No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
Abstract
We test whether an architecture that succeeds on a simple flow regime also succeeds on a richer one, with each trained separately on each regime. We explore two transient flows under time-varying boundary conditions: the three-dimensional slurry film in chemical-mechanical planarisation (CMP), central to semiconductor manufacturing, and the two-dimensional Kármán vortex street (KVS). Eight surrogate models on one shared pipeline differ in whether they learn the full field or a latent representation, and in whether they predict in one shot or step by step. No single architecture wins both regimes. On the film, a one-shot full-field model reconstructs the cumulative wall shear stress to 2.7% relative error. On the wake, a latent autoregressive DeepONet retains 90% of the shedding power that direct and one-shot models damp to almost zero. The treatment of time decides the outcome. The self-sustained wake calls for autoregressive feedback and the boundary-driven film for a direct map. Pointwise RMSE hides the damped oscillation on the wake, compresses the sixfold lead on the film's process target, and picks the damped model under wake extrapolation. The evaluation scores five physical questions. Trained surrogates answer queries 10^3 to 10^4 times faster than the finite-element solver and pay off from the first query beyond the training set on the film and from the third on the wake. Neither the winning architecture nor its validation holds across regimes. The choice of surrogate should follow the dynamical character of the target flow, and its validation should resolve the failure modes.
Related
- Multi-regime Markov-switching models with time-varying transition probabilities: An application to U.S. Treasury yields
- Latent Inversion of Material Coefficients from Boundary Data via Finite Tests and Neural Surrogates
- Input-to-State Stabilization of a Coupled ODE-PDE System with Time-Varying Coefficients via Composite Boundary Control
- Identifying unknown time delay and spatially varying coefficients in a reaction-diffusion equation from boundary measurements
- An inverse spectral problem for the wave equation with a varying Robin parameter at the boundary
BibTeX
@misc{winkler2026free,
title = {{No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study}},
author = {Georg Winkler and Martin Stoll},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.23667},
eprint = {2607.23667},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.23667},
}
RIS
TY - UNPB
TI - No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study
AU - Georg Winkler
AU - Martin Stoll
PY - 2026
DA - 2026/09/24
PB - arXiv
DO - 10.48550/arxiv.2607.23667
UR - https://arxiv.org/abs/2607.23667
AB - We test whether an architecture that succeeds on a simple flow regime also succeeds on a richer one, with each trained separately on each regime. We explore two transient flows under time-varying boundary conditions: the three-dimensional slurry film in chemical-mechanical planarisation (CMP), central to semiconductor manufacturing, and the two-dimensional Kármán vortex street (KVS). Eight surrogate models on one shared pipeline differ in whether they learn the full field or a latent representation, and in whether they predict in one shot or step by step. No single architecture wins both regimes. On the film, a one-shot full-field model reconstructs the cumulative wall shear stress to 2.7% relative error. On the wake, a latent autoregressive DeepONet retains 90% of the shedding power that direct and one-shot models damp to almost zero. The treatment of time decides the outcome. The self-sustained wake calls for autoregressive feedback and the boundary-driven film for a direct map. Pointwise RMSE hides the damped oscillation on the wake, compresses the sixfold lead on the film's process target, and picks the damped model under wake extrapolation. The evaluation scores five physical questions. Trained surrogates answer queries 10^3 to 10^4 times faster than the finite-element solver and pay off from the first query beyond the training set on the film and from the third on the wake. Neither the winning architecture nor its validation holds across regimes. The choice of surrogate should follow the dynamical character of the target flow, and its validation should resolve the failure modes.
ER -