[论文解读] Turbulence generation and data assimilation in wall-bounded flows with a latent diffusion model

Fabian Steinbrenner, Baris Turan+2 more|arXiv (Cornell University)|Mar 2, 2026

Model Reduction and Neural Networks被引用 0

一句话总结

该论文开发了一个条件潜在扩散框架（β-VAE + 扩散变换器）来生成4D湍流平行 Couette 流样本并利用观测进行数据同化，实现高压缩并再现关键统计量。

ABSTRACT

Wall-bounded turbulent flows are chaotic and multiscale, rendering real-time prediction at high Reynolds numbers computationally prohibitive in applications such as wind farms. Classical data assimilation methods are based on repeated solution of the governing equations and thus inherit this cost. Generative models instead learn the probability distribution of flow states, enabling scalable probabilistic reconstruction. Using plane Couette flow as a canonical configuration, we develop a generative framework that couples a $β$-variational autoencoder with a transformer-based diffusion model to generate four-dimensional spatiotemporal samples. Bayesian conditioning enables data assimilation without retraining and allows statistical constraints to be imposed through sampling. The framework is applied to a subdomain of turbulent plane Couette flow at $Re_h=1300$, where the corresponding DNS resolution in this region requires $O(10^6)$ spatial degrees of freedom. The diffusion model reproduces two-point correlations, energy spectra, and single-point statistics up to fourth order using $O(10)$ latent spatial degrees of freedom, yielding a compression ratio of $O(10^5)$ - one to two orders of magnitude above prior reports. Two assimilation scenarios demonstrate that conditional diffusion models with the proposed sampling strategy can enforce complex statistical constraints. However, enforcing these constraints while preserving physical fidelity and sample diversity introduces an inherent trade-off. Excessive conditioning can distort the learned diffusion prior, paralleling limitations of classical ensemble-based data assimilation. These results highlight both the promise of diffusion models as probabilistic surrogates for turbulent wall-bounded flows and the challenges of conditioning such models, establishing a foundation for future real-time reconstruction from operational data.

研究动机与目标

• 使用紧凑的潜在表示来捕捉四维湍流平行 Couette 流统计量。
• 开发一个两阶段生成模型（β-VAE 加扩散变换器）以从有限数据中恢复时空流场。
• 通过观测进行条件生成实现数据同化，无需重新训练。
• 评估再现高阶湍流水平统计量和能谱的能力。
• 探讨条件强度、物理保真度与样本多样性之间的权衡。

提出的方法

• 使用 β-VAE 将4D流场（u、v、w、p）压缩为低维潜在空间。
• 训练扩散变换器（DiT）对潜在轨迹建模并生成4D时空样本。
• 将编码器–解码器与 DiT 相连，使解码样本从潜在轨迹恢复4D流场。
• 应用条件扩散采样，通过贝叶斯条件框架强制观测。
• 通过对时间序列传感观测进行采样来进行条件化，以间接实现湍流统计约束，而非重新训练。

实验结果

研究问题

• RQ1 潜在扩散模型是否能从紧凑潜在表示再现壁面有界湍流的关键统计量（二维相关、能谱、至四阶）？
• RQ2 在保持先验随机性和物理保真度的前提下，条件扩散采样在多大程度上能强制观测？
• RQ3 在平行 Couette 流中，当 Reynolds_h = 1300 时，捕捉基本湍流动力学所需的最小潜在维数是多少？
• RQ4 条件强度如何影响样本多样性和统计准确性，这与传统数据同化挑战类似？
• RQ5 该框架是否能够实现对有限观测的实时流场重建的数据同化？

主要发现

• 扩散模型在使用大约 O(10) 个潜在空间维度的情况下就能再现二维相关、能谱和至四阶的单点统计量。
• 实现了大约 O(10^5) 的压缩比（潜在空间约 10^1 vs 全 DNS 约 10^6 自由度）。
• 两种同化场景表明，使用所提出采样的条件扩散可以强制复杂的统计约束。
• 条件过强会扭曲所学的扩散先验并降低统计保真度，暴露出类似于 EnKF 偏差的权衡。
• β-VAE 使湍流流动的潜在扩散框架实现降阶建模，为可扩展的概率替身提供了贡献。