While computational fluid dynamics (CFD) can solve a wide variety of fluid flow problems, accurate CFD simulations require significant computational resources and time. We propose a general method for super-resolution of low-fidelity flow simulations using deep learning. The approach is based on a conditional generative adversarial network (GAN) with inexpensive, low-fidelity solutions as inputs and high-fidelity simulations as outputs. The details, including the flexible structure, unique loss functions, and handling strategies, are thoroughly discussed, and the methodology is demonstrated using numerical simulations of incompressible flows. The distinction between low- and high-fidelity solutions is made in terms of discretization and physical modeling errors. Numerical experiments demonstrate that the approach is capable of accurately forecasting high-fidelity simulations.
GoodfellowIPouget-AbadieJMirzaM, et al. Generative adversarial nets. In: Proceedings of the 27th international conference on neural information processing systems, Montreal, QC, Canada, 8–13 December 2014. Cambridge, MA: The MIT Press.
2.
ChenWChiuKFugeM.Aerodynamic design optimization and shape exploration using generative adversarial networks. In: Proceedings of the AIAA Scitech 2019 forum, San Diego, CA, 7–11 January 2019. Reston, VA: AIAA.
3.
LiuYWangYDengL, et al. A novel in situ compression method for CFD data based on generative adversarial network. J Visual2019; 22: 95–108.
4.
KimBAzevedoVCThuereyN, et al. Deep fluids: a generative network for parameterized fluid simulations. Comput Graph Forum2019; 38: 59–70.
5.
XieYFranzEChuM, et al. TempoGAN: a temporally coherent, volumetric GAN for super-resolution fluid flow. ACM T Graphic2018; 37: 1–15.
6.
DengZHeCLiuY, et al. Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework. Phys Fluids2019; 31: 125111.
7.
FerdianESuinesiaputraADubowitzDJ, et al. 4DFlowNet: super-resolution 4D flow MRI using deep learning and computational fluid dynamics. Front Phys2020; 8: 138.
SubramaniamAWongMLBorkerRD, et al. Turbulence enrichment using physics-informed generative adversarial networks, 2020, https://arxiv.org/abs/2003.01907
10.
ChenDGaoXXuC, et al. FlowGAN: a conditional generative adversarial network for flow prediction in various conditions. In: Proceedings of the IEEE 32nd international conference on tools with artificial intelligence (ICTAI), Baltimore, MD, 9–11 November 2020, pp. 315–322. New York: IEEE.
11.
WenSShenNZhangJ, et al. Single-rotor UAV flow field simulation using generative adversarial networks. Comput Electron Agr2019; 167: 105004.
12.
AfzaliJCasasCQArcucciR. Latent GAN: using a latent space-based GAN for rapid forecasting of CFD models. In: Proceedings of the 21st international conference on computational science, Krakow, 16–18 June 2021, pp. 360–372. Berlin; Heidelberg: Springer.
13.
WuHLiuXAnW, et al. A deep learning approach for efficiently and accurately evaluating the flow field of supercritical airfoils. Comput Fluids2020; 198: 104393.
14.
SiddaniBBalachandarSMooreWC, et al. Machine learning for physics-informed generation of dispersed multiphase flow using generative adversarial networks. Theor Comp Fluid Dyn. Epub ahead of print 28October2021. DOI: 10.1007/s00162-021-00593-9.
15.
Quilodrán-CasasCArcucciRMottetL, et al. Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations, 2021, https://arxiv.org/abs/2104.06297
16.
PenaBHuangL.Wave-GAN: a deep learning approach for the prediction of nonlinear regular wave loads and run-up on a fixed cylinder. Coast Eng2021; 167: 103902.
17.
BrownleeJ.Generative adversarial networks with python: deep learning generative models for image synthesis and image translation. San Juan, PR: Machine Learning Mastery, 2019.
18.
IsolaPZhuJ-YZhouT, et al. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, 21–26 July 2017, pp.1125–1134. New York: IEEE.
19.
FukushimaK.Analysis of the process of visual pattern recognition by the neocognitron. Neural Networks1989; 2: 413–420.
20.
SrivastavaNHintonGKrizhevskyA, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res2014; 15: 1929–1958.
21.
RonnebergerOFischerPBroxT. U-Net: convolutional networks for biomedical image segmentation. In: Proceedings of the international conference on medical image computing and computer-assisted intervention, Munich, 5–9 October 2015, pp. 234–241. Cham: Springer.
22.
IoffeSSzegedyC. Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, Lille, 6–11 July 2015, pp. 448–456. Proceedings of Machine Learning Research (PMLR).
23.
FrancaLPFreySL.Stabilized finite element methods: II. The incompressible Navier-Stokes equations. Comput Method Appl M1992; 99: 209–233.
WangZBovikAC.Mean squared error: love it or leave it? A new look at signal fidelity measures. IEEE Signal Proc Mag2009; 26: 98–117.
26.
BakerTJ.Mesh adaptation strategies for problems in fluid dynamics. Finite Elem Anal Des1997; 25: 243–273.
27.
WangZBovikACSheikhHR, et al. Image quality assessment: from error visibility to structural similarity. IEEE T Image Process2004; 13: 600–612.
28.
GhiaUGhiaKNShinC.High-Re solutions for incompressible flow using the Navier-Stokes equations and a multigrid method. J Comput Phys1982; 48: 387–411.
29.
KuhlmannHCRomanòF.The lid-driven cavity. In: GelfgatA (ed.) Computational modelling of bifurcations and instabilities in fluid dynamics. Cham: Springer, 2019, pp. 233–309.
30.
CodinaRBadiaSBaigesJ, et al. Variational multiscale methods in computational fluid dynamics. In: SteinEDe BorstRHughesTJR (eds) Encyclopedia of computational mechanics. Hoboken, NJ: John Wiley & Sons, 2018, pp. 1–28.
31.
InnamoratiCRitschelTWeyrichT, et al. Learning on the edge: investigating boundary filters in CNNs. Int J Comput Vision2020; 128: 773–782.
32.
SchubertSNeubertPPöschmannJ, et al. Circular convolutional neural networks for panoramic images and laser data. In: Proceedings of the 2019 IEEE intelligent vehicles symposium (IV), Paris, 9–12 June 2019, pp. 653–660. New York: IEEE.
