Regional accuracy of physics-informed neural networks (PINNs) for recirculation in a deep lid-driven cavity

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 $\mathrm{Re}=100$, 250, 500, and 1000, evaluation on a common $121\times 605$ 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 $1.255\times 10^{-10}U$ to $2.332\times 10^{-9}U$, where $U$ is the lid-velocity scale. In a separate $161\times 801$ assessment at $\Rey=1000$, the refined workflow lowers interior velocity discrepancy from 5.624% to 2.658% and gauge-aligned pressure RMS discrepancy from $2.793\times 10^{-3}$ to $1.167\times 10^{-3}\rho U^2$. 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.