Superhigh-Resolution Recognition of Optical Vortex Modes Assisted by a Deep-Learning Method.

Abstract

Orbital angular momentum (OAM) has demonstrated great success in the optical communication field, which theoretically allows an infinite increase of the transmitted capacity. The resolution of a receiver to precisely recognize OAM modes is crucial to expand the communication capacity. Here, we propose a deep learning (DL) method to precisely recognize OAM modes with fractional topological charges. The minimum interval recognized between adjacent modes decreases to 0.01, which as far as we know is the first time this superhigh resolution has been realized. To exhibit its efficiency in the optical communication process, we transfer an Einstein portrait by a superhigh-resolution OAM multiplexing system. As the convolutional neuron networks can be trained by data up to an infinitely large volume in theory, this work exhibits a huge potential of generalized suitability for next generation DL based ultrafine OAM optical communication, which might even be applied to microwave, millimeter wave, and terahertz OAM communication systems.