arXiv：cs.LG· Arth Sojitra, Muhammad Abid, Omer San·· 3 小时前
从单一实现出发的均匀湍流极端超分辨率重建
Extreme-Scale Super-Resolution of Homogeneous Turbulence from a Single Realization
AI 导读
研究者用 WDSR 网络仅从单个高分辨率湍流实现中提取重叠 patch 训练，在二维均匀各向同性湍流的 x32 和 x64 超分辨率任务上重建出未见流场，并比传统插值更准确地恢复细尺度特征与高波数能量。与在 1、25、50、100 个完整高分辨率快照上训练的 WDSR 对比后，结果表明利用单一湍流实现内部的空间冗余即可实现准确重建，为高分辨率训练数据稀缺时的湍流超分辨率提供了数据高效方案。
正文
Abstract:Homogeneous turbulent flows exhibit recurring multiscale structures across spatially separated regions, suggesting that a single flow realization may contain sufficient information to learn representations of unresolved scales. We investigate this hypothesis through an extreme super-resolution framework in which a wide-activation deep super-resolution (WDSR) network is trained exclusively on overlapping patches extracted from a single high-resolution turbulent realization. Previously unseen flow fields are reconstructed through patchwise prediction followed by Hann-window-weighted overlap-add assembly. The framework is evaluated for two-dimensional homogeneous isotropic turbulence at super-resolution factors of x32 and x64, representing severe spatial under-resolution. Despite the limited training data, the proposed approach reconstructs coherent vortical structures and recovers fine-scale features more accurately than conventional interpolation. Spectral and statistical analyses further demonstrate improved recovery of high-wavenumber energy content and multiscale flow characteristics. To assess the effectiveness of exploiting internal spatial information, we compare the proposed framework against WDSR models trained on 1, 25, 50, and 100 complete high-resolution snapshots without patch extraction. This comparison distinguishes the benefits of localized learning from those associated with increasing the number of training realizations. The results demonstrate that exploiting spatial redundancy within a single turbulent realization enables accurate reconstruction of previously unseen flow fields, even under extreme spatial under-resolution. These findings establish single-realization patch-based learning as a promising data-efficient approach for turbulent super-resolution when high-resolution training data are scarce.
| Subjects: | Fluid Dynamics (physics.flu-dyn); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.20305 [physics.flu-dyn] |
| (or arXiv:2610.20305v1 [physics.flu-dyn] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20305 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Muhammad Abid [view email]
[v1]
Wed, 14 Oct 2026 14:54:20 UTC (22,692 KB)
来源：arXiv：cs.LG · arxiv.org