Sensing in the presence of strong noise by deep learning of dynamic multimode fiber interference

• DOI: 10.1364/prj.415902
• Publication Date: 2021-02-03T15:49:18Z
• Authors: Linh V. Nguyen; Cuong C. Nguyen; Gustavo Carneiro; Heike Ebendorff-H...; Stephen C. Warren...
• Keywords: Fiber Bragg Grating

A new approach to optical fiber sensing is proposed and demonstrated that allows for specific measurement even in the presence of strong noise from undesired environmental perturbations. deep neural network model trained statistically learn relation complex interference output a multimode (MMF) with respect measurand interest while discriminating noise. This technique negates need carefully shield against, or compensate for, perturbations, as often case traditional sensors. achieved entirely software without any postprocessing fabrication steps packaging required, such Bragg gratings specialized coatings. The highly generalizable, whereby can be identify within noisy environment provided affects path length MMF’s guided modes. We demonstrate using sapphire crystal temperature under induced by mechanical vibrations, showing power not only extract information buried but also enable traditionally challenging exotic materials.