Generative Adversarial Network Based Adaptive Optics Scheme for Vortex Beam in Oceanic Turbulence

Abstract

Vortex beam carrying orbital angular momentum (OAM) suffers heavily interference from oceanic turbulence (OT) when it is transmitted through underwater wireless optical communication (UWOC) system. Adaptive optics (AO) is up to now the best candidate to improve the UWOC communications quality. In this work, we propose a generative adversarial network (GAN) based AO scheme to compensate for the distortion caused by OT, where the GAN is first trained by numerical simulations to obtain the mapping between the distortion intensity distribution and its corresponding phase screen representating OT, and a predicted phase screen is then given from the trained GAN when the experimental distorted intensity distribution is input. Finally, the predicted phase screen is compensated to the distorted vortex beam. The results show that the proposed scheme can quickly extract data features and accurately output the predicted phase screen. The distorted intensity pattern of the vortex beam is well compensated even in strong turbulence, where the intermodal crosstalk of different OAM modes is alleviated and the transmission probability of OAM mode is promoted significantly.