Nonseparable Symplectic Neural Networks

Abstract

Predicting the behaviors of Hamiltonian systems has been drawing increasing attention in scientific machine learning. However, the vast majority of the literature was focused on predicting separable Hamiltonian systems with their kinematic and potential energy terms being explicitly decoupled while building data-driven paradigms to predict nonseparable Hamiltonian systems that are ubiquitous in fluid dynamics and quantum mechanics were rarely explored. The main computational challenge lies in the effective embedding of symplectic priors to describe the inherently coupled evolution of position and momentum, which typically exhibits intricate dynamics. To solve the problem, we propose a novel neural network architecture, Nonseparable Symplectic Neural Networks (NSSNNs), to uncover and embed the symplectic structure of a nonseparable Hamiltonian system from limited observation data. The enabling mechanics of our approach is an augmented symplectic time integrator to decouple the position and momentum energy terms and facilitate their evolution. We demonstrated the efficacy and versatility of our method by predicting a wide range of Hamiltonian systems, both separable and nonseparable, including chaotic vortical flows. We showed the unique computational merits of our approach to yield long-term, accurate, and robust predictions for large-scale Hamiltonian systems by rigorously enforcing symplectomorphism.

arXiv commentICLR2021

References in corpus (16)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Interaction Networks for Learning about Objects, Relations and Physics
• Hamiltonian Neural Networks
• Wave Physics as an Analog Recurrent Neural Network
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control
• Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions
• Explicit symplectic approximation of nonseparable Hamiltonians: algorithm and long time performance
• Structure-preserving neural networks
• Physics enhanced neural networks predict order and chaos
• Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
• Hamiltonian Graph Networks with ODE Integrators
• Lagrangian Neural Networks
• Explicit symplectic algorithms based on generating functions for charged particle dynamics
• Symplectic Neural Networks in Taylor Series Form for Hamiltonian Systems
• Coercing Machine Learning to Output Physically Accurate Results
• Classifying orbits in the classical Henon-Heiles Hamiltonian system