Journal Article

PUBDB-2023-07140

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Deep learning for laser beam imprinting

Chalupsky, J. (Corresponding author)Extern*XFEL.EU* ; Vozda, V.Extern*XFEL.EU* ; Hering, J.Extern* ; Kybic, J. ; Burian, T.Extern*XFEL.EU* ; Dziarzhytski, S.DESY* ; Frantálová, K. ; Hájková, V.Extern*XFEL.EU* ; Jelinek, S.Extern*XFEL.EU* ; Juha, L.Extern* ; Keitel, B.DESY* ; Kuglerova, Z.Extern* ; Kuhlmann, M.DESY* ; Petryshak, B. ; Ruiz Lopez, M.DESY* ; Vyšín, L.Extern*XFEL.EU* ; Wodzinski, T. ; Plönjes, E.DESY*

2023
Optica Washington, DC

This record in other databases:        

Please use a persistent id in citations: doi:10.1364/OE.481776  doi:10.3204/PUBDB-2023-07140

Abstract: Methods of ablation imprints in solid targets are widely used to characterize focusedX-ray laser beams due to a remarkable dynamic range and resolving power. A detailed descriptionof intense beam profiles is especially important in high-energy-density physics aiming at nonlinearphenomena. Complex interaction experiments require an enormous number of imprints to becreated under all desired conditions making the analysis demanding and requiring a huge amountof human work. Here, for the first time, we present ablation imprinting methods assistedby deep learning approaches. Employing a multi-layer convolutional neural network (U-Net)trained on thousands of manually annotated ablation imprints in poly(methyl methacrylate), wecharacterize a focused beam of beamline FL24/FLASH2 at the Free-electron laser in Hamburg.The performance of the neural network is subject to a thorough benchmark test and comparisonwith experienced human analysts. Methods presented in this Paper pave the way towards a virtualanalyst automatically processing experimental data from start to end.

---

Contributing Institute(s):

1. DOOR-User (DOOR ; HAS-User)
2. FLASH Photonen-Strahlführungen und Optiken (FS-FLASH-B)
3. FLASH Wissenschaftlicher Nutzerbetrieb (FS-FLASH-O)

Research Program(s):

1. 631 - Matter – Dynamics, Mechanisms and Control (POF4-631) (POF4-631)
2. 6G2 - FLASH (DESY) (POF4-6G2) (POF4-6G2)

Experiment(s):

1. FLASH2 Beamline FL24 (FLASH2)

Appears in the scientific report 2023

---

Database coverage:
; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Physical, Chemical and Earth Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF < 5 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---