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

Physical Review Fluids

Export citation

Export citation

Choose format for download:

Download Citation
  • Editors' Suggestion
  • Access by Xinjiang University

High-fidelity reconstruction of large-area damaged turbulent fields with a physically constrained generative adversarial network

Qinmin Zheng1,2, Tianyi Li3, Benteng Ma1, Lin Fu2,4,5,*, and Xiaomeng Li1,†

  • 1Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
  • 2Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
  • 3Department of Physics and INFN, University of Rome “Tor Vergata”, Via della Ricerca Scientifica 1, Rome 00133, Italy
  • 4Department of Mathematics and Center for Ocean Research in Hong Kong and Macau (CORE), The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong
  • 5HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute, Futian, Shenzhen, People's Republic of China

  • *linfu@ust.hk
  • †eexmli@ust.hk
PDF

Phys. Rev. Fluids 9, 024608 – Published 29 February, 2024

DOI: https://doi.org/10.1103/PhysRevFluids.9.024608

Abstract

The reconstruction of incomplete information in flow fields is a pervasive challenge in numerous turbulence-related applications. This paper proposes a framework for the high-fidelity reconstruction of large-area damaged turbulent fields with high resolution based on a physically constrained generative adversarial network. The network incorporates some special designs, such as leveraging complete or sparse fields of velocity components as physical constraints, employing a ResNet-like network with a fast Fourier convolution module, and adopting a PatchGAN discriminator network. To train the network, we employ a combination of loss functions, which comprise mean absolute error, network-level loss, and feature matching loss. We validate our method on a dataset of compressible isotropic turbulent flow and investigate three distinct damaged distributions with gap ratios of 39.06% and 56.25%. The proposed reconstruction framework has been shown to achieve excellent reconstruction performance. The reconstructed flow fields are consistent with the raw flow fields in terms of magnitude, power spectrum, and two-point correlation function. We also provide extensive ablation studies to validate our approach. The results indicate that the utilization of physical constraints significantly improves the reconstruction performance in damaged regions, particularly in cases that involve a large damaged area. Furthermore, in the proposed reconstruction framework, the size of patch in the PatchGAN discriminator network can be flexibly adjusted according to the scale of turbulence structures, and the perceptual loss function plays a crucial role in evaluating differences between feature maps of flow fields at network levels based on a pretrained network. These special designs ensure consistency across diverse scales of turbulence structures and improve the accuracy and efficiency of network training.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (68)

  1. A. Güemes, C. Sanmiguel Vila, and S. Discetti, Super-resolution generative adversarial networks of randomly-seeded fields, Nat. Mach. Intell. 4, 1165 (2022).
  2. L. Fu, S. Bose, and P. Moin, Prediction of aerothermal characteristics of a generic hypersonic inlet flow, Theor. Comput. Fluid Dyn. 36, 345 (2022).
  3. K. Fukami, R. Maulik, N. Ramachandra, K. Fukagata, and K. Taira, Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning, Nat. Mach. Intell. 3, 945 (2021).
  4. S. L. Brunton, B. R. Noack, and P. Koumoutsakos, Machine learning for fluid mechanics, Annu. Rev. Fluid Mech. 52, 477 (2020).
  5. X. Wen, Z. Li, D. Peng, W. Zhou, and Y. Liu, Missing data recovery using data fusion of incomplete complementary data sets: A particle image velocimetry application, Phys. Fluids 31, 025105 (2019).
  6. C. Wang, Q. Gao, H. Wang, R. Wei, T. Li, and J. Wang, Divergence-free smoothing for volumetric PIV data, Exp. Fluids 57, 1 (2016).
  7. C. Irrgang, N. Boers, M. Sonnewald, E. A. Barnes, C. Kadow, J. Staneva, and J. Saynisch-Wagner, Towards neural earth system modelling by integrating artificial intelligence in earth system science, Nat. Mach. Intell. 3, 667 (2021).
  8. S. Yu and J. Ma, Deep learning for geophysics: Current and future trends, Rev. Geophys. 59, e2021RG000742 (2021).
  9. C. Kadow, D. M. Hall, and U. Ulbrich, Artificial intelligence reconstructs missing climate information, Nature Geosci. 13, 408 (2020).
  10. P. Holmes, J. L. Lumley, G. Berkooz, and C. W. Rowley, Turbulence, Coherent Structures, Dynamical Systems and Symmetry, Cambridge Monographs on Mechanics (Cambridge University Press, Cambridge, UK, 2012).
  11. G. Berkooz, P. Holmes, and J. L. Lumley, The proper orthogonal decomposition in the analysis of turbulent flows, Annu. Rev. Fluid Mech. 25, 539 (1993).
  12. P. J. Schmid, Dynamic mode decomposition and its variants, Annu. Rev. Fluid Mech. 54, 225 (2022).
  13. P. J. Schmid, Dynamic mode decomposition of numerical and experimental data, J. Fluid Mech. 656, 5 (2010).
  14. S. G. Raben, J. J. Charonko, and P. P. Vlachos, Adaptive gappy proper orthogonal decomposition for particle image velocimetry data reconstruction, Meas. Sci. Technol. 23, 025303 (2012).
  15. N. Murray and J. Seiner, The effects of gappy POD on higher-order turbulence quantities, in Proceedings of the 46th AIAA Aerospace Sciences Meeting and Exhibit (AIAA, Reston, VA, 2008), p. 241.
  16. H. Gunes, S. Sirisup, and G. E. Karniadakis, Gappy data: To Krig or not to Krig? J. Comput. Phys. 212, 358 (2006).
  17. D. Venturi and G. E. Karniadakis, Gappy data and reconstruction procedures for flow past a cylinder, J. Fluid Mech. 519, 315 (1999).
  18. T. Li, M. Buzzicotti, L. Biferale, F. Bonaccorso, S. Chen, and M. Wan, Multi-scale reconstruction of turbulent rotating flows with proper orthogonal decomposition and generative adversarial networks, J. Fluid Mech. 971, A3 (2023).
  19. M. Buzzicotti, F. Bonaccorso, P. C. Di Leoni, and L. Biferale, Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database, Phys. Rev. Fluids 6, 050503 (2021).
  20. E. Jagodinski, X. Zhu, and S. Verma, Inverse identification of dynamically important regions in turbulent flows using three-dimensional convolutional neural networks, Phys. Rev. Fluids 8, 094605 (2023).
  21. J. Kim and C. Lee, Prediction of turbulent heat transfer using convolutional neural networks, J. Fluid Mech. 882, A18 (2020).
  22. S. Bhatnagar, Y. Afshar, S. Pan, K. Duraisamy, and S. Kaushik, Prediction of aerodynamic flow fields using convolutional neural networks, Comput. Mech. 64, 525 (2019).
  23. K. Stengel, A. Glaws, D. Hettinger, and R. N. King, Adversarial super-resolution of climatological wind and solar data, Proc. Natl. Acad. Sci. USA 117, 16805 (2020).
  24. T. Bolton and L. Zanna, Applications of deep learning to ocean data inference and subgrid parameterization, J. Adv. Model. Earth Syst. 11, 376 (2019).
  25. A. Asensio Ramos and C. J. Díaz Baso, Stokes inversion based on convolutional neural networks, Astron. Astrophys. 626, A102 (2019).
  26. C. Schaefer, M. Geiger, T. Kuntzer, and J.-P. Kneib, Deep convolutional neural networks as strong gravitational lens detectors, Astron. Astrophys. 611, A2 (2018).
  27. A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Commun. ACM 60, 84 (2017).
  28. Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature (London) 521, 436 (2015).
  29. C. Drygala, B. Winhart, F. di Mare, and H. Gottschalk, Generative modeling of turbulence, Phys. Fluids 34, 035114 (2022).
  30. M. Z. Yousif, L. Yu, and H.-C. Lim, High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network, Phys. Fluids 33, 125119 (2021).
  31. 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).
  32. L. Sun and J.-X. Wang, Physics-constrained Bayesian neural network for fluid flow reconstruction with sparse and noisy data, Theor. Appl. Mech. Lett. 10, 161 (2020).
  33. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, Generative adversarial networks, Commun. ACM 63, 139 (2020).
  34. M. Z. Yousif, L. Yu, S. Hoyas, R. Vinuesa, and H. Lim, A deep-learning approach for reconstructing 3D turbulent flows from 2D observation data, Sci. Rep. 13, 2529 (2023).
  35. A. Subramaniam, M. L. Wong, R. D. Borker, S. Nimmagadda, and S. K. Lele, Turbulence enrichment using physics-informed generative adversarial networks, arXiv:2003.01907.
  36. H. Kim, J. Kim, S. Won, and C. Lee, Unsupervised deep learning for super-resolution reconstruction of turbulence, J. Fluid Mech. 910, A29 (2021).
  37. Q. Zheng and M. M. Alam, Evolution of the wake of three inline square prisms, Phys. Rev. Fluids 4, 104701 (2019).
  38. H. Choi, W.-P. Jeon, and J. Kim, Control of flow over a bluff body, Annu. Rev. Fluid Mech. 40, 113 (2008).
  39. C. H. Williamson, Vortex dynamics in the cylinder wake, Annu. Rev. Fluid Mech. 28, 477 (1996).
  40. C. Cheng, W. Shyy, and L. Fu, Streamwise inclination angle of wall-attached eddies in turbulent channel flows, J. Fluid Mech. 946, A49 (2022).
  41. C. Cheng and L. Fu, Consistency between the attached-eddy model and the inner–outer interaction model: A study of streamwise wall-shear stress fluctuations in a turbulent channel flow, J. Fluid Mech. 942, R9 (2022).
  42. K. Fukami, K. Fukagata, and K. Taira, Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows, J. Fluid Mech. 909, A9 (2021).
  43. D. Buaria, M. P. Clay, K. R. Sreenivasan, and P. K. Yeung, Small-scale isotropy and ramp-cliff structures in scalar turbulence, Phys. Rev. Lett. 126, 034504 (2021).
  44. S. B. Pope, Turbulent Flows (Cambridge University Press, Cambridge, UK, 2000).
  45. M. Z. G. Yousif, L. Yu, and H. Lim, Physics-guided deep learning for generating turbulent inflow conditions, J. Fluid Mech. 936, A21 (2022).
  46. 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).
  47. P. Sharma, W. T. Chung, B. Akoush, and M. Ihme, A review of physics-informed machine learning in fluid mechanics, Energies 16, 2343 (2023).
  48. Q. Zheng, Y. Yang, J. Wang, and S. Chen, Enstrophy production and flow topology in compressible isotropic turbulence with vibrational nonequilibrium, J. Fluid Mech. 950, A21 (2022).
  49. Q. Zheng, J. Wang, M. M. Alam, B. R. Noack, H. Li, and S. Chen, Transfer of internal energy fluctuation in compressible isotropic turbulence with vibrational nonequilibrium, J. Fluid Mech. 919, A26 (2021).
  50. Q. Zheng, J. Wang, B. R. Noack, H. Li, M. Wan, and S. Chen, Vibrational relaxation in compressible isotropic turbulence with thermal nonequilibrium, Phys. Rev. Fluids 5, 044602 (2020).
  51. L. Chi, B. Jiang, and Y. Mu, Fast fourier convolution, Adv. Neural Inf. Process. Syst. 33, 4479 (2020).
  52. K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ, 2016), pp. 770–778.
  53. D. Zhang, F. Huang, S. Liu, X. Wang, and Z. Jin, Swinfir: Revisiting the swinir with fast fourier convolution and improved training for image super-resolution, arXiv:2208.11247.
  54. R. Suvorov, E. Logacheva, A. Mashikhin, A. Remizova, A. Ashukha, A. Silvestrov, N. Kong, H. Goka, K. Park, and V. Lempitsky, Resolution-robust large mask inpainting with fourier convolutions, in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (IEEE, Piscataway, NJ, 2022), pp. 2149–2159.
  55. U. Demir and G. Unal, Patch-based image inpainting with generative adversarial networks, arXiv:1803.07422.
  56. P. Isola, J.-Y. Zhu, T. Zhou, and A. A. Efros, Image-to-image translation with conditional adversarial networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ, 2017), pp. 1125–1134.
  57. J. Johnson, A. Alahi, and L. Fei-Fei, Perceptual losses for real-time style transfer and super-resolution, in Proceedings of the 14th European Conference on Computer Vision (ECCV), Part II 14 (Springer, Berlin, 2016), pp. 694–711.
  58. B. Zhou, H. Zhao, X. Puig, T. Xiao, S. Fidler, A. Barriuso, and A. Torralba, Semantic understanding of scenes through the ade20k dataset, Int. J. Comput. Vision 127, 302 (2019).
  59. B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, and A. Torralba, Scene parsing through ade20k dataset, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ, 2017), pp. 633–641.
  60. A. Ross and F. Doshi-Velez, Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients, in Proceedings of the AAAI Conference on Artificial Intelligence (AIAA, Reston, VA, 2018), Vol. 32.
  61. T.-C. Wang, M.-Y. Liu, J.-Y. Zhu, A. Tao, J. Kautz, and B. Catanzaro, High-resolution image synthesis and semantic manipulation with conditional gans, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (IEEE, Piscataway, NJ, 2018), pp. 8798–8807.
  62. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., Pytorch: An imperative style, high-performance deep learning library, Adv. Neural Inf. Process. Syst. 32 (2019).
  63. D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv:1412.6980.
  64. V. Kushwaha, G. Nandi et al., Study of prevention of mode collapse in generative adversarial network (GAN), in Proceedings of the IEEE 4th Conference on Information and Communication Technology (CICT) (IEEE, Piscataway, NJ, 2020), pp. 1–6.
  65. M. Bode, M. Gauding, Z. Lian, D. Denker, M. Davidovic, K. Kleinheinz, J. Jitsev, and H. Pitsch, Using physics-informed enhanced super-resolution generative adversarial networks for subfilter modeling in turbulent reactive flows, Proc. Combust. Inst. 38, 2617 (2021).
  66. K. Fukami, K. Fukagata, and K. Taira, Super-resolution reconstruction of turbulent flows with machine learning, J. Fluid Mech. 870, 106 (2019).
  67. Z. Deng, C. He, Y. Liu, and K. C. Kim, Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework, Phys. Fluids 31, 125111 (2019).
  68. L. Fu, M. Karp, S. T. Bose, P. Moin, and J. Urzay, Shock-induced heating and transition to turbulence in a hypersonic boundary layer, J. Fluid Mech. 909, A8 (2021).

Outline

Information

Phys. Rev. Fluids 9, 024608– Published 29 February, 2024
  • Received 9 October 2023
  • Accepted 17 January 2024
Crossmark - Check for updates button

©2024 American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation