Metraipolis › archive › dc_d3ddce5a025d
FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors — arXiv:2611.06912
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06912
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:22:47.312Z
- SHA-256 of the archived text
88c81c5eabbf242c9c5314e179df4250b88f068760c9c6255883d1f2d43c15a5- Stable URL of this page
https://metraipolis.com/documento/dc_d3ddce5a025d
How to cite
FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors — arXiv:2611.06912 — arXiv (en), https://arxiv.org/abs/2611.06912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3ddce5a025d (Metraipolis archive dc_d3ddce5a025d, sha256 88c81c5eabbf242c9c5314e179df4250b88f068760c9c6255883d1f2d43c15a5)
BibTeX
@misc{dcd3ddce5a025d,
title = {FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors — arXiv:2611.06912},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06912},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3ddce5a025d; sha256 88c81c5eabbf242c9c5314e179df4250b88f068760c9c6255883d1f2d43c15a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reconstructing full flow fields from sparse sensors requires prior assumptions about unmeasured regions and physical variables. Yet it remains unclear when learned models outperform classical estimators and which aspects of their predictions can be trusted. FlowReconBench evaluates ten learned and five classical methods on three regimes: a laminar cylinder wake across Reynolds numbers, two-dimensional Kolmogorov turbulence and a large-scale three-dimensional (3D) isotropic turbulence. Methods share leakage-controlled splits and sensor draws and are scored on per-channel error, ensemble spread, calibration, spectra and cost. The leading method changes for each regime. Classical methods perform strongly in low-order and dense-sensing regimes. On the cylinder wake, linear stochastic estimation and gappy proper orthogonal decomposition lead, including for unobserved pressure. In 3D, inverse-distance weighting matches the best learned methods on observed channels. Data-driven methods become superior at decreasing sensor density or poor sensor observability. On Kolmogorov flow, continuous ranked probability score and error yield different method rankings: generative models offer broader but underdispersed ensembles, while deterministic models prioritize pointwise error. Generative models balance this tradeoff through their sampler budget, with a larger budget improving ensemble quality at higher computational cost. In 3D, scaling tests demonstrate that queryable methods are flat in memory, while full-grid construction methods run out of memory. Observing only 2 of 4 fields leaves the problem kinematically underconstrained, yet a latent model can reproduce structural similarities to the ground truth. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Fluid Dynamics (physics.flu-dyn) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.06912 — 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 2026-11-05T18:15:49.045Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).