Machine learning identification of multiple-state OAM superpositions detected with spatial mode sensors

Jaime E. Cisternas; Javier I. Espinoza; Jaime A. Anguita

doi:10.1117/12.2593811

1 August 2021 Machine learning identification of multiple-state OAM superpositions detected with spatial mode sensors

Jaime E. Cisternas, Javier I. Espinoza, Jaime A. Anguita

Proceedings Volume 11834, Laser Communication and Propagation through the Atmosphere and Oceans X; 118340I (2021) https://doi.org/10.1117/12.2593811
Event: SPIE Optical Engineering + Applications, 2021, San Diego, California, United States

Abstract

When propagated through atmospheric turbulence, Orbital Angular Momentum (OAM) modes suffer a loss of orthogonality that can compromise their detection and classification. The problem is more challenging when user information encoded on multi-state OAM superpositions needs to be detected with high probability. Optical sensors like the Shack-Hartmann detector or the Mode Sorter are candidates for such task. We describe how OAM histograms derived from such detectors can be used for decoding the original data symbols. We propose Machine Learning strategies for a reliable classification of the histogram patterns obtained with 4-mode superpositions propagated over a 1 km range in weak to intermediate turbulence.

Conference Presentation

Citation Download Citation

Jaime E. Cisternas, Javier I. Espinoza, and Jaime A. Anguita "Machine learning identification of multiple-state OAM superpositions detected with spatial mode sensors", Proc. SPIE 11834, Laser Communication and Propagation through the Atmosphere and Oceans X, 118340I (1 August 2021); https://doi.org/10.1117/12.2593811

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available