Spatial Mode Correction of Single Photons using Machine Learning

TL;DR

This paper demonstrates how machine learning, specifically neural networks, can correct spatial distortions in single photons' modes, enhancing quantum communication and imaging technologies affected by media-induced phase distortions.

Contribution

It introduces a neural network-based method for real-time correction of spatial mode distortions in single photons, surpassing traditional techniques in adaptability and performance.

Findings

Neural networks effectively correct complex spatial profiles of distorted single-photon modes.

Machine learning improves the robustness of quantum communication protocols against turbulence.

The approach enables real-time turbulence correction for structured photons.

Abstract

Spatial modes of light constitute valuable resources for a variety of quantum technologies ranging from quantum communication and quantum imaging to remote sensing. Nevertheless, their vulnerabilities to phase distortions, induced by random media, impose significant limitations on the realistic implementation of numerous quantum-photonic technologies. Unfortunately, this problem is exacerbated at the single-photon level. Over the last two decades, this challenging problem has been tackled through conventional schemes that utilize optical nonlinearities, quantum correlations, and adaptive optics. In this article, we exploit the self-learning and self-evolving features of artificial neural networks to correct the complex spatial profile of distorted Laguerre-Gaussian modes at the single-photon level. Furthermore, we demonstrate the possibility of boosting the performance of an optical communication protocol through the spatial mode correction of single photons using machine learning. Our results have important implications for real-time turbulence correction of structured photons and single-photon images.