Deep Learning for Computational Mode Decomposition in Optical Fibers

Abstract

Multimode fibers are regarded as the key technology for the steady increase in data rates in optical communication. However, light propagation in multimode fibers is complex and can lead to distortions in the transmission of information. Therefore, strategies to control the propagation of light should be developed. These strategies include the measurement of the amplitude and phase of the light field after propagation through the fiber. This is usually done with holographic approaches. In this paper, we discuss the use of a deep neural network to determine the amplitude and phase information from simple intensity-only camera images. A new type of training was developed, which is much more robust and precise than conventional training data designs. We show that the performance of the deep neural network is comparable to digital holography, but requires significantly smaller efforts. The fast characterization of multimode fibers is particularly suitable for high-performance applications like cyberphysical systems in the internet of things.

Few-Mode Fiber Characterization System Based on the Spatially and Spectrally Imaging Technique

“…Besides, there are also some people combing the deep learning and mode decomposition, for instance, mode decomposition for the multi-mode fibers based on the convolutional neural network (CNN) [33] and deep neural network (DNN) [34]. Since the S 2 testing technique measures the characteristics of FMFs by analyzing the optical field image, the machine learning and deep learning technology can also be combined with it, which will be a future research direction.…”

Complex Wavefront Shaping through a Multi-Core Fiber

“…The experimental results present the distal light field transmitted through a 50 cm long calibrated MCF (Figure 3h,m). Implementing the image correlation evaluation method introduced in [35], the experimental reconstructed distal far-field employing the Core-GS algorithm has a fidelity of 96.2% for the smiling face and 90.7% for the MST logo compared with the simulation. Hence, we demonstrate a robust phase retrieval algorithm for complex wavefront shaping through an MCF with high fidelity.…”

Reusability report: Predicting spatiotemporal nonlinear dynamics in multimode fibre optics with a recurrent neural network

“…There are two main directions in which to expand the scope of the proposed recurrent neural network architecture: introducing spatiotemporal characteristics together in the network instead of decoupling the space and time information of the pulse as well as a network capable of handling complex fields. Neural network architectures that deal with complex fields have already been presented, such as a neural network that decomposes the output field into LP modes 21,22 . With a similar scheme, the network could accept transverse complex fields and the time domain information in a (2 + 1) D fashion to perform the nonlinear evolution step by step in the propagation direction.…”