Hamiltonian Neural Networks with Automatic Symmetry Detection

DOI10.1063/5.0142969MaRDI QIDQ6423803zbMATH OpenOpenAlexFDO

Authors Eva Dierkes, Christian Offen, Sina Ober-Blöbaum, Kathrin Flasskamp

Publication date 19 January 2023

Full work available at URL https://doi.org/10.1063/5.0142969

Mathematics Subject Classification ID

Partial differential equations of mathematical physics and other areas of application (35Qxx) Numerical problems in dynamical systems (65Pxx) Artificial intelligence (68Txx)

Abstract: Recently, Hamiltonian neural networks (HNN) have been introduced to incorporate prior physical knowledge when learning the dynamical equations of Hamiltonian systems. Hereby, the symplectic system structure is preserved despite the data-driven modeling approach. However, preserving symmetries requires additional attention. In this research, we enhance HNN with a Lie algebra framework to detect and embed symmetries in the neural network. This approach allows to simultaneously learn the symmetry group action and the total energy of the system. As illustrating examples, a pendulum on a cart and a two-body problem from astrodynamics are considered.

Cited in

(4)

• Learning of discrete models of variational PDEs from data
• On tensor invariants of the Clebsch system
• Group-convolutional extended dynamic mode decomposition
• Machine learning of continuous and discrete variational ODEs with convergence guarantee and uncertainty quantification

This page was built for publication: Hamiltonian Neural Networks with Automatic Symmetry Detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6423803)