High-Accuracy Recognition of Orbital Angular Momentum Modes Propagated in Atmospheric Turbulences Based on Deep Learning

Abstract

The atmospheric turbulence (AT) causes distortion of phase fronts of orbital angular momentum (OAM) beams, which hinders the recognition of OAM modes. Convolutional neural network (CNN), a deep learning (DL) technique, can be utilized to realize the effective recognition of OAM modes. In this article, we propose a properly designed six-layer CNN model that can achieve high recognition accuracy (RA) of OAM modes at a reasonable computing complexity. We used intensity images of Laguerre-Gaussian (LG) beams to train our CNN model and explored the relationship between the RA for different single OAM modes and many factors including the number of training epochs, AT intensity, transmission distance, and the number of single OAM modes. Our CNN model can obtain an RA of 97.1% under moderate turbulence and 80% under strong turbulence, which are better than some CNN models proposed previously. Compared with these previous CNN models, our CNN model can also reduce the time consumption for at most 70%. Our research could contribute in achieving higher data capacity in OAM-based free space optical (FSO) communication systems. INDEX TERMS atmospheric turbulence (AT), convolutional neural network (CNN), free-space optical (FSO) communication, orbital angular momentum (OAM)

Deep Learning Recognition of Orbital Angular Momentum Modes Over Atmospheric Turbulence Channels Assisted by Vortex Phase Modulation

“…Therefore, we decide to use a twelve-layer CNN in this work. It provides better recognition performance than the CNNs with fewer layers did in [24], [28], [42] and requires fewer computational resources than the CNNs with more layers did in [30], [43].…”

Low complexity deep learning algorithms for compensating atmospheric turbulence in the free space optical communication system

“…In the context of FSO communication, many algorithms are used to detect the received signal after propagating through atmospheric turbulence. Depending on the deployed algorithm, these works can be divided into three categories; classical machine learning-based methods [16][17][18][19], convolutional neural network (CNN)-based methods [20][21][22][23][24][25][26][27][28][29][30][31][32], and deep neural network (DNN)-based methods [33][34][35][36][37][38][39][40]. Table 1 shows the main differences between these works.…”

“…However, atmospheric turbulence causes distortion of phase fronts of OAM beams and hinders the decoding of OAM modes. Different CNN structures are deployed in Ref [23,24] for efficient decoding of the OAM modes. In Ref [25][26][27], the CNN is used as a demodulator for a turbo-coded OAM-shift keying (SK) FSO system at strong atmospheric turbulence.…”

Atmospheric turbulence recognition with deep learning models for sinusoidal hyperbolic hollow Gaussian beams-based free-space optical communication links

“…Under the effect of atmospheric turbulence, the transmitted modes are predicted utilizing an artificial neural network model (ANN) [11]. However, the OAM modes are predicted by a CNN model with higher prediction accuracy under moderate turbulence researched 97.1% [12]. Recently, the turbulence-induced OAM mode distortion in FSO links is 97% detected using ANN and CNN models [13].…”