Regional accuracy of physics-informed neural networks (PINNs) for recirculation in a deep lid-driven cavity
physics.flu-dyn, math-ph, math.MP
Submitted: 2026-10-28
Updated: 2026-10-31
License: http://creativecommons.org/licenses/by/4.0/
The gist: Deep lid-driven cavities contain strong motion beneath the lid and much weaker recirculation at depth, so agreement in bulk velocity is an incomplete assessment of a computed flow.
Terminology
Abstract
Deep lid-driven cavities contain strong motion beneath the lid and much weaker recirculation at depth, so agreement in bulk velocity is an incomplete assessment of a computed flow. We examine data-free physics-informed neural networks (PINNs) for steady, two-dimensional incompressible flow in a cavity of depth-to-width ratio five at Reynolds numbers 100, 250, 500 and 1000. An established hard-constrained streamfunction formulation is combined with prescribed regional collocation, transferred initialization, and selected residual-scaling and envelope variants. Independent spectral/ hp calculations with the same Gaussian-regularized lid provide the reference fields. For a cavity of depth-to-width ratio D/W=5 at Reynolds numbers Re=100, 250, 500, and 1000, evaluation on a common 121 times605 grid gives interior relative velocity discrepancies of 5.130%--7.850%. Over the same cases, floor-region relative velocity discrepancies remain below 5%, with absolute RMS discrepancies ranging from 1.255 times10-10U to 2.332 times10-9U, where U is the lid-velocity scale. In a separate 161 times801 assessment at =1000, the refined workflow lowers interior velocity discrepancy from 5.624% to 2.658% and gauge-aligned pressure RMS discrepancy from 2.793 times10-3 to 1.167 times10-3ρU squared. The improvements compare accumulated training workflows and do not isolate regional sampling. Configuration rankings depend on both region and observable. These finite-budget comparisons establish where the retained workflows agree with the reference and where rotational-field discrepancies remain substantial.
Related papers
- Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
- Early onset of secondary shear instability in Kelvin-Helmholtz braids at high Reynolds number
- Rotational covariance, continuous spectrum and non-modal growth of three-dimensional planar weak viscous shock layers
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows
- Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows
- Size and shape of condensing steam jets and plumes