Physics enhanced neural networks predict order and chaos

Abstract

Conventional artificial neural networks are powerful tools in science and industry, but they can fail when applied to nonlinear systems where order and chaos coexist. We use neural networks that incorporate the structures and symmetries of Hamiltonian dynamics to predict phase space trajectories even as nonlinear systems transition from order to chaos. We demonstrate Hamiltonian neural networks on the canonical Henon-Heiles system, which models diverse dynamics from astrophysics to chemistry. The power of the technique and the ubiquity of chaos suggest widespread utility.

5 pages and 5 figures

References in corpus (11)

• Chaotic Dirac billiard in graphene quantum dots
• Deep learning for universal linear embeddings of nonlinear dynamics
• Discovering physical concepts with neural networks
• Hamiltonian Neural Networks
• Multilayer multi-configuration time-dependent Hartree method: implementation and applications to a Henon-Heiles Hamiltonian and to pyrazine
• On Learning Hamiltonian Systems from Data
• Toward an AI Physicist for Unsupervised Learning
• Newton vs the machine: solving the chaotic three-body problem using deep neural networks
• Network Structure Effects in Reservoir Computers
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• Learning Symmetries of Classical Integrable Systems

Cited by in corpus (28)

• Hamiltonian neural networks for solving equations of motion
• Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
• Model-free prediction of multistability using echo state network
• Adaptable Hamiltonian neural networks
• Learning Hamiltonian dynamics by reservoir computer
• Reducing the complexity of chemical networks via interpretable autoencoders
• Data driven soliton solution of the nonlinear Schrödinger equation with certain $\mathcal{P}\mathcal{T}$-symmetric potentials via deep learning
• Machine Learning Potential of a Single Pendulum
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra
• Constrained Hamiltonian Systems and Physics-Informed Neural Networks: Hamilton-Dirac Neural Networks
• Controlling Chaos in Van Der Pol Dynamics Using Signal-Encoded Deep Learning
• Tomography of time-dependent quantum spin networks with machine learning
• Machine Learning Classification of Kuiper Belt Populations
• Learning unidirectional coupling using echo-state network
• Generating extreme quantum scattering in graphene with machine learning
• Neuronal diversity can improve machine learning for physics and beyond
• One-Shot Transfer Learning of Physics-Informed Neural Networks
• Efficient PINNs via Multi-Head Unimodular Regularization of the Solutions Space
• Unsupervised Reservoir Computing for Solving Ordinary Differential Equations
• Residual Generation Using Physically-Based Grey-Box Recurrent Neural Networks For Engine Fault Diagnosis
• RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow
• Variational Integrator Graph Networks for Learning Energy Conserving Dynamical Systems
• Differential Euler: Designing a Neural Network approximator to solve the Chaotic Three Body Problem
• Nonseparable Symplectic Neural Networks
• Physical discovery in representation learning via conditioning on prior knowledge: applications for ferroelectric domain dynamics
• Local error quantification for Neural Network Differential Equation solvers
• Dynamics of reservoir computing for crises prediction
• Deep learning of thermodynamic laws from microscopic dynamics