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

Physical Review Fluids

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access
  • Access by Xinjiang University

Sharper predictions: The role of loss functions for enhanced turbulent-flow sensing

A. G. Balasubramanian*

A. Cremades

R. Vinuesa

O. Tammisola†

  • *Contact author: argb@mech.kth.se
  • †Contact author: outi@mech.kth.se
PDF

Phys. Rev. Fluids 11, 044907 – Published 16 April, 2026

DOI: https://doi.org/10.1103/26js-tpg4

Abstract

Accurate estimation of near-wall turbulence from limited surface measurements is critical for various practical and experimental applications; however, it remains challenging due to the complex and multiscale characteristics inherent to turbulent flows. Recent developments in data-driven methods have improved performance over traditional linear approaches but are often limited by loss functions that primarily penalize pointwise errors. In this study, we consider a composite, spectrally informed loss function that augments the conventional mean-squared error with terms that explicitly promote statistical consistency of fluctuation levels and spectral energy distributions. This loss function is evaluated using a baseline convolutional network model applied to direct numerical simulation datasets of turbulent open-channel flow at friction Reynolds numbers, Reτ=180 and 550. We show that the considered loss function substantially reduces reconstruction errors of near-wall fluctuation velocity fields obtained from the network model using wall-shear stress and wall-pressure data as inputs. The proposed method recovers up to a threefold improvement in reconstruction accuracy relative to baseline employing mean-squared loss and retains energy content at small-scale structures. We further show that reconstruction accuracy is only mildly affected when the input wall signals are contaminated with 5–100% Gaussian noise and retains energy content in small flow structures when predicting from coarse wall inputs, indicating that the trained models generalize robustly to noisy, experimentally relevant conditions. Our results demonstrate that properly designed loss functions can improve reconstruction accuracy, highlighting the importance of training strategy in achieving efficient, high-performance neural-network models for practical nonintrusive sensing applications. The present study also provides a foundation for future extensions with advanced architectures, such as generative or diffusion-based models to further improve reconstruction of turbulent flow fields in complex settings.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (53)

  1. K. Duraisamy, G. Iaccarino, and H. Xiao, Turbulence modeling in the age of data, Annu. Rev. Fluid Mech. 51, 357 (2019).
  2. R. Vinuesa, Perspectives on predicting and controlling turbulent flows through deep learning, Phys. Fluids 36, 031401 (2024).
  3. A. Cremades, S. Hoyas, and R. Vinuesa, Classically studied coherent structures only paint a partial picture of wall-bounded turbulence, Nat. Commun. 16, 10189 (2025).
  4. J. Kutz, Deep learning in fluid dynamics, J. Fluid Mech. 814, 1 (2017).
  5. S. Brunton, B. Noack, and P. Koumoutsakos, Machine learning for fluid mechanics, Annu. Rev. Fluid Mech. 52, 477 (2020).
  6. R. Vinuesa and S. Brunton, Emerging trends in machine learning for computational fluid dynamics, Comput. Sci. Eng. 24, 33 (2023).
  7. K. Duraisamy, Perspectives on machine learning-augmented Reynolds-averaged and large eddy simulation models of turbulence, Phys. Rev. Fluids 6, 050504 (2021).
  8. J. Ling, A. Kurzawski, and J. Templeton, Reynolds averaged turbulence modelling using deep neural networks with embedded invariance, J. Fluid Mech. 807, 155 (2016).
  9. Y. Zhao, H. Akolekar, J. Weatheritt, V. Michelassi, and R. Sandberg, RANS turbulence model development using CFD-driven machine learning, J. Comput. Phys. 411, 109413 (2020).
  10. H. Eivazi, M. Tahani, P. Schlatter, and R. Vinuesa, Physics-informed neural networks for solving Reynolds-averaged Navier–Stokes equations, Phys. Fluids 34, 075117 (2022).
  11. Z. Wang, K. Luo, D. Li, J. Tan, and J. Fan, Investigations of data-driven closure for subgrid-scale stress in large-eddy simulation, Phys. Fluids 30, 125101 (2018).
  12. H. Bae and P. Koumoutsakos, Scientific multi-agent reinforcement learning for wall-models of turbulent flows, Nat. Commun. 13, 1443 (2022).
  13. J. Sirignano and J. MacArt, Deep learning closure models for large-eddy simulation of flows around bluff bodies, J. Fluid Mech. 966, A26 (2023).
  14. M. Kurz, P. Offenhäuser, and A. Beck, Deep reinforcement learning for turbulence modeling in large eddy simulations, Int. J. Heat Fluid Flow 99, 109094 (2023).
  15. L. Guastoni, A. Güemes, A. Ianiro, S. Discetti, P. Schlatter, H. Azizpour, and R. Vinuesa, Convolutional-network models to predict wall-bounded turbulence from wall quantities, J. Fluid Mech. 928, A27 (2021).
  16. A. Balasubramanian, L. Guastoni, P. Schlatter, H. Azizpour, and R. Vinuesa, Predicting the wall-shear stress and wall pressure through convolutional neural networks, Int. J. Heat Fluid Flow 103, 109200 (2023).
  17. K. Fukami, K. Fukagata, and K. Taira, Super-resolution reconstruction of turbulent flows with machine learning, J. Fluid Mech. 870, 106 (2019).
  18. A. Güemes, S. Discetti, A. Ianiro, B. Sirmacek, H. Azizpour, and R. Vinuesa, From coarse wall measurements to turbulent velocity fields through deep learning, Phys. Fluids 33, 075121 (2021).
  19. K. Fukami and K. Taira, Single-snapshot machine learning for super-resolution of turbulence, J. Fluid Mech. 1001, A32 (2024).
  20. A. Lozano-Durán, H. Bae, and M. Encinar, Causality of energy-containing eddies in wall turbulence, J. Fluid Mech. 882, A2 (2020).
  21. D. Floryan and M. Graham, Data-driven discovery of intrinsic dynamics, Nat. Mach. Intell. 4, 1113 (2022).
  22. A. Linot and M. Graham, Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flow, J. Fluid Mech. 973, A42 (2023).
  23. A. Solera-Rico, C. Sanmiguel Vila, M. Gómez-López, Y. Wang, A. Almashjary, S. Dawson, and R. Vinuesa, β-variational autoencoders and transformers for reduced-order modelling of fluid flows, Nat. Commun. 15, 1361 (2024).
  24. M. Raissi, A. Yazdani, and G. E. Karniadakis, Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations, Science 367, 1026 (2020).
  25. R. Vinuesa and S. Brunton, Enhancing computational fluid dynamics with machine learning, Nat. Comput. Sci. 2, 358 (2022).
  26. H. Gao, L. Sun, and J.-X. Wang, Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels, Phys. Fluids 33, 073603 (2021).
  27. H. Eivazi, Y. Wang, and R. Vinuesa, Physics-informed deep-learning applications to experimental fluid mechanics, Meas. Sci. Technol. 35, 075303 (2024).
  28. R. Vinuesa, S. Brunton, and B. McKeon, The transformative potential of machine learning for experiments in fluid mechanics, Nat. Rev. Phys. 5, 536 (2023).
  29. P. A. Srinivasan, L. Guastoni, H. Azizpour, P. Schlatter, and R. Vinuesa, Predictions of turbulent shear flows using deep neural networks, Phys. Rev. Fluids 4, 054603 (2019).
  30. H. Eivazi, L. Guastoni, P. Schlatter, H. Azizpour, and R. Vinuesa, Recurrent neural networks and Koopman-based frameworks for temporal predictions in a low-order model of turbulence, Int. J. Heat Fluid Flow 90, 108816 (2021).
  31. G. Borrelli, L. Guastoni, H. Eivazi, P. Schlatter, and R. Vinuesa, Predicting the temporal dynamics of turbulent channels through deep learning, Int. J. Heat Fluid Flow 96, 109010 (2022).
  32. J. Rabault, M. Kuchta, A. Jensen, U. Réglade, and N. Cerardi, Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control, J. Fluid Mech. 865, 281 (2019).
  33. J. Park and H. Choi, Machine-learning-based feedback control for drag reduction in a turbulent channel flow, J. Fluid Mech. 904, A24 (2020).
  34. C. Vignon, J. Rabault, and R. Vinuesa, Recent advances in applying deep reinforcement learning for flow control: Perspectives and future directions, Phys. Fluids 35, 031301 (2023).
  35. L. Guastoni, J. Rabault, P. Schlatter, H. Azizpour, and R. Vinuesa, Deep reinforcement learning for turbulent drag reduction in channel flows, EPJ E 46, 27 (2023).
  36. A. Cremades, S. Hoyas, and R. Vinuesa, Additive-feature-attribution methods: A review on explainable artificial intelligence for fluid dynamics and heat transfer, Int. J. Heat Fluid Flow 112, 109662 (2025).
  37. A. Cremades, S. Hoyas, R. Deshpande, P. Quintero, M. Lellep, W. Lee, J. Monty, N. Hutchins, M. Linkmann, I. Marusic, and R. Vinuesa, Identifying regions of importance in wall-bounded turbulence through explainable deep learning, Nat. Commun. 15, 3864 (2024).
  38. E. Lagemann, J. Roeb, S. Brunton, and C. Lagemann, A deep learning approach to wall-shear stress quantification: From numerical training to zero-shot experimental application, J. Fluid Mech. 1014, A1 (2025).
  39. N. Rahaman, A. Baratin, D. Arpit, F. Draxler, M. Lin, F. Hamprecht, Y. Bengio, and A. Courville, On the spectral bias of neural networks, in Proceedings of the 36th International Conference on Machine Learning, edited by K. Chaudhuri and R. Salakhutdinov (PMLR, 2019), Vol. 97, pp. 5301–5310.
  40. M. Tancik, P. Srinivasan, B. Mildenhall, S. Fridovich-Keil, N. Raghavan, U. Singhal, R. Ramamoorthi, J. Barron, and R. Ng, Fourier features let networks learn high frequency functions in low dimensional domains, in Advances in Neural Information Processing Systems, edited by H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Curran Associates, Inc., 2020), Vol. 33, pp. 7537–7547.
  41. K. Taira, G. Rigas, and K. Fukami, Machine learning in fluid dynamics: A critical assessment, Phys. Rev. Fluids 10, 090701 (2025).
  42. M. Chevalier, A. Lundbladh, and D. Henningson, SIMSON: A pseudo-spectral solver for incompressible boundary layer flow, KTH Tech. Rep. Trita-Mek 7 (KTH, 2007).
  43. S. Hoyas, R. Vinuesa, P. Schmid, and H. Nagib, Sensitivity study of resolution and convergence requirements for the extended overlap region in wall-bounded turbulence, Phys. Rev. Fluids 9, L082601 (2024).
  44. M. Morimoto, K. Fukami, K. Zhang, A. Nair, and K. Fukagata, Convolutional neural networks for fluid flow analysis: Toward effective metamodeling and low dimensionalization, Theor. Comput. Fluid Dyn. 35, 633 (2021).
  45. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  46. Z.-Q. Xu, Y. Zhang, and Y. Xiao, Training behavior of deep neural network in frequency domain, in Neural Information Processing, edited by T. Gedeon, K. Wong, and M. Lee, Lecture Notes in Computer Science, Vol. 11953 (Springer International Publishing, Cham, 2019), pp. 264–274.
  47. A. Balasubramanian, R. Vinuesa, and O. Tammisola, Prediction of flow and polymeric stresses in a viscoelastic turbulent channel flow using convolutional neural networks, J. Fluid Mech. 1009, A36 (2025).
  48. C. Yan, S. Foo, V. Trinh, D. Yeung, K. Wong, and W. Wong, Fourier amplitude and correlation loss: Beyond using L2 loss for skillful precipitation nowcasting, Advances in Neural Information Processing Systems, edited by A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Curran Associates, Inc., 2024), Vol. 37, pp. 100007–100041.
  49. D. Fuoli, L. Van Gool, and R. Timofte, Fourier space losses for efficient perceptual image super-resolution, in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (IEEE, 2021), pp. 2360–2369.
  50. M. Bode, M. Gauding, K. Kleinheinz, and H. Pitsch, Deep learning at scale for subgrid modeling in turbulent flows: regression and reconstruction, in High Performance Computing, edited by M. Weiland, G. Juckeland, S. Alam, and H. Jagode, Lecture Notes in Computer Science, Vol. 11887 (Springer, Cham, 2019), pp. 541–560.
  51. 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).
  52. L. Guastoni and R. Vinuesa, A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models: Fluid dynamics, Nat. Mach. Intell. 7, 816 (2025).
  53. A. Balasubramanian, Code repository of Sharper predictions: The role of loss functions for enhanced turbulent-flow sensing, https://github.com/KTH-Complex-fluids-group/2026_Sharper-predictions-The-role-of-loss-functions-for-enhanced-turbulent-flow-sensing (2026).

Outline

Information

Phys. Rev. Fluids 11, 044907– Published 16 April, 2026
  • Received 15 December 2025
  • Accepted 9 March 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI. Funded by Bibsam.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation