生成式 AI 在湍流研究中的应用：基础、验证与基准（综述）
Generative AI in Turbulence: Foundations, Applications, Validations and Benchmarks
AI 导读
arXiv 论文（arXiv:2610.35123）综述生成式 AI 应对湍流问题的方法，重点分析 diffusion models、score-based 方法及相关概率输运形式，应用于随机闭合、超分辨率、数据同化和不确定性量化等场景。
正文 · 原文
Abstract:Generative AI offers new approaches to turbulence problems in which incomplete observations or unresolved d.o.f. admit multiple physically plausible solutions. Potential applications include stochastic closures, super-resolution, data assimilation, uncertainty quantification, and the generation of Eulerian and Lagrangian flow ensembles. However, turbulence is not a conventional image-generation problem. Its multiscale dynamics, intermittency, extreme events, rough velocity fields and intrinsically stochastic transport make visual realism, pointwise error, and low-order spectral agreement insufficient measures of physical fidelity. We examine where generative AI provide novel capabilities with emphasis on diffusion models, score-based methods, and related probability-transport formulations. We discuss their use in unconditional generation, probabilistic reconstruction, reduced-order modeling, temporal evolution, and mesh-free representations. We argue that validation must address turbulence properties: energy transfer, structure functions, anomalous scaling, pdf tails, coherent structures, conservation laws, temporal consistency, ensemble diversity and generalization. Finally, we discuss potential limitations in validation, baseline, data availability and reproducibility, and the need for a benchmark ecosystem combining open data, standardized challenges, hidden tests, physics-aware metrics, and documented failures. This paper serves as a bridge between two communities. For AI practitioners, we provide a fair and accessible introduction to turbulence, essential for appreciating the challenges posed by the field and for assessing the physical relevance of generative models. For turbulent practitioners, we provide an introduction to the key technological aspects of Generative AI, clarifying what these tools actually do, and where their potential and current limitations lie.
| Comments: | submitted to JFM-Perspective |
| Subjects: | Fluid Dynamics (physics.flu-dyn); Statistical Mechanics (cond-mat.stat-mech); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Chaotic Dynamics (nlin.CD) |
| Cite as: | arXiv:2610.35123 [physics.flu-dyn] |
| (or arXiv:2610.35123v1 [physics.flu-dyn] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35123 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Luca Biferale [view email]
[v1]
Mon, 26 Oct 2026 10:00:04 UTC (16,843 KB)
来源：arXiv cs.AI · arxiv.org