Efficient and accurate analysis of oscillation dynamics for dissipative cavity solitons based on the artificial neural network

As a conventional means to analyze the system mechanism based on partial differential equations (PDE) or nonlinear dynamics, iterative algorithms are computationally intensive. In this framework, analyzing the details of oscillating dynamics of cavity solitons are indeed challenging, since they are beyond the reach of traditional mathematical tools. To this end, we demonstrate that this long-standing obstacle could be tackled down with the long short-term memory (LSTM) neural network. We propose the incorporating parameter-fed ports, which are capable of recognizing multiple-period bifurcations of respiratory solitons and efficiently predicting nonlinear dynamics of solitons with arbitrary parameter combinations and arbitrary time series lengths.