Predicting Time-Dependent Flow Over Complex Geometries Using Operator Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rabeh, Ali, Murugaiyan, Suresh, Krishnamurthy, Adarsh, Ganapathysubramanian, Baskar
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915653299994624
author Rabeh, Ali
Murugaiyan, Suresh
Krishnamurthy, Adarsh
Ganapathysubramanian, Baskar
author_facet Rabeh, Ali
Murugaiyan, Suresh
Krishnamurthy, Adarsh
Ganapathysubramanian, Baskar
contents Fast, geometry-generalizing surrogates for unsteady flow remain challenging. We present a time-dependent, geometry-aware Deep Operator Network that predicts velocity fields for moderate-Re flows around parametric and non-parametric shapes. The model encodes geometry via a signed distance field (SDF) trunk and flow history via a CNN branch, trained on 841 high-fidelity simulations. On held-out shapes, it attains $\sim 5\%$ relative L2 single-step error and up to 1000X speedups over CFD. We provide physics-centric rollout diagnostics, including phase error at probes and divergence norms, to quantify long-horizon fidelity. These reveal accurate near-term transients but error accumulation in fine-scale wakes, most pronounced for sharp-cornered geometries. We analyze failure modes and outline practical mitigations. Code, splits, and scripts are openly released at: https://github.com/baskargroup/TimeDependent-DeepONet to support reproducibility and benchmarking.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04434
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Predicting Time-Dependent Flow Over Complex Geometries Using Operator Networks
Rabeh, Ali
Murugaiyan, Suresh
Krishnamurthy, Adarsh
Ganapathysubramanian, Baskar
Fluid Dynamics
Machine Learning
Fast, geometry-generalizing surrogates for unsteady flow remain challenging. We present a time-dependent, geometry-aware Deep Operator Network that predicts velocity fields for moderate-Re flows around parametric and non-parametric shapes. The model encodes geometry via a signed distance field (SDF) trunk and flow history via a CNN branch, trained on 841 high-fidelity simulations. On held-out shapes, it attains $\sim 5\%$ relative L2 single-step error and up to 1000X speedups over CFD. We provide physics-centric rollout diagnostics, including phase error at probes and divergence norms, to quantify long-horizon fidelity. These reveal accurate near-term transients but error accumulation in fine-scale wakes, most pronounced for sharp-cornered geometries. We analyze failure modes and outline practical mitigations. Code, splits, and scripts are openly released at: https://github.com/baskargroup/TimeDependent-DeepONet to support reproducibility and benchmarking.
title Predicting Time-Dependent Flow Over Complex Geometries Using Operator Networks
topic Fluid Dynamics
Machine Learning
url https://arxiv.org/abs/2512.04434