Learning the Dynamics of Physical Systems with Hamiltonian Graph Neural Networks

Suresh Bishnoi, Ravinder Bhattoo, Jayadeva Jayadeva, Sayan Ranu, N M Anoop Krishnan

Keywords: Hamiltonian graph neural network, graph neural network, physics-informed machine learning

TL;DR: We propose a Hamiltonian graph neural network for learning the dynamics of physical systems

Abstract: Inductive biases in the form of conservation laws have been shown to provide superior performance for modeling physical systems. Here, we present Hamiltonian graph neural network (HGNN), a physics-informed GNN that learns the dynamics directly from the trajectory. We evaluate the performance of HGNN on spring, pendulum, and gravitational systems and show that it outperforms other Hamiltonian-based neural networks. We also demonstrate the zero-shot generalizability of HGNN to unseen hybrid spring-pendulum systems and system sizes that are two orders of magnitude larger than the training systems. HGNN provides excellent inference in all the systems providing a stable trajectory. Altogether, HGNN presents a promising approach to modeling complex physical systems directly from their trajectory.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/learning-the-dynamics-of-physical-systems/code)