Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks

• URL: http://arxiv.org/abs/2606.06313v1
• Date: Thu, 04 Jun 2026 15:53:42 GMT
• Title: Wall Shear Stress Reconstruction from Concentration: Differentiable Physics and Physics-Informed Neural Networks
• Abstract summary: Wall shear stress governs near-wall transport dynamics and is a key hemodynamic indicator in cardiovascular flows.<n>In this work, we demonstrate such reconstruction from spatially limited passive scalar observations using two fundamentally different inverse frameworks.<n>The proposed framework opens a path toward estimation of near-wall hemodynamics from scalar transport data, with broader applicability to fluid flow problems.
• Score: 0.39998518782208775
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Wall shear stress (WSS) governs near-wall transport dynamics and is a key hemodynamic indicator in cardiovascular flows, yet remains difficult to infer accurately due to the need for precise computation of near-wall velocity gradients. Passive scalar fields, such as concentration or temperature, are advected by the same underlying velocity field and have the potential to uncover hidden flow physics metrics such as WSS. In this work, we demonstrate such reconstruction from spatially limited passive scalar observations using two fundamentally different inverse frameworks: a differentiable physics framework based on discrete adjoint, PDE-constrained optimization, which enforces the governing equations as hard constraints, and physics-informed neural networks (PINNs), which treat them as soft constraints. Benchmark problems include a 2D canonical backward-facing step (2D-BFS) and a 3D patient-specific stenotic coronary artery. For the 2D-BFS case, evaluated under three measurement scenarios (near-wall, far-field, and combined), PINN achieves high accuracy when near-wall data are available but fails when restricted to far-field measurements, whereas the differentiable physics approach recovers accurate WSS across all scenarios. In the 3D patient-specific case, the differentiable physics framework outperforms PINNs, yielding accurate WSS reconstruction. These results establish that measurement location and inverse formulation jointly determine reconstruction fidelity in scalar-based near-wall flow inference. The proposed framework opens a path toward estimation of near-wall hemodynamics from scalar transport data, with broader applicability to fluid flow problems where passive scalars can be observed.

Related papers

• Learning Unsteady Aneurysm Hemodynamics with Physics-Informed DeepONets [0.0]
  M3PI-DeepONet simultaneously predicts unsteady 3D flow velocity and pressure fields with an average relative L2 velocity error below 4% and pressure error around 5%.<n>This work advances the application of deep learning in cardiovascular disease modeling, marking step toward real-time, non-invasive clinical diagnostics.
  arXiv  Detail & Related papers  (2026-08-13T09:08:24Z)
• HIPNO: Symmetry-Aware Physics-Informed Neural Operators for Noninvasive Hemodynamic Inference [3.3014658977998397]
  Continuous hemodynamic monitoring guides treatment decisions in surgery and intensive care.<n>Gold-standard signals are only measured in severe cases due to risks associated with invasive measurement.<n>We introduce HIPNO to recover hemodynamic state from ubiquitous, non-invasive signals.
  arXiv  Detail & Related papers  (2026-08-08T07:03:49Z)
• ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction [81.07048249760953]
  longitudinal changes are often subtle and confined to specific anatomical regions.<n>Most subject-specific brain structure remains stable over time.<n>ProgFormer is a hierarchical voxel-space Diffusion Transformer for longitudinal brain MRI prediction.
  arXiv  Detail & Related papers  (2026-07-30T00:13:42Z)
• Anisotropic Permeability Tensor Prediction from Porous Media Microstructure via Physics-Informed Progressive Transfer Learning with Hybrid CNN-Transformer [0.0]
  Prediction of permeability tensors from pore-scale microstructure images is essential for subsurface flow modeling, yet direct numerical simulation requires hours per sample.<n>A physics-informed deep learning framework is presented that resolves this bottleneck by combining a MaxViT hybrid CNN-Transformer architecture with progressive transfer learning and differentiable physical constraints.
  arXiv  Detail & Related papers  (2026-03-18T09:41:01Z)
• Differentiable Autoencoding Neural Operator for Interpretable and Integrable Latent Space Modeling [0.24554686192257422]
  Scientific machine learning has enabled the extraction of physical insights from high-dimensional flow data using linear and nonlinearity reduction techniques.<n>Despite these advances, interpretability within the latent space remains a challenge.<n>We propose the DIDIANiable Autoencoding Neural Operator (O) that constructs physically interpretable latent spaces for both dimensional and geometric reduction.
  arXiv  Detail & Related papers  (2025-09-30T19:57:52Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• Forecasting Continuous Non-Conservative Dynamical Systems in SO(3) [51.510040541600176]
  We propose a novel approach to modeling the rotation of moving objects in computer vision.<n>Our approach is agnostic to energy and momentum conservation while being robust to input noise.<n>By learning to approximate object dynamics from noisy states during training, our model attains robust extrapolation capabilities in simulation and various real-world settings.
  arXiv  Detail & Related papers  (2025-08-11T09:03:10Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs)<n>We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations.<n>We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall [13.113110989699571]
  We consider the estimation of vector-valued quantities on the wall of three-dimensional geometric artery models. We employ group equivariant graph convolution in an end-to-end SE(3)-equivariant neural network that operates directly on triangular surface meshes. We show that our method is powerful enough to accurately predict transient, vector-valued WSS over the cardiac cycle while conditioned on a range of different inflow boundary conditions.
  arXiv  Detail & Related papers  (2022-12-09T18:16:06Z)
• Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignments [110.79706180350507]
  We show that our proposed loss can be used to define temporal-temporal baryechecenters as Fr'teche means duality. Experiments on handwritten letters and brain imaging data confirm our theoretical findings.
  arXiv  Detail & Related papers  (2022-03-11T09:46:22Z)
• Simultaneous boundary shape estimation and velocity field de-noising in Magnetic Resonance Velocimetry using Physics-informed Neural Networks [70.7321040534471]
  Magnetic resonance velocimetry (MRV) is a non-invasive technique widely used in medicine and engineering to measure the velocity field of a fluid. Previous studies have required the shape of the boundary (for example, a blood vessel) to be known a priori. We present a physics-informed neural network that instead uses the noisy MRV data alone to infer the most likely boundary shape and de-noised velocity field.
  arXiv  Detail & Related papers  (2021-07-16T12:56:09Z)

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.