arXiv：cs.AI· Hanlin Kong, Jianan Wei, Yuntian Chen, Yujia Wang, Wenguan Wang·· 22 小时前
湍流感知框架实现高保真三维流场重建
High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics
AI 导读
研究者提出一种湍流感知的时间分辨三维流场重建框架，将多尺度神经算子与状态空间模型耦合以恢复体结构并保持时间一致性，同时引入Navier-Stokes残差作为软约束、并用混合专家机制支持对未知粗粒化的无监督适应。在典型湍流系统和大气再分析数据上，该框架相比学习类和经典基线降低了重建误差，更好地保留了多尺度空间结构与连贯时间演化。
正文
Abstract:High-fidelity three-dimensional turbulent flow fields are essential for scientific and engineering analyses, yet obtaining them through direct numerical simulation or high-resolution measurements remains expensive. Super-resolution reconstruction from coarse-grained data therefore offers a promising alternative, but remains fundamentally challenging because fine-scale structures are intrinsically three-dimensional and dynamically coupled across scales. Existing data-driven approaches still struggle to recover multiscale volumetric structures and their coherent temporal evolution. To address these limitations, we propose a turbulence-aware framework for time-resolved three-dimensional flow reconstruction. The framework couples a multiscale neural operator, designed to recover volumetric structures, with a state space model to promote temporal consistency in the reconstructed dynamics. In addition, Navier-Stokes residuals are incorporated as soft constraints to regularize the reconstruction toward physically plausible dynamics. A mixture-of-experts mechanism is also introduced to support unsupervised adaptation to unknown coarse-graining. Across evaluations on canonical turbulent systems and atmospheric reanalysis data, the proposed framework reduces reconstruction errors relative to learning-based and classical baselines, while better preserving multiscale spatial structure and coherent temporal evolution. These results validate the effectiveness of the proposed framework in reconstructing high-fidelity three-dimensional flow fields from coarse-grained data.
| Comments: | 66 pages, 9 main-text figures and 1 main-text table; includes Supplementary Information with 14 figures and 22 tables |
| Subjects: | Fluid Dynamics (physics.flu-dyn); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.18045 [physics.flu-dyn] |
| (or arXiv:2610.18045v1 [physics.flu-dyn] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18045 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hanlin Kong [view email]
[v1]
Tue, 13 Oct 2026 09:36:28 UTC (26,538 KB)
来源：arXiv：cs.AI · arxiv.org