ML-based approach to classification and generation of structured light propagation in turbulent media
arXiv:2604.14208v2 Announce Type: replace-cross Abstract: We study the classification task of structured-light beams after propagation through a random turbulent medium. The received speckle patterns are generated by numerical simulation of a stochastic paraxial propagation model, and the classification task is formulated over a finite alphabet of 15 OAM source classes. We benchmark intensity and autocorrelation inputs using SimpleCNN and ResNet-18 as classifiers. We also quantify the effect of training-set size and receiver-window misalignment. Since additional propagated samples may be costl
The increasing sophistication of ML techniques and computational power allows for new approaches to complex physics problems like turbulent media propagation, which is critical for advanced communication and sensing.
This development could significantly improve the reliability and efficiency of optical communication and remote sensing systems operating in challenging environments, impacting defence, space, and terrestrial applications.
The ability to more accurately classify and generate structured light propagation in turbulent media using ML changes how we might design and operate next-generation long-range optical systems.
- · Defence contractors
- · Space communication companies
- · Optical networking providers
- · AI/ML research institutions
- · Companies reliant on less robust optical communication methods
Improved performance of free-space optical communication links and imaging systems in atmospheric turbulence.
Reduced vulnerability of critical communication infrastructure to environmental interference, enhancing national security and data transmission capacity.
New paradigms for secure quantum communication or advanced remote sensing leveraging resilient structured light propagation for novel applications.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG