mlsanityData to 7 Oct 2026

Thermodynamics of learning physical phenomena

arXiv 2207.12749 ↗First posted 26 Jul 2022cs.LG cond-mat.stat-mechcited by 10

Not on the map. Why?

Abstract (arXiv)

Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many fields. We review how thermodynamics provides helpful insights in the learning process. At the same time, we study the influence of aspects such as the scale at which a given phenomenon is to be described, the choice of relevant variables for this description or the different techniques available for the learning process.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 53 of its 150 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

53 of 150 references.

References · 53

  1. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  2. 2016Group Equivariant Convolutional Networkscited by 1,154
  3. 2021E(n) Equivariant Graph Neural Networkscited by 951
  4. 2019Hamiltonian Neural Networkscited by 702
  5. 2021Characterizing possible failure modes in physics-informed neural networkscited by 632
  6. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 603
  7. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 470
  8. 2016Input Convex Neural Networkscited by 407
  9. 2020Lagrangian Neural Networkscited by 388
  10. 2019Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learningcited by 205
  11. 2020Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solverscited by 201
  12. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
38 more
  1. 2019Symplectic Recurrent Neural Networkscited by 148
  2. 2019Hamiltonian Generative Networkscited by 136
  3. 2020Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraintscited by 102
  4. 2022Approximately Equivariant Networks for Imperfectly Symmetric Dynamicscited by 95
  5. 2019Physics-Informed Neural Networks for Power Systemscited by 80
  6. 2020Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learningcited by 77
  7. 2020NeuralSim: Augmenting Differentiable Simulators with Neural Networkscited by 77
  8. 2021Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systemscited by 66
  9. 2018SPNets: Differentiable Fluid Dynamics for Deep Neural Networkscited by 62
  10. 2020Structure-preserving neural networkscited by 54
  11. 2021Machine learning structure preserving brackets for forecasting irreversible processescited by 51
  12. 2021GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systemscited by 48
  13. 2020Benchmarking Energy-Conserving Neural Networks for Learning Dynamics from Datacited by 40
  14. 2020Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Controlcited by 38
  15. 2020Deep learning of thermodynamics-aware reduced-order models from datacited by 38
  16. 2022Physical Design using Differentiable Learned Simulatorscited by 37
  17. 2021Symplectic Learning for Hamiltonian Neural Networkscited by 35
  18. 2020Hamiltonian neural networks for solving equations of motioncited by 33
  19. 2020Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanicscited by 32
  20. 2022Deconstructing the Inductive Biases of Hamiltonian Neural Networkscited by 31
  21. 2022Thermodynamics-informed graph neural networkscited by 31
  22. 2022NN-EUCLID: deep-learning hyperelasticity without stress datacited by 30
  23. 2020Symplectic Neural Networks in Taylor Series Form for Hamiltonian Systemscited by 24
  24. 2020LagNetViP: A Lagrangian Neural Network for Video Predictioncited by 24
  25. 2020Machine Learning and Computational Mathematicscited by 22
  26. 2021Adaptable Hamiltonian neural networkscited by 21
  27. 2020Sparse Symplectically Integrated Neural Networkscited by 20
  28. 2018Model Reduction with Memory and the Machine Learning of Dynamical Systemscited by 19
  29. 2021Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by Designcited by 18
  30. 2021Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)cited by 18
  31. 2022Pseudo-Hamiltonian Neural Networks with State-Dependent External Forcescited by 17
  32. 2021Distributed neural network control with dependability guarantees: a compositional port-Hamiltonian approachcited by 12
  33. 2021Physics perception in sloshing scenes with guaranteed thermodynamic consistencycited by 10
  34. 2022A Thermodynamics-informed Active Learning Approach to Perception and Reasoning about Fluidscited by 9
  35. 2022Learning Neural Hamiltonian Dynamics: A Methodological Overviewcited by 8
  36. 2022Simulating Liquids with Graph Networkscited by 8
  37. 2018Robust port-Hamiltonian representations of passive systemscited by 4
  38. 2019Port-Hamiltonian Approach to Neural Network Trainingcited by 4

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 4; 2025: 4.

10 papers.

  1. 2022Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systemscited by 11
  2. 2024Physics-Aware Neural Implicit Solvers for multiscale, parametric PDEs with applications in heterogeneous mediacited by 5
  3. 2024A comparison of Single- and Double-generator formalisms for Thermodynamics-Informed Neural Networkscited by 4
  4. 2024A hybrid numerical methodology coupling Reduced Order Modeling and Graph Neural Networks for non-parametric geometries: applications to structural dynamics problemscited by 3
  5. 2023Predicting and explaining nonlinear material response using deep Physically Guided Neural Networks with Internal Variablescited by 1
  6. 2024A POD-TANN approach for the multiscale modeling of materials and macroelement derivation in geomechanicscited by 1
  7. 2025Physics-based machine learning for fatigue lifetime prediction under non-uniform loading scenarioscited by 0
  8. 2025Learning thermodynamic master equations for open quantum systemscited by 0
  9. 2025Can Transformers overcome the lack of data in the simulation of history-dependent flows?cited by 0
  10. 2025GIMLET: Generalizable and Interpretable Model Learning through Embedded Thermodynamicscited by 0