- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Fluids

Export citation

Export citation

Choose format for download:

Download Citation
  • Access by Xinjiang University

Generative reconstruction of spatiotemporal Wall-pressure in turbulent boundary layers via patchwise latent diffusion

Xiantao Fan1, Meet Hemant Parikh1, Yi Liu1,2, Xin-Yang Liu2, Junyi Guo1, Meng Wang2, and Jian-Xun Wang1,2,*

  • *Contact author: jw2837@cornell.edu
PDF

Phys. Rev. Fluids 11, 084607 – Published 13 August, 2026

DOI: https://doi.org/10.1103/ln5n-v7db

Abstract

Wall-pressure fluctuations beneath turbulent boundary layers induce structural vibration and acoustic radiation, especially in underwater and aerospace systems. Accurate prediction of their wave number-frequency spectra is critical for effective noise mitigation and design, yet empirical/analytical models rely on simplifying assumptions and miss the full spatiotemporal complexity, while high-fidelity simulations are prohibitive at high Reynolds numbers. Experimental measurements, though accessible, typically provide only pointwise signals and lack the resolution to recover full spatiotemporal fields. We propose a probabilistic generative framework that couples a patchwise (domain-decomposed) conditional neural field with a latent diffusion model to synthesize spatiotemporal wall-pressure fields under varying pressure-gradient conditions. The model conditions on sparse surface-sensor measurements and a low-cost mean-pressure descriptor, supports zero-shot adaptation to new sensor layouts, and produces ensembles with calibrated uncertainty. Validation against reference data shows accurate recovery of instantaneous fields and key statistics.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (65)

  1. Y. Na and P. Moin, The structure of wall-pressure fluctuations in turbulent boundary layers with adverse pressure gradient and separation, J. Fluid Mech. 377, 347 (1998).
  2. W. Devenport, N. Alexander, S. Glegg, and M. Wang, The sound of flow over rigid walls, Annu. Rev. Fluid Mech. 50, 435 (2018).
  3. S. Lee, L. Ayton, F. Bertagnolio, S. Moreau, T. P. Chong, and P. Joseph, Turbulent boundary layer trailing-edge noise: Theory, computation, experiment, and application, Prog. Aerosp. Sci. 126, 100737 (2021).
  4. M. Wang, J. B. Freund, and S. K. Lele, Computational prediction of flow-generated sound, Annu. Rev. Fluid Mech. 38, 483 (2006).
  5. B. Yang and Z. Yang, On the wavenumber–frequency spectrum of the wall pressure fluctuations in turbulent channel flow, J. Fluid Mech. 937, A39 (2022).
  6. G. Grasso, P. Jaiswal, H. Wu, S. Moreau, and M. Roger, Analytical models of the wall-pressure spectrum under a turbulent boundary layer with adverse pressure gradient, J. Fluid Mech. 877, 1007 (2019).
  7. S. L. Prigent, É. Salze, and C. Bailly, Deconvolution of wave-number-frequency spectra of wall pressure fluctuations, AIAA J. 58, 164 (2020).
  8. H. Choi and P. Moin, Grid-point requirements for large eddy simulation: Chapman's estimates revisited, Phys. Fluids 24, 011702 (2012).
  9. M. Slama, C. Leblond, and P. Sagaut, A Kriging-based elliptic extended anisotropic model for the turbulent boundary layer wall pressure spectrum, J. Fluid Mech. 840, 25 (2018).
  10. L. T. L. Pereira, F. Avallone, D. Ragni, and F. Scarano, A physics-based description and modelling of the wall-pressure fluctuations on a serrated trailing edge, J. Fluid Mech. 938, A28 (2022).
  11. R. L. Panton and J. H. Linebarger, Wall pressure spectra calculations for equilibrium boundary layers, J. Fluid Mech. 65, 261 (1974).
  12. N. Thomson and J. Rocha, Comparison of semi-empirical single point wall pressure spectrum models with experimental data, Fluids 6, 270 (2021).
  13. D. J. Fritsch, V. Vishwanathan, C. J. Roy, K. Todd Lowe, W. J. Devenport, P. Croaker, O. Tkachenko, D. Pook, G. Lane, S. Shubham, et al., Modeling the surface pressure spectrum beneath turbulent boundary layers in pressure gradients, AIAA J. 61, 2002 (2023).
  14. J. Dominique, J. Christophe, C. Schram, and R. D. Sandberg, Inferring empirical wall pressure spectral models with gene expression programming, J. Sound Vib. 506, 116162 (2021).
  15. S. Shubham, S. Pargal, S. Moreau, R. D. Sandberg, J. Yuan, A. Kushari, and M. Sanjose, Data-driven empirical wall pressure spectrum models for fan noise prediction, in: AIAA Aviation 2023 Forum (American Institute of Aeronautics and Astronautics, San Diego, CA, 2023), p. 3508.
  16. S. Shubham, R. D. Sandberg, and A. Kushari, More general wall pressure spectra models: Combining feature engineering with evolutionary algorithms, AIAA J. 62, 2622 (2024).
  17. Y. Jin, Y. Li, F. Liao, and J. Cai, Assessment of recent empirical wall-pressure auto-spectrum models under various pressure gradient conditions, Appl. Math. Modell. 146, 116154 (2025).
  18. L. Botero-BolÃvar, D. Huergo, F. L. dos Santos, C. H. Venner, L. D. de Santana, and E. Ferrer, An empirical wall-pressure spectrum model for aeroacoustic predictions based on symbolic regression, Appl. Acoust. 240, 110876 (2025).
  19. N. N. Kurhade, N. R. Vadlamani, and A. Haridas, Artificial neural networks and guided gene expression programming to predict wall pressure spectra beneath turbulent boundary layers, Phys. Fluids 35, 085123 (2023).
  20. J. Dominique, J. Van den Berghe, C. Schram, and M. Mendez, Artificial neural networks modeling of wall pressure spectra beneath turbulent boundary layers, Phys. Fluids 34, 035119 (2022).
  21. S. Zeng, K. Liu, W. Yang, M. Fu, G. Wu, and J. Zheng, Rapid prediction of rocket wall pressure fluctuation spectra using machine learning, Phys. Fluids 37, 035191 (2025).
  22. K. Poulinakis, D. Drikakis, I. W. Kokkinakis, and S. M. Spottswood, Deep learning reconstruction of pressure fluctuations in supersonic shock–boundary layer interaction, Phys. Fluids 35, 076117 (2023).
  23. K. Fukami, K. Fukagata, and K. Taira, Super-resolution reconstruction of turbulent flows with machine learning, J. Fluid Mech. 870, 106 (2019).
  24. K. Fukami, K. Fukagata, and K. Taira, Super-resolution analysis via machine learning: A survey for fluid flows, Theor. Comput. Fluid Dyn. 37, 421 (2023).
  25. K. Fukami, B. An, M. Nohmi, M. Obuchi, and K. Taira, Machine-learning-based reconstruction of turbulent vortices from sparse pressure sensors in a pump sump, J. Fluids Eng. 144, 121501 (2022).
  26. B. A. Danciu, V. A. Pagone, B. Böhm, M. Schmidt, and C. E. Frouzakis, Flow reconstruction in time-varying geometries using graph neural networks, arXiv:2411.08764.
  27. F. Sofos, D. Drikakis, and I. W. Kokkinakis, Comparison of super-resolution deep learning models for flow imaging, Comput. Fluids 283, 106396 (2024).
  28. R. Cheng, A. Shamooni, T. Zirwes, and A. Kronenburg, Improved super-resolution reconstruction of turbulent flows with spectral loss function, Phys. Fluids 37, 035208 (2025).
  29. K. Zeng, Y. Zhang, H. Xu, and X. Feng, Super-resolution reconstruction of turbulent flows with a hybrid framework of attention, Phys. Fluids 36, 065107 (2024).
  30. M. Diop, P. Dubois, H. Toubin, L. Planckaert, J.-F. Le Roy, and E. Garnier, Reconstruction of flow around a high-rise building from wake measurements using machine learning techniques, J. Wind Eng. Ind. Aerodyn. 230, 105149 (2022).
  31. J.-W. Hu and W.-W. Zhang, Mesh-Conv: Convolution operator with mesh resolution independence for flow field modeling, J. Comput. Phys. 452, 110896 (2022).
  32. V. Yadav, M. Casel, and A. Ghani, RF-PINNs: Reactive flow physics-informed neural networks for field reconstruction of laminar and turbulent flames using sparse data, J. Comput. Phys. 524, 113698 (2025).
  33. L. Zhu, X. Jiang, A. Lefauve, R. R. Kerswell, and P. Linden, New insights into experimental stratified flows obtained through physics-informed neural networks, J. Fluid Mech. 981, R1 (2024).
  34. C. Lee, Y. Ozawa, T. Nagata, T. Colonius, and T. Nonomura, Superresolution and analysis of three-dimensional velocity fields of underexpanded jets in different screech modes, Phys. Rev. Fluids 9, 104604 (2024).
  35. S. Rühling Cachay, B. Zhao, H. Joren, and R. Yu, Dyffusion: A dynamics-informed diffusion model for spatiotemporal forecasting, Adv. Neural Inf. Process. Syst. 36, 45259 (2023).
  36. R. Molinaro, S. Lanthaler, B. Raonić, T. Rohner, V. Armegioiu, S. Simonis, D. Grund, Y. Ramic, Z. Y. Wan, F. Sha, et al., Generative AI for fast and accurate statistical computation of fluids, arXiv:2409.18359.
  37. D. Shu, Z. Li, and A. B. Farimani, A physics-informed diffusion model for high-fidelity flow field reconstruction, J. Comput. Phys. 478, 111972 (2023).
  38. G. Kohl, L.-W. Chen, and N. Thuerey, Benchmarking autoregressive conditional diffusion models for turbulent flow simulation, in ICML 2024 AI for Science Workshop (OpenReview.net, Vienna, Austria, 2024).
  39. H. Gao, X. Han, X. Fan, L. Sun, L.-P. Liu, L. Duan, and J.-X. Wang, Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation, Comput. Methods Appl. Mech. Eng. 427, 117023 (2024).
  40. Y. Shehata, B. Holzschuh, and N. Thuerey, Improved sampling of diffusion models in fluid dynamics with Tweedie's formula, in: The Thirteenth International Conference on Learning Representations (OpenReview.net, Singapore, 2025).
  41. P. Du, M. H. Parikh, X. Fan, X.-Y. Liu, and J.-X. Wang, Conditional neural field latent diffusion model for generating spatiotemporal turbulence, Nat. Commun. 15, 10416 (2024).
  42. X.-Y. Liu, M. H. Parikh, X. Fan, P. Du, Q. Wang, Y.-F. Chen, and J.-X. Wang, CoNFiLD-inlet: Synthetic turbulence inflow using generative latent diffusion models with neural fields, Phys. Rev. Fluids 10, 054901 (2025).
  43. X. Fan, D. Akhare, and J.-X. Wang, Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence, Comput. Methods Appl. Mech. Eng. 433, 117478 (2025).
  44. M. Hemant Parikh, X. Fan, and J.-X. Wang, Conditional flow matching for generative modeling of near-wall turbulence with quantified uncertainty, J. Fluid Mech. 1029, A32 (2026).
  45. S. Meloni, F. Centracchio, E. De Paola, R. Camussi, and U. Iemma, Experimental characterisation and data-driven modelling of unsteady wall pressure fields induced by a supersonic jet over a tangential flat plate, J. Fluid Mech. 958, A27 (2023).
  46. J. Guo, P. Du, X. Fan, Y. Li, and J.-X. Wang, Conditional neural field for spatial dimension reduction of turbulence data: A comparison study, Phys. Fluids 38, 025153 (2026)
  47. V. Sitzmann, J. Martel, A. Bergman, D. Lindell, and G. Wetzstein, Implicit neural representations with periodic activation functions, Adv. Neural Inf. Process. Syst. 33, 7462 (2020).
  48. J. Ho and T. Salimans, Classifier-free diffusion guidance, arXiv:2207.12598.
  49. H. Chung, J. Kim, M. T. Mccann, M. L. Klasky, and J. C. Ye, Diffusion posterior sampling for general noisy inverse problems, in The Eleventh International Conference on Learning Representations (OpenReview.net, Kigali, Rwanda, 2023).
  50. B. Efron, Tweedie's formula and selection bias, J. Am. Stat. Assoc. 106, 1602 (2011).
  51. K. Kim and J. C. Ye, Noise2Score: Tweedie's approach to self-supervised image denoising without clean images, Adv. Neural Inf. Process. Syst. 34, 864 (2021).
  52. D. You, F. Ham, and P. Moin, Discrete conservation principles in large-eddy simulation with application to separation control over an airfoil, Phys. Fluids 20, 101515 (2008).
  53. H. Abe, Reynolds-number dependence of wall-pressure fluctuations in a pressure-induced turbulent separation bubble, J. Fluid Mech. 833, 563 (2017).
  54. H. Abe, Direct numerical simulation of a turbulent boundary layer with separation and reattachment over a range of Reynolds numbers, Fluid Dyn. Res. 51, 011409 (2019).
  55. T. S. Lund, X. Wu, and K. D. Squires, Generation of turbulent inflow data for spatially-developing boundary layer simulations, J. Comput. Phys. 140, 233 (1998).
  56. V. Kitsios, A. Sekimoto, C. Atkinson, J. A. Sillero, G. Borrell, A. G. Gungor, J. Jiménez, and J. Soria, Direct numerical simulation of a self-similar adverse pressure gradient turbulent boundary layer at the verge of separation, J. Fluid Mech. 829, 392 (2017).
  57. P. R. Spalart, Direct simulation of a turbulent boundary layer up to Rθ = 1410, J. Fluid Mech. 187, 61 (1988).
  58. Y. Na and P. Moin, Direct numerical simulation of a separated turbulent boundary layer, J. Fluid Mech. 374, 379 (1998).
  59. J. Wang, An intuitive tutorial to Gaussian process regression, Comput. Sci. Eng. 25, 4 (2023).
  60. O. Ashtari and T. M. Schneider, Identifying invariant solutions of wall-bounded three-dimensional shear flows using robust adjoint-based variational techniques, J. Fluid Mech. 977, A7 (2023).
  61. M. Wang and T. A. Zaki, Variational data assimilation in wall turbulence: From outer observations to wall stress and pressure, J. Fluid Mech. 1008, A26 (2025).
  62. J.-X. Wang and H. Xiao, Data-driven CFD modeling of turbulent flows through complex structures, Int. J. Heat Fluid Flow 62, 138 (2016).
  63. J.-X. Wang, R. Sun, and H. Xiao, Quantification of uncertainties in turbulence modeling: A comparison of physics-based and random matrix theoretic approaches, Int. J. Heat Fluid Flow 62, 577 (2016).
  64. T. Yin, M. Gharbi, R. Zhang, E. Shechtman, F. Durand, W. T. Freeman, and T. Park, One-step diffusion with distribution matching distillation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (IEEE, Seattle, WA, 2024), pp. 6613–6623.
  65. Y. Song, P. Dhariwal, M. Chen, and I. Sutskever, Consistency models, arXiv:2303.01469.

Outline

Information

Phys. Rev. Fluids 11, 084607– Published 13 August, 2026
  • Received 21 November 2025
  • Accepted 22 July 2026
Article part of CHORUS
Crossmark - Check for updates button

©2026 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation