Predicting Ultrafast Nonlinear Dynamics in Fiber Optics by Enhanced Physics-Informed Neural Network
Predicting Ultrafast Nonlinear Dynamics in Fiber Optics by Enhanced Physics-Informed Neural Network
复制标题
DOI：
10.1109/jlt.2023.3322893
复制
发表时间：
2024-03
影响因子：
4.7
通讯作者：
Xiaotian Jiang;Min Zhang;Yuchen Song;Hongjie Chen;Dongmei Huang;Danshi Wang
中科院分区：
文献类型：
--
作者：
Xiaotian Jiang;Min Zhang;Yuchen Song;Hongjie Chen;Dongmei Huang;Danshi Wang
超快非线性动力学在超快光学中起着至关重要的作用，需要精确求解广义非线性薛定谔方程（GNLSE）来理解其基本的数学机制。然而，GNLSE表现出复杂的物理相互作用与高度非线性效应，导致数值方法的复杂性瓶颈和数据驱动方法的物理不一致性。物理信息神经网络（PINN）可以通过在网络优化过程中学习先验物理知识来解决这些挑战。然而，香草PINN的结构和学习模式中的病态阻碍了其学习高非线性动力学和高频特征的能力。在这项研究中，提出了一种增强的PINN光纤中的超快非线性动力学，它严格遵循空间因果关系，同时学习所有频率分量。在高阶孤子压缩和超连续谱产生两种典型的超快非线性情形下，研究了模型的性能和推广能力，所得结果与文献结果吻合较好.此外，我们还分析了数值方法的计算复杂性和数据驱动方法的物理不一致性，并提出了更复杂的情况下的潜在扩展。这项工作表明了增强PINN在理解，表征和建模复杂的高非线性和高频率的动力学方面的潜力。
Ultrafast nonlinear dynamics plays a crucial role in ultrafast optics, necessitating accurate solutions to the generalized nonlinear Schrödinger equation (GNLSE) for understanding its underlying mathematical mechanisms. However, the GNLSE exhibits intricate physical interactions with highly nonlinear effects, leading to the complexity bottleneck in numerical methods and physical inconsistency in data-driven methods. Physics-informed neural networks (PINNs) can address these challenges by learning prior physical knowledge during the network optimization. However, the pathologies in the structure and learning mode of the vanilla PINN hinders its ability to learn high-nonlinear dynamics and high-frequency features. In this study, an enhanced PINN is proposed for ultrafast nonlinear dynamics in fiber optics, which strictly follows the spatial causality while simultaneously learning all frequency components. The model performance and generalization ability are investigated in two typical ultrafast nonlinear scenarios: higher-order soliton compression and supercontinuum generation, and the generated results exhibit remarkable agreement with reference results. Moreover, we also analyze the computational complexity of numerical methods and physical inconsistency of data-driven methods, and propose potential extensions for more complex scenarios. This work demonstrates the promising potential of the enhanced PINN in comprehending, characterizing, and modeling intricate dynamics with high-nonlinearity and high-frequency.