Classification of single photons in higher-order spatial modes via convolutional neural networks
- 17 April 2025
- journal article
- Published by Optica Publishing Group in Optics Letters
- Vol. 50 (9) , 2820-2823
Abstract
Spatial modes are a promising candidate for encoding information for classical and quantum optical communication due to their potential high information capacity. Unfortunately, compensation of a wavefront upon propagation through the atmosphere is necessary to benefit from advantages spatial modes offer. In this work, we leverage the success of convolutional networks in denoising and classifying images to improve information transfer of spatial modes. Hermite–Gaussian (HG), Laguerre–Gaussian (LG), and Ince–Gaussian (IG) modes are experimentally generated using single photons and imaged. A denoising autoencoder corrects for turbulence effects on the wavefront, followed by a convolutional neural network to classify mode orders. The model achieves a 99.2% classification accuracy across all modes, and Hermite–Gaussian modes exhibited the highest individual mode accuracy. As the convolutional networks rely solely on intensity, they offer an efficient and cost-effective tool for optical communication systems in the single-photon limit.Keywords
All Related Versions
Funding Information
- U.S. Department of Energy (DE-SC0024676)
- National Science Foundation (GRFP 2139911)
- Gordon and Betty Moore Foundation (442)
This publication has 30 references indexed in Scilit:
- Deep learning for enhanced free-space optical communicationsMachine Learning: Science and Technology, 2023
- Machine learning assisted two-dimensional beam-steering for integrated optical phased arraysOptics Communications, 2023
- Advanced multi-feedback stochastic parallel gradient descent wavefront correction in free-space optical communicationOptics Communications, 2023
- A contemporary survey on free space optical communication: Potentials, technical challenges, recent advances and research directionJournal of Network and Computer Applications, 2022
- Machine learning for optical fiber communication systems: An introduction and overviewAPL Photonics, 2021
- Generative machine learning for robust free-space communicationCommunications Physics, 2020
- Coherent optical communications enhanced by machine intelligenceMachine Learning: Science and Technology, 2020
- Atmospheric turbulence compensation with sensorless AO in OAM-FSO combining the deep learning-based demodulatorOptics Communications, 2020
- Satellite-based links for quantum key distribution: beam effects and weather dependenceNew Journal of Physics, 2019
- High-capacity millimetre-wave communications with orbital angular momentum multiplexingNature Communications, 2014