Neural Networks Enforcing Physical Symmetries in Nonlinear Dynamical Lattices: The Case Example of the Ablowitz-Ladik Model

Abstract

In this work we introduce symmetry-preserving, physics-informed neural networks (S-PINNs) motivated by symmetries that are ubiquitous to solutions of nonlinear dynamical lattices. Although the use of PINNs have recently attracted much attention in data-driven discovery of solutions chiefly to partial differential equations, we demonstrate that they fail at enforcing important physical laws including symmetries of solutions and conservation laws. Through the correlation of parity symmetries in both space and time of solutions to differential equations with their group equivariant representation, we construct group-equivariant NNs which respect spatio-temporal parity symmetry. Moreover, we adapt the proposed architecture to enforce different types of periodicity (or localization) of solutions to nonlinear dynamical lattices. We do so by applying S-PINNs to the completely integrable Ablowitz-Ladik model, and performing numerical experiments with a special focus on waveforms that are related to rogue structures. These include the Kuznetsov-Ma soliton, and Akhmediev breather as well as the Peregrine soliton. Our numerical results demonstrate the superiority and robustness of the proposed architecture over standard PINNs.

arXiv comment15 pages, 9 figures

References in corpus (37)

• DeepXDE: A deep learning library for solving differential equations
• Artificial Neural Networks for Solving Ordinary and Partial Differential Equations
• DGM: A deep learning algorithm for solving partial differential equations
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Solving high-dimensional partial differential equations using deep learning
• Nonlinear waves in $\mathcal{P}\mathcal{T}$-symmetric systems
• Instabilities, breathers and rogue waves in optics
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Group Equivariant Convolutional Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Deep neural network solution of the electronic Schrödinger equation
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• Rogue waves and analogies in optics and oceanography
• SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
• Rotation equivariant vector field networks
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• Data-driven rogue waves and parameter discovery in the defocusing NLS equation with a potential using the PINN deep learning
• Universal Peregrine soliton structure in nonlinear pulse compression in optical fiber
• Universal Invariant and Equivariant Graph Neural Networks
• Locally Scale-Invariant Convolutional Neural Networks
• Scale-Invariant Convolutional Neural Networks
• General $E(2)$-Equivariant Steerable CNNs
• 3D G-CNNs for Pulmonary Nodule Detection
• SelectNet: Self-paced Learning for High-dimensional Partial Differential Equations
• Observation of modulation instability and rogue breathers on stationary periodic waves
• Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
• Kinetic Alfvén solitary and rogue waves in superthermal plasmas
• Permutation-equivariant neural networks applied to dynamics prediction
• Universal approximations of permutation invariant/equivariant functions by deep neural networks
• Deep Scale-spaces: Equivariance Over Scale
• Scale equivariance in CNNs with vector fields
• Error estimates of residual minimization using neural networks for linear PDEs
• Template Matching via Densities on the Roto-Translation Group
• Rogue Waves in Ultracold Bosonic Seas

Cited by in corpus (2)

• HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
• Invariant deep neural networks under the finite group for solving partial differential equations