Complex amplitude field reconstruction in atmospheric turbulence based on deep learning

• Main Authors: Hu, X. (Author), Tan, Y. (Author), Wang, J. (Author)
• Format: Article
• Language: English
• Published: Optica Publishing Group (formerly OSA) 2022
• Subjects: Amplitude information; Amplitude reconstruction; Atmospheric thermodynamics; Atmospheric turbulence; Complex amplitude; Complex networks; Deep neural networks; Field reconstruction; Light fields; Pattern pairs; Phase information; Phase patterns; Phase reconstruction; Training methods
• Online Access: View Fulltext in Publisher
• Physical Description: 9
• ISBN: 10944087 (ISSN)
• DOI: 10.1364/OE.450710

In this paper, we use deep neural networks (DNNs) to simultaneously reconstruct the amplitude and phase information of the complex light field transmitted in atmospheric turbulence based on deep learning. The results of amplitude and phase reconstruction by four different training methods are compared comprehensively. The obtained results indicate that the training method that can more accurately reconstruct the complex amplitude field is to input the amplitude and phase pattern pairs into the neural network as two channels to train the model. © 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement Journal © 2022