A Comparative Investigation of Thermodynamic Structure-Informed Neural Networks

• URL: http://arxiv.org/abs/2603.26803v1
• Date: Thu, 26 Mar 2026 07:39:15 GMT
• Title: A Comparative Investigation of Thermodynamic Structure-Informed Neural Networks
• Abstract summary: Physics-informed neural networks (PINNs) offer a unified framework for solving both forward and inverse problems of differential equations.<n>We present a systematic comparison of different thermodynamic structure-informed neural networks by incorporating various thermodynamics formulations.
• Score: 1.3965477771846408
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Physics-informed neural networks (PINNs) offer a unified framework for solving both forward and inverse problems of differential equations, yet their performance and physical consistency strongly depend on how governing laws are incorporated. In this work, we present a systematic comparison of different thermodynamic structure-informed neural networks by incorporating various thermodynamics formulations, including Newtonian, Lagrangian, and Hamiltonian mechanics for conservative systems, as well as the Onsager variational principle and extended irreversible thermodynamics for dissipative systems. Through comprehensive numerical experiments on representative ordinary and partial differential equations, we quantitatively evaluate the impact of these formulations on accuracy, physical consistency, noise robustness, and interpretability. The results show that Newtonian-residual-based PINNs can reconstruct system states but fail to reliably recover key physical and thermodynamic quantities, whereas structure-preserving formulation significantly enhances parameter identification, thermodynamic consistency, and robustness. These findings provide practical guidance for principled design of thermodynamics-consistency model, and lay the groundwork for integrating more general nonequilibrium thermodynamic structures into physics-informed machine learning.

Related papers

• Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models [50.08589060318727]
  We introduce Hamiltonian Causal Models (HCMs), a trajectory-level framework in which observed variables interact with local environments.<n>HCMs separate immutable equations of motion from intervenable mechanisms and define causal effects as discrepancies between interventional path laws.
  arXiv  Detail & Related papers  (2026-06-03T12:43:46Z)
• Physics-Informed Deep Learning for Entropy Prediction in Heterogeneous Systems: Thermodynamic and Information-Theoretic Case Studies [0.0]
  Entropy governs irreversibility and uncertainty in both physical and information-theoretic systems.<n>This paper introduces a unified Physics-Informed Deep Learning framework that simultaneously enforces differential equation residuals and information-theoretic bounds.
  arXiv  Detail & Related papers  (2026-05-31T11:38:52Z)
• Learning partially observed systems with neural Hamiltonian ordinary differential equations [41.99844472131922]
  We present neural Hamiltonian ordinary differential equations (NHODE) to learn partially observed dynamical systems from data.<n>The framework is evaluated on systems of increasing complexity, from linear and nonlinear mass-spring systems to the chaotic three-body problem.
  arXiv  Detail & Related papers  (2026-05-22T11:18:39Z)
• A Convex Route to Thermomechanics: Learning Internal Energy and Dissipation [0.0]
  We present a physics-based neural network framework for the discovery of models in fully coupled thermomechanics.<n>In contrast to classical formulations based on the Helmholtz energy, we adopt the internal energy and a dissipation potential as primary functions.<n>Results show that the learned models accurately capture the underlying behavior.
  arXiv  Detail & Related papers  (2026-03-30T17:26:13Z)
• Differentiable Thermodynamic Phase-Equilibria for Machine Learning [39.691553958657764]
  DISCOMAX is a differentiable algorithm for phase-equilibrium calculation that guarantees thermodynamic consistency at both training and inference.<n>We evaluate the approach on binary liquid-liquid equilibrium data and demonstrate that it outperforms existing surrogate-based methods.
  arXiv  Detail & Related papers  (2026-03-11T19:14:04Z)
• Hard-Constrained Neural Networks with Physics-Embedded Architecture for Residual Dynamics Learning and Invariant Enforcement in Cyber-Physical Systems [0.5735035463793009]
  We formalize the Hybrid Recurrent Physics-Informed Neural Network (HRPINN), a general-purpose architecture that embeds known physics as a hard structural constraint within a recurrent integrator to learn only residual dynamics.<n>Second, we introduce the Projected HRPINN (PHRPINN), a novel extension that integrates a predict-project mechanism to strictly enforce algebraic invariants by design.<n>We validate HRPINN on a real-world battery prognostics DAE and evaluate PHRPINN on a suite of standard constrained benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T16:06:24Z)
• KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches [45.173398806932376]
  This paper introduces KO, a novel neural gradient inspired by kinetic theory and partial differential equation (PDE) simulations.<n>We reimagine the dynamics of network parameters as the evolution of a particle system governed by kinetic principles.<n>This physics-driven approach inherently promotes parameter diversity during optimization, mitigating the phenomenon of parameter condensation.
  arXiv  Detail & Related papers  (2025-05-20T18:00:01Z)
• Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling [41.82469276824927]
  We present a framework that achieves high-precision modeling for a wide range of dynamical systems. It helps preserve energies for conservative systems while serving as a strong inductive bias for non-conservative, reversible systems. By integrating the TRS loss within neural ordinary differential equation models, the proposed model TREAT demonstrates superior performance on diverse physical systems.
  arXiv  Detail & Related papers  (2024-10-08T21:04:01Z)
• Thermodynamics-Consistent Graph Neural Networks [50.0791489606211]
  We propose excess Gibbs free energy graph neural networks (GE-GNNs) for predicting composition-dependent activity coefficients of binary mixtures. The GE-GNN architecture ensures thermodynamic consistency by predicting the molar excess Gibbs free energy. We demonstrate high accuracy and thermodynamic consistency of the activity coefficient predictions.
  arXiv  Detail & Related papers  (2024-07-08T06:58:56Z)
• Physical consequences of Lindbladian invariance transformations [44.99833362998488]
  We show that symmetry transformations can be exploited, on their own, to optimize practical physical tasks. In particular, we show how they can be used to change the measurable values of physical quantities regarding the exchange of energy and/or information with the environment.
  arXiv  Detail & Related papers  (2024-07-02T18:22:11Z)
• Quantum thermodynamics of the spin-boson model using the principle of minimal dissipation [41.94295877935867]
  We investigate the influence of the environment on quantities such as work, heat and entropy production. The results reveal significant differences to the weak-coupling forms of work, heat and entropy production.
  arXiv  Detail & Related papers  (2024-04-18T12:11:18Z)
• TANGO: Time-Reversal Latent GraphODE for Multi-Agent Dynamical Systems [43.39754726042369]
  We propose a simple-yet-effective self-supervised regularization term as a soft constraint that aligns the forward and backward trajectories predicted by a continuous graph neural network-based ordinary differential equation (GraphODE) It effectively imposes time-reversal symmetry to enable more accurate model predictions across a wider range of dynamical systems under classical mechanics. Experimental results on a variety of physical systems demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-10-10T08:52:16Z)
• 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)
• Equivariant Graph Mechanics Networks with Constraints [83.38709956935095]
  We propose Graph Mechanics Network (GMN) which is efficient, equivariant and constraint-aware. GMN represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency.
  arXiv  Detail & Related papers  (2022-03-12T14:22:14Z)
• Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting [34.61959169976758]
  APHYNITY is a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models. It consists in decomposing the dynamics into two components: a physical component accounting for the dynamics for which we have some prior knowledge, and a data-driven component accounting for errors of the physical model.
  arXiv  Detail & Related papers  (2020-10-09T09:31:03Z)

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.