Deep learning for laser beam imprinting

0583382 - ÚFP 2024 RIV US eng J - Journal Article
Chalupský, J. - Vozda, V. - Hering, J. - Kybic, J. - Burian, Tomáš - Dziarzhytski, S. - Frantálová, K. - Hájková, V. - Jelínek, Šimon - Juha, L. - Keitel, B. - Kuglerová, M. - Kuhlmann, M. - Petryshak, B. - Ruiz-Lopez, M. - Vyšín, L. - Wodzinski, T. - Plönjes, E.
Deep learning for laser beam imprinting.
Optics Express. Roč. 31, č. 12 (2023), s. 19703-19721. ISSN 1094-4087
R&D Projects: GA ČR(CZ) GA20-08452S
EU Projects: European Commission(XE) 654148 - LASERLAB-EUROPE
Institutional support: RVO:61389021
Keywords : deep learning * laser beam imprinting * X-ray
OECD category: Optics (including laser optics and quantum optics)
Impact factor: 3.8, year: 2022
Method of publishing: Open access
https://opg.optica.org/oe/fulltext.cfm?uri=oe-31-12-19703&id=531063

Methods of ablation imprints in solid targets are widely used to characterize focused X-ray laser beams due to a remarkable dynamic range and resolving power. A detailed description of intense beam profiles is especially important in high-energy-density physics aiming at nonlinear phenomena. Complex interaction experiments require an enormous number of imprints to be created under all desired conditions making the analysis demanding and requiring a huge amount of human work. Here, for the first time, we present ablation imprinting methods assisted by deep learning approaches. Employing a multi-layer convolutional neural network (U-Net) trained on thousands of manually annotated ablation imprints in poly(methyl methacrylate), we characterize 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 comparison with experienced human analysts. Methods presented in this Paper pave the way towards a virtual analyst automatically processing experimental data from start to end.
Permanent Link: https://hdl.handle.net/11104/0351354