Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

Abstract

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy, non-negative entropy production), we modify accordingly the port-Hamiltonian formalism so as to achieve a port-metriplectic one. We show that the constructed networks are able to learn the physics of complex systems by parts, thus alleviating the burden associated to the experimental characterization and posterior learning process of this kind of systems. Predictions can be done, however, at the scale of the complete system. Examples are shown on the performance of the proposed technique.

arXiv comment9 pages, 5 figures

References in corpus (8)

• On Learning Hamiltonian Systems from Data
• Deep learning of thermodynamics-aware reduced-order models from data
• Structure-preserving neural networks
• Machine Learning and Computational Mathematics
• GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systems
• Thermodynamics-informed graph neural networks
• Pseudo-Hamiltonian Neural Networks with State-Dependent External Forces
• Gradient and GENERIC evolution towards reduced dynamics