Attention:The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Thursday, November 12th until 12:00 AM ET on Friday, November 13th due to maintenance. We apologize for the inconvenience.


This content will become publicly available on February 25, 2027

Title: Conditional flow matching for generative modelling of near-wall turbulence with quantified uncertainty
Reconstructing near-wall turbulence from wall-based measurements is a critical yet inherently ill-posed problem in wall-bounded flows, where limited sensing and spatially heterogeneous flow–wall coupling challenge deterministic estimation strategies. To address this, we introduce a novel generative modelling framework based on conditional flow matching for synthesising instantaneous velocity fluctuation fields from wall observations, with explicit quantification of predictive uncertainty. Our method integrates continuous-time flow matching with a probabilistic forward operator trained using stochastic weight-averaging Gaussian, enabling zero-shot conditional generation without model re-training. We demonstrate that the proposed approach not only recovers physically realistic, statistically consistent turbulence structures across the near-wall region but also effectively adapts to various sensor configurations, including sparse, incomplete and low-resolution wall measurements. The model achieves robust uncertainty-aware reconstruction, preserving flow intermittency and structure even under significantly degraded observability. Compared with classical linear stochastic estimation and deterministic convolutional neural network methods, our stochastic generative learning framework exhibits superior generalisation for unseen realisations under same flow conditions and resilience under measurement sparsity with quantified uncertainty. This work establishes a robust semi-supervised generative modelling paradigm for data-consistent flow reconstruction and lays the foundation for uncertainty-aware, sensor-driven modelling of wall-bounded turbulence.  more » « less
Award ID(s):
2535515 2047127
PAR ID:
10693094
Author(s) / Creator(s):
; ;
Publisher / Repository:
Cambridge University Press
Date Published:
Journal Name:
Journal of Fluid Mechanics
Volume:
1029
ISSN:
0022-1120
Subject(s) / Keyword(s):
Sponsoring Org:
National Science Foundation
More Like this
  1. Turbulent flows, characterized by their chaotic and stochastic nature, have historically presented formidable challenges to predictive computational modeling. Traditional eddy-resolved numerical simulations often require vast computational resources, making them impractical or infeasible for numerous engineering applications. As an alternative, deep learning-based surrogate models have emerged, offering data-drive solutions. However, these are typically constructed within deterministic settings, leading to shortfall in capturing the innate chaotic and stochastic behaviors of turbulent dynamics. In this study, we introduce a novel generative framework grounded in probabilistic diffusion models for versatile generation of spatiotemporal turbulence under various conditions. Our method unifies both unconditional and conditional sampling strategies within a Bayesian framework, which can accommodate diverse conditioning scenarios, including those with a direct differentiable link between specified conditions and generated unsteady flow outcomes, as well as scenarios lacking such explicit correlations. A notable feature of our approach is the method proposed for long-span flow sequence generation, which is based on autoregressive gradient-based conditional sampling, eliminating the need for cumbersome retraining processes. We evaluate and showcase the versatile turbulence generation capability of our framework through a suite of numerical experiments, including: (1) the synthesis of Large Eddy Simulations (LES) simulated instantaneous flow sequences from unsteady Reynolds-Averaged Navier–Stokes (URANS) inputs; (2) holistic generation of inhomogeneous, anisotropic wall-bounded turbulence, whether from given initial conditions, prescribed turbulence statistics, or entirely from scratch; (3) super-resolved generation of high-speed turbulent boundary layer flows from low-resolution data across a range of input resolutions. Collectively, our numerical experiments highlight the merit and transformative potential of the proposed methods, making a significant advance in the field of turbulence generation. 
    more » « less
  2. Transient growth and resolvent analyses are routinely used to assess nonasymptotic properties of fluid flows. In particular, resolvent analysis can be interpreted as a special case of viewing flow dynamics as an open system in which free-stream turbulence, surface roughness, and other irregularities provide sources of input forcing. We offer a comprehensive summary of the tools that can be employed to probe the dynamics of fluctuations around a laminar or turbulent base flow in the presence of such stochastic or deterministic input forcing and describe how input–output techniques enhance resolvent analysis. Specifically, physical insights that may remain hidden in the resolvent analysis are gained by detailed examination of input–output responses between spatially localized body forces and selected linear combinations of state variables. This differentiating feature plays a key role in quantifying the importance of different mechanisms for bypass transition in wall-bounded shear flows and in explaining how turbulent jets generate noise. We highlight the utility of a stochastic framework, with white or colored inputs, in addressing a variety of open challenges including transition in complex fluids, flow control, and physics-aware data-driven turbulence modeling. Applications with temporally or spatially periodic base flows are discussed and future research directions are outlined. 
    more » « less
  3. Accurate prediction of dynamical systems in unstructured meshes has recently shown successes in scientific simulations. Many dynamical systems have a nonnegligible level of stochasticity introduced by various factors (e.g. chaoticity), so there is a need for a unified framework that captures both deterministic and stochastic components in the rollouts of these systems. Inspired by regeneration learning, we propose a new model that combines generative and sequential networks to model dynamical systems. Specifically, we use an autoencoder to learn compact representations of full-space physical variables in a low-dimensional space. We then integrate a transformer with a conditional normalizing flow model to model the temporal sequence of latent representations. We evaluate the new model in both deterministic and stochastic systems. The model outperforms several competitive baseline models and makes more accurate predictions of deterministic systems. Its own prediction error is also reflected in its uncertainty estimations. When predicting stochastic systems, the proposed model generates high-quality rollout samples. The mean and variance of these samples well match the statistics of samples computed from expensive numerical simulations. 
    more » « less
  4. Accurate and uncertainty-aware wind power forecasting is essential for reliable and cost-effective power system operations. This paper presents a novel probabilistic forecasting framework based on diffusion probabilistic models. We adopted a two-stage modeling strategy—a deterministic predictor first generates baseline forecasts, and a conditional diffusion model then learns the distribution of residual errors. Such a two-stage decoupling strategy improves learning efficiency and sharpens uncertainty estimation. We employed the elucidated diffusion model (EDM) to enable flexible noise control and enhance calibration, stability, and expressiveness. For the generative backbone, we introduced a time-series-specific diffusion Transformer (TimeDiT) that incorporates modular conditioning to separately fuse numerical weather prediction (NWP) inputs, noise, and temporal features. The proposed method was evaluated using the public database from ten wind farms in the Global Energy Forecasting Competition 2014 (GEFCom2014). We further compared our approach with two popular baseline models, i.e., a distribution parameter regression model and a generative adversarial network (GAN)-based model. Results showed that our method consistently achieves superior performance in both deterministic metrics and probabilistic accuracy, offering better forecast calibration and sharper distributions. 
    more » « less
  5. This paper presents a novel machine learning framework for reconstructing low-order gust-encounter flow field and lift coefficients from sparse, noisy surface pressure measurements. Our study thoroughly investigates the time-varying response of sensors to gust–airfoil interactions, uncovering valuable insights into optimal sensor placement. To address uncertainties in deep learning predictions, we implement probabilistic regression strategies to model both epistemic and aleatoric uncertainties. Epistemic uncertainty, reflecting the model’s confidence in its predictions, is modelled using Monte Carlo dropout – as an approximation to the variational inference in the Bayesian framework – treating the neural network as a stochastic entity. On the other hand, aleatoric uncertainty, arising from noisy input measurements, is captured via learned statistical parameters, and propagate measurement noise through the network into the final predictions. Our results showcase the efficacy of this dual uncertainty quantification strategy in accurately predicting aerodynamic behaviour under extreme conditions while maintaining computational efficiency, underscoring its potential to improve online sensor-based flow estimation in real-world applications. 
    more » « less