We propose an alternative approach to compensation of intermodal interactions in few-mode optical fibers by means of digital backpropagation. Instead of solving the inverse generalized multimode nonlinear Schrödinger equation, we accomplish backpropagation of the multimode signals with help of their near-field intensity distributions captured by a camera. We demonstrate that this task can successfully be handled by a deep neural network and provide a proof of concept by training an autoencoder for backpropagation of six linearly polarized (LP) modes of a step-index fiber.

Space-division multiplexing (SDM) has attracted significant attention in recent years because larger transmission capacity is enabled by more degrees of freedom (DOFs) in few-mode fibers (FMFs) compared with single-mode fibers (SMFs). To transmit independent information on spatial modes without or with minor digital signal processing (DSP), weakly-coupled FMFs are preferred in various applications. Several cases with different use of spatial DOFs in weakly-coupled FMFs are demonstrated in this work, including single-mode or mode-group-multiplexed transmission, and spatial DOFs combined with time or frequency DOF to improve the system performance.