva, Aashwin Mishra, Hae Ja Lee, Quynh L. Nguyen, Gilliss Dyer, Philip Hart, Eric Galtier, Caterina Riconda, Ariel Arnott, Peregrine McGehee, Jonathan Ehni, Anna Grassi
article en

Abstract

Imperfections in X-ray free-electron laser (XFEL) imaging systems can limit their performance, especially in High Energy Density (HED) or Inertial Fusion Energy (IFE)-relevant experiments that are typically single shot, by introducing structured, non-stationary features that overlap with the signal of interest. When the X-ray transmission is reconstructed by typical flat-field normalization, even small shot-to-shot drift of structured features imprints residual patterns onto transmission maps, degrading signal visibility and biasing measurements such as electron density, velocity and feature sizes. We investigate this limitation by modeling the artifacts as a separable feature layer and training a U-Net architecture to estimate and infer them directly from the experimental data. We compare our method against Fourier filtering, phase cross-correlation (PCC), and more advanced procedures like Dynamic Flat-Field Normalization (DFFN) to evaluate artifact suppression capability and signal preservation in the reconstructed transmission maps. In multiple synthetic injection tests, our Physics-Guided Deep Learning approach is able to obtain an improvement in mean Structural Similarity Index (SSIM) from 0.345 to 0.906 and from 0.0679 to 0.945, while better preserving filament profiles and reducing degradation of the filament signal during artifact suppression. Additionally, we utilize deep ensembles to obtain predictive epistemic uncertainty estimates for the U-Net based reconstruction, to ensure Out Of Distribution (OOD) robustness for this procedure.

Scientific Reports
Centre National de la Recherche Scientifique (FR), École Polytechnique (FR), Lawrence Berkeley National Laboratory (US), GSI Helmholtz Centre for Heavy Ion Research (DE), Institut Universitaire de France (FR), Commissariat à l'Énergie Atomique et aux Énergies Alternatives (FR), SLAC National Accelerator Laboratory (US), Sorbonne Université (FR), Laboratoire pour l'Utilisation des Lasers Intenses (FR), Nvidia (United States) (US)
U.S. Department of Energy, Ministerio de Economía y Competitividad, Office of Science, Basic Energy Sciences, Fusion Energy Sciences, Laboratory Directed Research and Development, SLAC National Accelerator Laboratory
Advanced X-ray Imaging Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon