Searcharxiv⌕ Search

arXiv · 2610.22743

Fourier-Feature-Embedded Complex-Valued Physics-Informed Convolutional Residual Networks for Sparse and Gappy Noisy Flow-Field Reconstruction

Abstract

Reconstructing flow fields from sparse and noisy measurements becomes particularly challenging when data are completely absent from dynamically critical regions, such as the vortex-formation region of a wake. Conventional interpolation and numerical reconstruction methods generally require sufficient spatial or boundary information, while physics-informed neural networks (PINNs) can also face difficulties when sparse and noisy observations provide little or no supervision in the region of interest. To address this gap, we propose a Fourier-feature-embedded complex-valued physics-informed convolutional residual network (FCV-PICRN) for sparse, gappy, and noisy flow-field reconstruction. The framework integrates Fourier features for oscillatory and multiscale structures, complex-valued representations for coupled amplitude--phase learning, and convolutional residual blocks constrained by the Navier--Stokes equations. The method is first verified using the Taylor--Green vortex at $Re=100$ and then evaluated for the cylinder wake at $Re=100$. Three severe missing-data configurations are imposed in the dynamically sensitive wake: a large hole, a large truncation, and a plus-shaped gap extending in both streamwise and transverse directions. These gaps are further combined with additive Gaussian and multiplicative speckle noise. Despite having no supervised velocity data inside the excluded regions, FCV-PICRN reconstructs velocity, pressure, and vorticity with high structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), and remains robust under Gaussian noise up to $20\%$. Finally, for forced two-dimensional Kolmogorov turbulence with $5\%$ Gaussian noise, FCV-PICRN yields lower reconstruction errors than a conventional PINN. These results demonstrate robust physics-informed reconstruction of severely incomplete and noisy flows across laminar and turbulent regimes.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Biswanath Barman, Rajendra K. Ray. 2026-10-15. Fourier-Feature-Embedded Complex-Valued Physics-Informed Convolutional Residual Networks for Sparse and Gappy Noisy Flow-Field Reconstruction. https://searcharxiv.com/abs/2610.22743

Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.

KEEP EXPLORING

Related papers

Statistical State Dynamics of Couette MHD Turbulence

The roll streak structure (RSS) is ubiquitous in shear flow turbulence and is fundamental to the dynamics of the self-sustaining process (SSP) maintaining the turbulent state. The formation and maintenance of the RSS in wall-bounded shear flow suggest the presence of an underlying instability that has recently been identified using statistical state dynamics (SSD). Due to the parallelism between the Navier-Stokes equation and the induction equation, it is reasonable to inquire whether the RSS in wall-bounded shear flow has a counterpart in the MHD equations formulated as an SSD. In this work we show that this is the case and that an analytic solution for the composite velocitymagnetic field RSS in the MHD SSD also arises from an instability, that this instability equilibrates to either a fixed point or to a turbulent state, that these turbulent statistical equilibria may be self sustaining, and that both the fixed point and the turbulent states may correspond to large scale coherent dynamos.

physics.flu-dyn↗

A physics-constrained neural solver for incompressible flows without labeled data

We present a physics-constrained neural solver for incompressible flow that requires neither labeled data nor supervised pretraining. The solver enforces incompressibility and boundary conditions (BCs) to strict tolerances. We attribute the limited Reynolds numbers of existing physics-informed approaches to insufficient enforcement of these constraints, on which conventional finite-difference and finite-volume solvers depend. We therefore formulate incompressible flow as a constrained optimization problem within the physics- and equality-constrained artificial neural network (PECANN) framework: the pressure Poisson residual is minimized subject to the momentum equations, continuity equation, and BCs imposed as equality constraints on the primitive variables, while a conditionally adaptive augmented Lagrangian method enforces each constraint. The pressure Poisson objective proves critical. Across all benchmarks, replacing it with the momentum residual fails to converge to accurate solutions under identical architecture and constraint enforcement, which we attribute to the global elliptic coupling of pressure and velocity that local momentum-residual minimization lacks. For advection-dominated flows, we introduce an adaptive vanishing entropy viscosity that stabilizes training while leaving the converged solution unchanged. The solver predicts lid-driven cavity flow up to Re = 7,500 with centerline velocity profiles matching benchmark data, and is further validated on flow over a backward-facing step at Re = 800, 3D unsteady Beltrami flow, and steady and unsteady flow past a circular cylinder under an inflow-outflow configuration, for which an ablation study identifies admissible outlet BCs for velocity and pressure. From a randomly initialized network and without external perturbations, the solver captures the spontaneous onset of periodic vortex shedding in unsteady cylinder flow.

physics.flu-dyn↗

Soft Mobility Theory

Predicting how a deformable body moves and deforms in a viscous flow underlies problems ranging from microorganism locomotion to soft microrobotics, yet existing frameworks are either problem-specific or ill-suited to inverse design. We propose a soft mobility theory. Applying the principle of virtual power to an assembly of hydrodynamically interacting spheres connected by springs and rods yields a saddle-point problem, whose explicit solution is a configuration-dependent ordinary differential equation for the generalized coordinates of the body. This soft mobility equation extends classical rigid-body mobility theory in that the elastic, body-force, and flow-coupling tensors all depend explicitly on the instantaneous deformation. It is not restricted to sphere assemblies: the same equation follows from the continuum problem of a hyperelastic body in a background Stokes flow, of which the assembly is a Galerkin restriction. We compute the mobility from the Rotne-Prager-Yamakawa approximation and validate the framework on canonical problems spanning rigid and flexible bodies in quiescent and shear flows. An open-source JAX implementation makes entire simulations end-to-end differentiable. This allows efficient gradient-based inverse design: as proofs of concept, we recover the asymptotic optimum of a three-sphere swimmer and design a soft gyrotactic "surfer" that exploits passive deformation to ascend faster than its rigid counterpart in a Taylor-Green flow.

physics.flu-dyn↗