Learning to Extract Distributed Polarization Sensing Data from Noisy Jones Matrices

• We consider the problem of recovering spatially resolved polarization information from receiver Jones matrices. We introduce a physics-based learning approach, improving noise resilience compared to previous inverse scattering methods, while highlighting challenges related to model overparameterization.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)

Keyword

Machine Learning

fiber-optic communications

Fiber Sensing

Publication and Content Type

kon (subject category)

ref (subject category)