Vortex Beams and Deep Learning for Optical Wireless Communication Through Turbulent and Diffuse Media

Interest in optical wireless communications (OWC) as a possible complement to RF technology has increased recently. However, the propagation of optical beams through the atmosphere distorts the beam's amplitude and phase, resulting in information loss and significant noise. Arising due to a combination of multiple absorption and scattering events, the distortion of the beam makes optical communication difficult. In some cases, the orbital angular momentum of light (OAM), along with various deep learning algorithms (DL), could be helpful to mitigate the problem and provide high-capacity optical communication links. In this work, we propagate Laguerre-Gaussian (LG) beams with different topological charges (
l
) under diffuse and turbulent conditions and develop a deep-learning classification network to characterize the ‘
l
’ of the LG beam. The proposed method is later implemented using a laboratory setup demonstrating communication on the optical table. The results show that the proposed algorithm can identify the modes of the LG beam with high accuracy even when the optical beam propagates through highly turbulent and scattering media. To demonstrate the robustness of the proposed OWC system, small grayscale images are transmitted over the communication channel. A bit error rate (BER) of only
$2.3 \times {10}^{ - 4}$
and
$9.7 \times {10}^{ - 4}$
for the tabletop experiment and the simulations, respectively. The demonstrated low BER in the proposed OWC system suggests promising applications for secure and reliable data transmission in adverse atmospheric conditions, highlighting the potential of this method in advancing optical wireless communication technologies.