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

• URL: http://arxiv.org/abs/2211.01873v1
• Date: Thu, 3 Nov 2022 15:04:27 GMT
• Title: Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
• Authors: Quercus Hern\'andez, Alberto Bad\'ias, Francisco Chinesta, El\'ias Cueto
• Abstract summary: We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. We show that the constructed networks are able to learn the physics of complex systems by parts.
• Score: 0.09332987715848712
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Physics-Constrained Learning for PDE Systems with Uncertainty Quantified Port-Hamiltonian Models [0.7350858947639451]
  We propose a physics-constrained learning method that combines powerful learning tools and reliable physical models. Based on the Bayesian nature of the Gaussian process, we not only learn the dynamics of the system, but also enable uncertainty quantification.
  arXiv  Detail & Related papers  (2024-06-17T17:52:01Z)
• Autonomous Learning of Generative Models with Chemical Reaction Network Ensembles [0.0]
  We develop a general architecture whereby a broad class of chemical systems can autonomously learn complex distributions. Our construction takes the form of a chemical implementation of machine learning's optimization workhorse: gradient descent on the relative entropy cost function.
  arXiv  Detail & Related papers  (2023-11-02T03:46:23Z)
• Gaussian Process Port-Hamiltonian Systems: Bayesian Learning with Physics Prior [17.812064311297117]
  Data-driven approaches achieve remarkable results for the modeling of complex dynamics based on collected data. These models often neglect basic physical principles which determine the behavior of any real-world system. We propose a physics-informed Bayesian learning approach with uncertainty quantification.
  arXiv  Detail & Related papers  (2023-05-15T20:59:41Z)
• Physically Consistent Neural ODEs for Learning Multi-Physics Systems [0.0]
  In this paper, we leverage the framework of Irreversible port-Hamiltonian Systems (IPHS), which can describe most multi-physics systems. We propose Physically Consistent NODEs (PC-NODEs) to learn parameters from data. We demonstrate the effectiveness of the proposed method by learning the thermodynamics of a building from the real-world measurements.
  arXiv  Detail & Related papers  (2022-11-11T11:20:35Z)
• Port-Hamiltonian Neural Networks with State Dependent Ports [58.720142291102135]
  We stress-test the method on both simple mass-spring systems and more complex and realistic systems with several internal and external forces. Port-Hamiltonian neural networks can be extended to larger dimensions with state-dependent ports. We propose a symmetric high-order integrator for improved training on sparse and noisy data.
  arXiv  Detail & Related papers  (2022-06-06T14:57:25Z)
• Quantum state inference from coarse-grained descriptions: analysis and an application to quantum thermodynamics [101.18253437732933]
  We compare the Maximum Entropy Principle method, with the recently proposed Average Assignment Map method. Despite the fact that the assigned descriptions respect the measured constraints, the descriptions differ in scenarios that go beyond the traditional system-environment structure.
  arXiv  Detail & Related papers  (2022-05-16T19:42:24Z)
• Symmetry Group Equivariant Architectures for Physics [52.784926970374556]
  In the domain of machine learning, an awareness of symmetries has driven impressive performance breakthroughs. We argue that both the physics community and the broader machine learning community have much to understand.
  arXiv  Detail & Related papers  (2022-03-11T18:27:04Z)
• Constructing Neural Network-Based Models for Simulating Dynamical Systems [59.0861954179401]
  Data-driven modeling is an alternative paradigm that seeks to learn an approximation of the dynamics of a system using observations of the true system. This paper provides a survey of the different ways to construct models of dynamical systems using neural networks. In addition to the basic overview, we review the related literature and outline the most significant challenges from numerical simulations that this modeling paradigm must overcome.
  arXiv  Detail & Related papers  (2021-11-02T10:51:42Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)
• Interpretable machine learning models: a physics-based view [3.7431113857875755]
  We use port Hamiltonian (p-H) formalism to describe the basic constructs that contain physically interpretable processes. We show how we can build models out of the p-H constructs and how we can train them.
  arXiv  Detail & Related papers  (2020-03-22T23:17:19Z)
• Learning Stable Deep Dynamics Models [91.90131512825504]
  We propose an approach for learning dynamical systems that are guaranteed to be stable over the entire state space. We show that such learning systems are able to model simple dynamical systems and can be combined with additional deep generative models to learn complex dynamics.
  arXiv  Detail & Related papers  (2020-01-17T00:04:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.