ML-Enhanced Digital Backpropagation for Long-Reach Single-Span Systems

TL;DR

This paper introduces a machine learning-enhanced digital backpropagation technique that optimizes dispersion and nonlinear filters to improve accuracy in long-reach optical communication systems with low computational cost.

Contribution

It presents a novel ML-aided joint optimization approach for digital backpropagation, enhancing accuracy and efficiency in long-reach single-span systems.

Findings

Improved accuracy over traditional methods

Reduced computational complexity

Effective joint optimization of dispersion and nonlinear filters

Abstract

We propose a digital backpropagation method that employs machine-learning-aided joint optimization of dispersion step lengths and nonlinear phase rotation filters within an FFT-based enhanced split-step Fourier structure, achieving improved accuracy at low computational complexity.