Deep Micro Solvers for Rough-Wall Stokes Flow in a Heterogeneous Multiscale Method

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ström, Emanuel, Tornberg, Anna-Karin, Öktem, Ozan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918097261166592
author Ström, Emanuel
Tornberg, Anna-Karin
Öktem, Ozan
author_facet Ström, Emanuel
Tornberg, Anna-Karin
Öktem, Ozan
contents We propose a learned precomputation for the heterogeneous multiscale method (HMM) for rough-wall Stokes flow. A Fourier neural operator is used to approximate local averages over microscopic subsets of the flow, which allows to compute an effective slip length of the fluid away from the roughness. The network is designed to map from the local wall geometry to the Riesz representors for the corresponding local flow averages. With such a parameterisation, the network only depends on the local wall geometry and as such can be trained independent of boundary conditions. We perform a detailed theoretical analysis of the statistical error propagation, and prove that under suitable regularity and scaling assumptions, a bounded training loss leads to a bounded error in the resulting macroscopic flow. We then demonstrate on a family of test problems that the learned precomputation performs stably with respect to the scale of the roughness. The accuracy in the HMM solution for the macroscopic flow is comparable to when the local (micro) problems are solved using a classical approach, while the computational cost of solving the micro problems is significantly reduced.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13902
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Deep Micro Solvers for Rough-Wall Stokes Flow in a Heterogeneous Multiscale Method
Ström, Emanuel
Tornberg, Anna-Karin
Öktem, Ozan
Numerical Analysis
Machine Learning
65N55 (Primary) 65R20, 68T99, 76D07 (Secondary)
We propose a learned precomputation for the heterogeneous multiscale method (HMM) for rough-wall Stokes flow. A Fourier neural operator is used to approximate local averages over microscopic subsets of the flow, which allows to compute an effective slip length of the fluid away from the roughness. The network is designed to map from the local wall geometry to the Riesz representors for the corresponding local flow averages. With such a parameterisation, the network only depends on the local wall geometry and as such can be trained independent of boundary conditions. We perform a detailed theoretical analysis of the statistical error propagation, and prove that under suitable regularity and scaling assumptions, a bounded training loss leads to a bounded error in the resulting macroscopic flow. We then demonstrate on a family of test problems that the learned precomputation performs stably with respect to the scale of the roughness. The accuracy in the HMM solution for the macroscopic flow is comparable to when the local (micro) problems are solved using a classical approach, while the computational cost of solving the micro problems is significantly reduced.
title Deep Micro Solvers for Rough-Wall Stokes Flow in a Heterogeneous Multiscale Method
topic Numerical Analysis
Machine Learning
65N55 (Primary) 65R20, 68T99, 76D07 (Secondary)
url https://arxiv.org/abs/2507.13902