Rapid prediction of complex nonlinear dynamics in Kerr resonators using the recurrent neural network.

Abstract

Kerr resonator is one of the most popular platforms to produce optical frequency comb and temporal cavity soliton. As an essential method for investigating the nonlinear dynamics of Kerr resonators, traditional numerical simulations rely on solving the Lugiato-Lefever equation (LLE) using the split-step Fourier method (SSFM), which is computationally intensive and time-consuming. To address this challenge, this study proposes a recurrent neural network model with prior information feedback, enabling efficient and accurate prediction of soliton dynamics in Kerr resonator. With the acceleration of graphics processing unit (GPU), the computational efficiency improved by 20 times. We compared various recurrent neural networks and found that the gated recurrent unit (GRU) network demonstrated superior performance in this task. This work highlights the potential of artificial intelligence (AI) for modeling nonlinear optical dynamics in Kerr resonator, paving the way for designing optical frequency comb and generating ultrafast pulse.