mlsanityData to 7 Oct 2026

Nonlinear GENERIC-Embedded Neural Networks (N-GENNs): Learning GENERIC dynamics with non-quadratic dissipation potentials

arXiv 2605.09058 ↗First posted 9 May 2026physics.comp-ph cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce Nonlinear GENERIC-Embedded Neural Networks (N-GENNs), a deep learning framework for discovering evolution equations of systems governed by the nonlinear GENERIC formalism (General Equation for Non-Equilibrium Reversible-Irreversible Coupling). Such systems exhibit coupled conservative and dissipative dynamics, and can be described via the superposition of a Hamiltonian flow and a generalized gradient flow. In contrast to existing approaches, our formulation incorporates generalized gradient flows via convex dissipation potentials, enabling the identification of a broader class of thermodynamically consistent dynamics, including systems with non-quadratic dissipation potentials. Thermodynamic structure is strongly enforced by construction through suitable reparameterizations of both the reversible operator and the dissipation potential, ensuring exact compliance with the first and second laws of thermodynamics. We validate the proposed approach on three representative examples: a harmonic oscillator coupled to a heat bath, an idealized chemical motor, and a one-dimensional viscoplastic model of Perzyna type. These results demonstrate the method's ability to accurately infer thermodynamically consistent models from data for systems incorporating both conservative and nonlinear dissipative dynamics.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 80 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

25 of 80 references.

References · 25

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2019Hamiltonian Neural Networkscited by 702
  3. 2020Lagrangian Neural Networkscited by 388
  4. 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 183
  5. 2025Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspectivecited by 55
  6. 2020Structure-preserving neural networkscited by 54
  7. 2021Machine learning structure preserving brackets for forecasting irreversible processescited by 51
  8. 2021GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systemscited by 48
  9. 2020Deep learning of thermodynamics-aware reduced-order models from datacited by 38
  10. 2020Learning Poisson systems and trajectories of autonomous systems via Poisson neural networkscited by 37
  11. 2022Thermodynamics-informed graph neural networkscited by 31
  12. 2022Automated discovery of generalized standard material models with EUCLIDcited by 31
13 more
  1. 2020Structure preserving deep learningcited by 30
  2. 2023Reversible and irreversible bracket-based dynamics for deep graph neural networkscited by 25
  3. 2024tLaSDI: Thermodynamics-informed latent space dynamics identificationcited by 23
  4. 2024Efficiently Parameterized Neural Metriplectic Systemscited by 18
  5. 2024Viscoelasticty with physics-augmented neural networks: Model formulation and training methods without prescribed internal variablescited by 17
  6. 2023Data-driven anisotropic finite viscoelasticity using neural ordinary differential equationscited by 16
  7. 2023Theory and implementation of inelastic Constitutive Artificial Neural Networkscited by 12
  8. 2022Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systemscited by 11
  9. 2023Lie-Poisson Neural Networks (LPNets): Data-Based Computing of Hamiltonian Systems with Symmetriescited by 9
  10. 2025Thermodynamically Consistent Latent Dynamics Identification for Parametric Systemscited by 8
  11. 2024A comparison of Single- and Double-generator formalisms for Thermodynamics-Informed Neural Networkscited by 4
  12. 2025Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in non-equilibrium systemscited by 3
  13. 2025SPIEDiff: robust learning of long-time macroscopic dynamics from short-time particle simulations with quantified epistemic uncertaintycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Structure-preserving uncertainty quantification for GENERIC dynamicscited by 0