Low-complexity full-field ultrafast nonlinear dynamics prediction by a convolutional feature separation modeling method

TL;DR

This paper introduces a convolutional feature separation modeling method that significantly accelerates the prediction of ultrafast nonlinear dynamics in optical fibers, reducing computation time by over 90% while maintaining accuracy and flexibility.

Contribution

The authors develop a novel convolutional deep learning approach that separates linear and nonlinear effects, greatly reducing complexity and enhancing flexibility in ultrafast nonlinear dynamics prediction.

Findings

94% reduction in running time compared to NLSE

87% reduction in running time compared to RNN

Flexible input conditions without accuracy loss

Abstract

The modeling and prediction of the ultrafast nonlinear dynamics in the optical fiber are essential for the studies of laser design, experimental optimization, and other fundamental applications. The traditional propagation modeling method based on the nonlinear Schr\"odinger equation (NLSE) has long been regarded as extremely time-consuming, especially for designing and optimizing experiments. The recurrent neural network (RNN) has been implemented as an accurate intensity prediction tool with reduced complexity and good generalization capability. However, the complexity of long grid input points and the flexibility of neural network structure should be further optimized for broader applications. Here, we propose a convolutional feature separation modeling method to predict full-field ultrafast nonlinear dynamics with low complexity and high flexibility, where the linear effects are firstly modeled by NLSE-derived methods, then a convolutional deep learning method is implemented for nonlinearity modeling. With this method, the temporal relevance of nonlinear effects is substantially shortened, and the parameters and scale of neural networks can be greatly reduced. The running time achieves a 94% reduction versus NLSE and an 87% reduction versus RNN without accuracy deterioration. In addition, the input pulse conditions, including grid point numbers, durations, peak powers, and propagation distance, can be flexibly changed during the predicting process. The results represent a remarkable improvement in the ultrafast nonlinear dynamics prediction and this work also provides novel perspectives of the feature separation modeling method for quickly and flexibly studying the nonlinear characteristics in other fields.