mlsanityData to 14 Oct 2026

Finite basis physics-informed neural networks with hard constraints for viscous fluid flow in highly perforated domains

arXiv 2608.08114 ↗First posted 8 Aug 2026physics.flu-dyn cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, viscous fluid flow governed by the Stokes equations in highly perforated domains is studied using physics-informed neural networks (PINNs). Perforated microstructures induce complex boundary conditions and fine-scale flow features that are difficult for standard neural networks to resolve. Conventional PINNs, even when combined with advanced training techniques, can suffer from a loss of accuracy and efficiency as the number of perforations increases. One important source of this difficulty is the soft enforcement of boundary conditions through penalty terms, which can lead to stiffness, gradient conflicts, and poor resolution of near-boundary flow structures. Hard constraints provide an alternative by encoding boundary conditions exactly into the network ansatz, but may introduce undesirable non-local effects due to the global nature of the approximation. To address these challenges, finite basis PINNs (FBPINNs), which are based on domain decomposition and localisation principles, are used together with hard boundary constraints that efficiently encode perforation-related boundary conditions. This approach helps mitigate spectral bias, improves overall accuracy, and exhibits convergence that is only weakly affected by the number of perforations, thereby providing an efficient and highly parallelisable neural network framework. The proposed approach is further supported with theoretical arguments, specifically focusing on the localisation and approximation properties of FBPINNs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 70 references that are in the map. First posted on arXiv 8 Aug 2026.

Builds on

34 of 70 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  3. 2018On the Spectral Bias of Neural Networkscited by 1,341
  4. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  5. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  6. 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
  7. 2020On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networkscited by 284
  8. 2021Physics-informed neural networks with hard constraints for inverse designcited by 280
  9. 2019Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Datacited by 262
  10. 2022A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networkscited by 236
  11. 2021Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equationscited by 145
  12. 2021Exact imposition of boundary conditions with distance functions in physics-informed deep neural networkscited by 137
22 more
  1. 2023An Expert's Guide to Training Physics-informed Neural Networkscited by 126
  2. 2017A unified deep artificial neural network approach to partial differential equations in complex geometriescited by 122
  3. 2020Estimates on the generalization error of Physics Informed Neural Networks (PINNs) for approximating PDEscited by 116
  4. 2024Challenges in Training PINNs: A Loss Landscape Perspectivecited by 113
  5. 2021Multi-Objective Loss Balancing for Physics-Informed Deep Learningcited by 87
  6. 2024From PINNs to PIKANs: Recent Advances in Physics-Informed Machine Learningcited by 73
  7. 2022Error estimates for physics informed neural networks approximating the Navier-Stokes equationscited by 63
  8. 2025Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspectivecited by 56
  9. 2024ConFIG: Towards Conflict-free Training of Physics Informed Neural Networkscited by 46
  10. 2022Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodologycited by 44
  11. 2024Numerical analysis of physics-informed neural networks and related models in physics-informed machine learningcited by 39
  12. 2021Data vs. Physics: The Apparent Pareto Front of Physics-Informed Neural Networkscited by 27
  13. 2023An operator preconditioning perspective on training in physics-informed machine learningcited by 27
  14. 2022Constitutive model characterization and discovery using physics-informed deep learningcited by 17
  15. 2023Machine learning and domain decomposition methods -- a surveycited by 14
  16. 2025Simulating Three-dimensional Turbulence with Physics-informed Neural Networkscited by 14
  17. 2022A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEscited by 12
  18. 2024NeuroSEM: A hybrid framework for simulating multiphysics problems by coupling PINNs and spectral elementscited by 6
  19. 2025Hard-constraining Neumann boundary conditions in physics-informed neural networks via Fourier feature embeddingscited by 6
  20. 2023A hybrid physics-informed neural network based multiscale solver as a partial differential equation constrained optimization problemcited by 3
  21. 2026Constrained Neural Parameterization for Optimization in Function Spacescited by 2
  22. 2025Hybrid machine learning based scale bridging framework for permeability prediction of fibrous structurescited by 1

Built on by

Not cited yet.