Metraipolis › archive › dc_36bd5daa05bd
Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks — arXiv:2610.37986
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.37986
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:23:20.220Z
- SHA-256 of the archived text
b66b577f95465e25b58244bb93eac90b4af320caa1a3cf98f9060a03948e0b80- Stable URL of this page
https://metraipolis.com/documento/dc_36bd5daa05bd
How to cite
Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks — arXiv:2610.37986 — arXiv (en), https://arxiv.org/abs/2610.37986 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_36bd5daa05bd (Metraipolis archive dc_36bd5daa05bd, sha256 b66b577f95465e25b58244bb93eac90b4af320caa1a3cf98f9060a03948e0b80)
BibTeX
@misc{dc36bd5daa05bd,
title = {Predicting Sparse Observables in Parameterized Unsteady Flows Using Coarse-Mesh Graph Neural Networks — arXiv:2610.37986},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.37986},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_36bd5daa05bd; sha256 b66b577f95465e25b58244bb93eac90b4af320caa1a3cf98f9060a03948e0b80},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.37986. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Full-order surrogates for high-dimensional nonlinear flows are often unnecessary when applications require only selected degrees of freedom. We propose reduced-order models that bypass full-state reconstruction by deploying graph neural networks (GNNs) directly on coarse meshes. Applied to parameterized 2D/3D confined cylinder flows and an unevenly heated cavity over Reynolds/Rayleigh-number ranges, the models generalize to unseen conditions and accurately predict sparse probe locations and integrated quantities. Coarse-mesh GNNs match or outperform finer-mesh surrogates while reducing training time and memory, even for 3D chaotic dynamics. A dynamics-informed adaptive sampling strategy guided by frequency-spectrum variations reduces maximum errors by an order of magnitude versus uniform sampling at negligible cost. Coarse-mesh training also makes noise-augmented multi-step unrolling practical, improving long-horizon autoregressive predictions. The approach outperforms parametric DMD, sparse MLPs, U-Nets, and Fourier neural operators at lower cost, and enables system identification and state estimation from sparse observations. These results show that coarse-mesh representations, adaptive sampling, and noise-augmented unrolled training form an efficient framework for reduced-order modeling of parameterized unsteady flows without solver-resolution reconstruction. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Fluid Dynamics (physics.flu-dyn). Pagina del lavoro: https://arxiv.org/abs/2610.37986 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:12:44.093Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).