No CrossRef data available.
Article contents
Generalizable super-resolution turbulence reconstruction from minimal training data
Published online by Cambridge University Press: 02 December 2025
Abstract
Fully resolving turbulent flows remains challenging due to a turbulent systems’ multiscale complexity. Existing data-driven approaches typically demand expensive retraining for each flow scenario and struggle to generalize beyond their training conditions. Leveraging the universality of small-scale turbulent motions (Kolmogorov’s K41 theory), we propose a scale-oriented zonal generative adversarial network (SoZoGAN) framework for high-fidelity, zero-shot turbulence generation across diverse domains. Unlike conventional methods, SoZoGAN is trained exclusively on a single dataset of moderate-Reynolds-number homogeneous isotropic turbulence (HIT). The framework employs a zonal decomposition strategy, partitioning turbulent snapshots into subdomains based on scale-sensitive physical quantities. Within each subdomain, turbulence is synthesized using scale-indexed models pretrained solely on the HIT database. A SoZoGAN demonstrates high accuracy, cross-domain generalizability and robustness in zero-shot super-resolution of unsteady flows, as validated on untrained HIT, turbulent boundary layer and channel flow. Its strong generalization, demonstrated for homogeneous and inhomogeneous turbulence cases, suggests potential applicability to a wider range of industrial and natural turbulent flows. The scale-oriented zonal framework is architecture-agnostic, readily extending beyond generative adversarial networks to other deep learning models.
Information
- Type
- JFM Papers
- Information
- Copyright
- © The Author(s), 2025. Published by Cambridge University Press
Footnotes
†
These authors contributed equally to this work.
References
Aluie, H. 2009 Hydrodynamic and magnetohydrodynamic turbulence: invariants, cascades, and locality. PhD thesis, The Johns Hopkins University, Baltimore.CrossRefGoogle Scholar
Benzi, R., Ciliberto, S., Tripiccione, R., Baudet, C., Massaioli, F. & Succi, S. 1993 Extended self-similarity in turbulent flows. Phys. Rev. E
48, R29.CrossRefGoogle ScholarPubMed
Brunton, S.L., Noack, B.R. & Koumoutsakos, P. 2020 Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 52, 477–508.CrossRefGoogle Scholar
Buaria, D., Clay, M.P., Sreenivasan, K.R. & Yeung, P.K. 2021 Small-scale isotropy and ramp-cliff structures in scalar turbulence. Phys. Rev. Lett. 126, 034504.CrossRefGoogle ScholarPubMed
Buaria, D. & Pumir, A. 2025 Universality of extreme events in turbulent flows. Phys. Rev. Fluids 10, L042601.CrossRefGoogle Scholar
Buaria, D. & Sreenivasan, K.R. 2023 Forecasting small-scale dynamics of fluid turbulence using deep neural networks. Proc. Natl Acad. Sci. USA 120 (30), e2305765120.CrossRefGoogle ScholarPubMed
Cao, N., Chen, S. & Doolen, G.D. 1999 Statistics and structures of pressure in isotropic turbulence. Phys. Fluids 11 (8), 2235–2250.CrossRefGoogle Scholar
Cao, Y., Tamura, T., Zhou, D., Bao, Y. & Han, Z. 2022 Topological description of near-wall flows around a surface-mounted square cylinder at high Reynolds numbers. J. Fluid Mech. 933, A39.CrossRefGoogle Scholar
Choi, H. & Moin, P. 2012 Grid-point requirements for large eddy simulation: Chapman’s estimates revisited. Phys. Fluids 24, 011702.CrossRefGoogle Scholar
Cuéllar, A., Güemes, A., Ianiro, A., Flores, Ó., Vinuesa, R. & Discetti, S. 2024 Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements. J. Fluid Mech. 991, A1.CrossRefGoogle Scholar
Dhariwal, P. & Nichol, A. 2021 Diffusion models beat gans on image synthesis. Adv. Neur. In 34, 8780–8794.Google Scholar
Du, P., Parikh, M.H., Fan, X., Liu, XY. & Wang, JX. 2024 Conditional neural field latent diffusion model for generating spatiotemporal turbulence. Nat. Commun. 15, 10416.CrossRefGoogle ScholarPubMed
Du, X., Qu, X., He, Y. & Guo, D. 2018 Single image super-resolution based on multi-scale competitive convolutional neural network. Sensors 18 (3), 789.CrossRefGoogle ScholarPubMed
Dunbar, D., van der A, D.A., Scandura, P. & O’Donoghue, T. 2023 An experimental and numerical study of turbulent oscillatory flow over an irregular rough wall. J. Fluid Mech. 955, A33.CrossRefGoogle Scholar
Fukami, K., Fukagata, K. & Taira, K. 2019 Super-resolution reconstruction of turbulent flows with machine learning. J. Fluid Mech. 870, 106–120.CrossRefGoogle Scholar
Fukami, K., Fukagata, K. & Taira, K. 2021
a Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows. J. Fluid Mech. 909, A9.CrossRefGoogle Scholar
Fukami, K., Fukagata, K. & Taira, K. 2023 Super-resolution analysis via machine learning: a survey for fluid flows. Theor. Comput. Fluid Dyn. 37, 421–444.CrossRefGoogle Scholar
Fukami, K., Goto, S. & Taira, K. 2024 Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables. J. Fluid Mech. 984, R4.CrossRefGoogle Scholar
Fukami, K., Maulik, R., Ramachandra, N., Fukagata, K. & Taira, K. 2021
b Global field reconstruction from sparse sensors with voronoi tessellation-assisted deep learning. Nat. Machine Intell. 3, 945–951.CrossRefGoogle Scholar
Fukami, K. & Taira, K. 2024 Single-snapshot machine learning for super-resolution of turbulence. J. Fluid Mech. 1001, A32.CrossRefGoogle Scholar
Gao, S., Liu, X., Zeng, B., Xu, S., Li, Y., Luo, X., Liu, J., Zhen, X. & Zhang, B. 2023 Implicit diffusion models for continuous super-resolution. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10021–10030. IEEE.CrossRefGoogle Scholar
Gao, Y. & Ng, M.K. 2022 Wasserstein generative adversarial uncertainty quantification in physics-informed neural networks. J. Comput. Phys. 463, 111270.CrossRefGoogle Scholar
Guan, Y., Chattopadhyay, A., Subel, A. & Hassanzadeh, P. 2022 Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning. J. Comput. Phys. 458, 111090.CrossRefGoogle Scholar
Güemes, A., Sanmiguel Vila, C. & Discetti, S. 2022 Super-resolution generative adversarial networks of randomly-seeded fields. Nat. Machine Intell. 4, 1165–1173.CrossRefGoogle Scholar
Han, X., Gao, H., Pfaff, T., Wang, J.X. & Liu, L. 2022, Predicting physics in mesh-reduced space with temporal attention. ArXiv abs/2201.09113.Google Scholar
Kim, H., Kim, J., Won, S. & Lee, C. 2021 Unsupervised deep learning for super-resolution reconstruction of turbulence. J. Fluid Mech. 910, A29.CrossRefGoogle Scholar
Kim, J., Kim, J. & Lee, C. 2024 Prediction and control of two-dimensional decaying turbulence using generative adversarial networks. J. Fluid Mech. 981, A19.CrossRefGoogle Scholar
Kingma, D.P. & Ba, J. 2014 Adam: a method for stochastic optimization. CoRR, abs/1412.6980. Available at: https://api.semanticscholar.org/CorpusID:6628106.Google Scholar
Kolmogorov, A.N. 1941 Dissipation of energy in locally isotropic turbulence. Dokl. Akad. Nauk SSSR 32, 16–18.Google Scholar
Lecun, Y., Bottou, L., Bengio, Y. & Haffner, P. 1998 Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324.CrossRefGoogle Scholar
Lee, J. & Zaki, T.A. 2018 Detection algorithm for turbulent interfaces and large-scale structures in intermittent flows. Comput. Fluids 175, 142–158.CrossRefGoogle Scholar
Lee, M., Malaya, N. & Moser, R.D. 2013 Petascale direct numerical simulation of turbulent channel flow on up to 786k cores. In SC ’13: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1–11. IEEE.Google Scholar
Li, Z., Han, W., Zhang, Y., Fu, Q., Li, J., Qin, L., Dong, R., Sun, H., Deng, Y. & Yang, L. 2024 Learning spatiotemporal dynamics with a pretrained generative model. Nat. Machine Intell. 6, 1566–1579.CrossRefGoogle Scholar
Lienen, M., Lüdke, D., Hansen-Palmus, J. & Günnemann, S. 2024 From zero to turbulence: generative modeling for 3D flow simulation. In International Conference on Learning Representations
Google Scholar
Lozano-Durán, A. & Bae, H.J. 2023 Machine learning building-block-flow wall model for large-eddy simulation. J. Fluid Mech. 963, A35.CrossRefGoogle Scholar
Maejima, S. & Kawai, S. 2025 Unsupervised and supervised machine learning pipeline for super-resolution-based subgrid scale modelling in coarse-grid large-eddy simulations. J. Fluid Mech. 1013, A28.CrossRefGoogle Scholar
Manohar, K., Brunton, B.W., Kutz, J.N. & Brunton, S.L. 2018 Data-driven sparse sensor placement for reconstruction: demonstrating the benefits of exploiting known patterns. IEEE Control Syst. Mag. 38 (3), 63–86.Google Scholar
Mirza, M. & Osindero, S. 2014 Conditional generative adversarial nets. arXiv: 1411.1784.Google Scholar
Page, J. 2025 Super-resolution of turbulence with dynamics in the loss. J. Fluid Mech. 1002, R3.CrossRefGoogle Scholar
Patel, S., Sihmar, S. & Jatain, A. 2015 A study of hierarchical clustering algorithms. In 2015 2nd International Conference on Computing for Sustainable Global Development (INDIACom), pp. 537–541. IEEE.Google Scholar
Rumelhart, D., Hinton, G. & Williams, R. 1986 Learning representations by back-propagating errors. Nature 323, 533–536.CrossRefGoogle Scholar
Saddoughi, S.G. & Veeravalli, S.V. 1994 Local isotropy in turbulent boundary layers at high Reynolds number. J. Fluid Mech. 268, 333–372.CrossRefGoogle Scholar
Santos, J.E., Fox, Z.R., Mohan, A., O’Malley, D., Viswanathan, H. & Lubbers, N. 2023 Development of the Senseiver for efficient field reconstruction from sparse observations. Nat. Machine Intell. 5, 1317–1325.CrossRefGoogle Scholar
Scarano, F. 2013 Tomographic PIV: principles and practice. Meas. Sci. Technol. 24 (1), 012001.CrossRefGoogle Scholar
Schumacher, J., Scheel, J.D., Krasnov, D., Donzis, D.A., Yakhot, V. & Sreenivasan, K.R. 2014 Small-scale universality in fluid turbulence. Proc. Natl Acad. Sci. USA 111 (30), 10961–10965.CrossRefGoogle ScholarPubMed
Shen, X. & Warhaft, Z. 2000 The anisotropy of the small scale structure in high Reynolds number (
${R}_\lambda \sim 1000$
) turbulent shear flow. Phys. Fluids 12 (11), 2976–2989.CrossRefGoogle Scholar
${R}_\lambda \sim 1000$
) turbulent shear flow. Phys. Fluids 12 (11), 2976–2989.CrossRefGoogle ScholarShu, D., Li, Z. & Barati Farimani, A. 2023 A physics-informed diffusion model for high-fidelity flow field reconstruction. J. Comput. Phys. 478, 111972.CrossRefGoogle Scholar
Stengel, K., Glaws, A., Hettinger, D., King, R.N. 2020 Adversarial super-resolution of climatological wind and solar data. Proc. Natl Acad. Sci. USA 117 (29), 16805–16815.CrossRefGoogle ScholarPubMed
Sun, L., Han, X., Gao, H., Wang, J.X. & Liu, L. 2023 Unifying predictions of deterministic and stochastic physics in mesh-reduced space with sequential flow generative model. In Thirty-seventh Conference on Neural Information Processing Systems. Curran Associates, Inc.Google Scholar
Vinuesa, R. & Brunton, S.L. 2022 Enhancing computational fluid dynamics with machine learning. Nat. Comput. Sci. 2 (6), 358–366.CrossRefGoogle ScholarPubMed
Wang, H., Wu, W., Su, Y., Duan, Y. & Wang, P. 2019 Image super-resolution using a improved generative adversarial network. In 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE.Google Scholar
Wu, H., Chen, Y., Xie, P., Zhou, D., Tamura, T., Zhang, K., Cao, S. & Cao, Y. 2023 Sparse-measurement-based peak wind pressure evaluation by super-resolution convolutional neural networks. J. Wind Engng Ind. Aerodyn. 242, 105574.CrossRefGoogle Scholar
Wu, H., Zhang, K., Zhou, D., Chen, W.-L., Han, Z. & Cao, Y. 2024 High-flexibility reconstruction of small-scale motions in wall turbulence using a generalized zero-shot learning. J. Fluid Mech. 990, R1.CrossRefGoogle Scholar
Xian, Y., Lampert, C.H., Schiele, B. & Akata, Z. 2019 Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41 (9), 2251–2265.CrossRefGoogle ScholarPubMed
Yao, J., Chen, X. & Hussain, F. 2022 Direct numerical simulation of turbulent open channel flows at moderately high Reynolds numbers. J. Fluid Mech. 953, A19.CrossRefGoogle Scholar
Yasuda, Y. & Onishi, R. 2023 Spatio-temporal super-resolution data assimilation (SRDA) utilizing deep neural networks with domain generalization. J. Adv. Model. Earth Syst. 15 (11), e2023MS003658.CrossRefGoogle Scholar
Yeo, K., Zimoń, M.J., Zayats, M. & Zhuk, S. 2024 Reducing data resolution for better superresolution: reconstructing turbulent flows from noisy observation. Phys. Rev. Lett. 133, 264001.CrossRefGoogle ScholarPubMed
Yeung, P.K., Sreenivasan, K.R. & Pope, S.B. 2018 Effects of finite spatial and temporal resolution in direct numerical simulations of incompressible isotropic turbulence. Phys. Rev. Fluids 3, 064603.CrossRefGoogle Scholar
Yeung, P.K., Zhai, X.M. & Sreenivasan, K.R. 2015 Extreme events in computational turbulence. Proc. Natl Acad. Sci. USA 112 (41), 12633–12638.CrossRefGoogle ScholarPubMed
Zhao, Y., Karypis, G. & Fayyad, U. 2005 Hierarchical clustering algorithms for document datasets. Data Mining Knowledge Disc. 10, 141–168.CrossRefGoogle Scholar