Error Estimates in Physics-Informed Neural Networks to Heat-Wave Fluid-Structure Interactive System

Abstract

We study a physics-informed neural network (PINN) approximation of a coupled PDE system that models the interaction between fluid and elastic dynamics. The canonical heat-wave model considered here couples a parabolic and a hyperbolic equation through transmission conditions on a fixed boundary interface, and serves as a prototype for the Stokes-elastic systems that arises in real world applications. This coupling makes the error analysis more delicate than that for a single PDE. We bound the error between the exact and PINN solutions by the associated PINN residuals, and we moreover prove that the generalization error is controlled by the training error, the number of quadrature points, and the size of the network. {To the best of our knowledge}, these are the first error estimates for a PINN approximation of a coupled fluid-structure interaction PDE system. We also show that numerical experiments with respect to a given test problem.

Lazy training of quantum physics informed neural networks
Anderson Melchor Hernandez, Giacomo De Palma
arXiv16 Sep 2026PreprintCC BY 4.0Full textMathematical physics ProbabilityarXiv
AKAPINN: Adaptive Kolmogorov-Arnold Physics-Informed Neural Networks for approximating solutions to quasilinear partial differential equations
B. Veena S. N. Rao
arXiv22 Sep 2026PreprintCC BY 4.0Full textNumerical analysis & scientific computingarXiv
Solving Fredholm Integral Equations with Physics-Informed Neural Networks: Single-and double-network approaches
Mathieu Fabre, Laurence Grammont, Youcef Mammeri
HAL14 Oct 2026PreprintCC BY-NC-SA 4.0Full textGeneral mathematicsHAL
Lie Symmetry-Guided Adaptive Sampling for Physics-Informed Neural Networks
Runze Zhao
arXiv25 Oct 2026PreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv
A Hybrid Physics-informed holomorphic neural networks Method
Zhijie Su, Qiaolin He, Zhiping Mao +1
arXiv28 Oct 2026PreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv

Cite

BibTeX RIS

BibTeX

@misc{geredeli2026error,
  title = {{Error Estimates in Physics-Informed Neural Networks to Heat-Wave Fluid-Structure Interactive System}},
  author = {Pelin G. Geredeli and Mohammad Mahabubur Rahman and Deepanshu Verma},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.03575},
  eprint = {2610.03575},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.03575},
}

RIS

TY  - UNPB
TI  - Error Estimates in Physics-Informed Neural Networks to Heat-Wave Fluid-Structure Interactive System
AU  - Pelin G. Geredeli
AU  - Mohammad Mahabubur Rahman
AU  - Deepanshu Verma
PY  - 2026
DA  - 2026/10/25
PB  - arXiv
DO  - 10.48550/arxiv.2610.03575
UR  - https://arxiv.org/abs/2610.03575
AB  - We study a physics-informed neural network (PINN) approximation of a coupled PDE system that models the interaction between fluid and elastic dynamics. The canonical heat-wave model considered here couples a parabolic and a hyperbolic equation through transmission conditions on a fixed boundary interface, and serves as a prototype for the Stokes-elastic systems that arises in real world applications. This coupling makes the error analysis more delicate than that for a single PDE. We bound the error between the exact and PINN solutions by the associated PINN residuals, and we moreover prove that the generalization error is controlled by the training error, the number of quadrature points, and the size of the network. {To the best of our knowledge}, these are the first error estimates for a PINN approximation of a coupled fluid-structure interaction PDE system. We also show that numerical experiments with respect to a given test problem.
ER  -

Abstract

Related

Cite