Fast reconstruction of laser beam near-field and focal spot profiles using deep neural network and numerical propagation

• DOI: 10.1364/oe.510088
• Publication Date: 2024-05-16T08:00:09Z
• Authors: Xiaoliang He; Hua Tao; Suhas P. Veetil; Chencheng Chang; Cheng Liu; Jianqiang Zhu
• Keywords: Beam parameter product

Inertial confinement fusion (ICF) experiments demand precise knowledge of laser beam parameters on high-power facilities. Among these parameters, near-field and focal spot distributions are crucial for characterizing quality. While iterative phase retrieval shows promise reconstruction, its utility is hindered by extensive calculations. To address this limitation, we propose an online reconstruction method based deep neural network. In method, utilize coherent modulation imaging (CMI) to obtain labels training the The network reconstructs complex distribution, including amplitude phase, directly from a defocused diffraction pattern without iteration. Subsequently, distribution obtained propagating established far-field. Proof-of-principle validate feasibility our proposed method.