Generative modeling of turbulence

被引:25
|
作者
Drygala, C. [1 ,2 ]
Winhart, B. [3 ]
di Mare, F. [3 ]
Gottschalk, H. [1 ,2 ]
机构
[1] Univ Wuppertal, Sch Math & Nat Sci, IMACM, Wuppertal, Germany
[2] Univ Wuppertal, Sch Math & Nat Sci, IZMD, Wuppertal, Germany
[3] Ruhr Univ Bochum, Dept Mech Engn, Chair Thermal Turbomachines & Aero Engines, Bochum, Germany
关键词
CIRCULAR-CYLINDER; MACHINE; FLOWS; PROOF; FIELD;
D O I
10.1063/5.0082562
中图分类号
O3 [力学];
学科分类号
08 ; 0801 ;
摘要
We present a mathematically well-founded approach for the synthetic modeling of turbulent flows using generative adversarial networks (GAN). Based on the analysis of chaotic, deterministic systems in terms of ergodicity, we outline a mathematical proof that GAN can actually learn to sample state snapshots from the invariant measure of the chaotic system. Based on this analysis, we study a hierarchy of chaotic systems starting with the Lorenz attractor and then carry on to the modeling of turbulent flows with GAN. As training data, we use fields of velocity fluctuations obtained from large-eddy simulations (LES). Two architectures are investigated in detail: we use a deep, convolutional GAN (DCGAN) to synthesize the turbulent flow around a cylinder. We furthermore simulate the flow around a low-pressure turbine stator using the pix2pixHD architecture for a conditional DCGAN being conditioned on the position of a rotating wake in front of the stator. The settings of adversarial training and the effects of using specific GAN architectures are explained. We thereby show that GAN are efficient in simulating turbulence in technically challenging flow problems on the basis of a moderate amount of training data. GAN training and inference times significantly fall short when compared with classical numerical methods, in particular, LES, while still providing turbulent flows in high resolution. We furthermore analyze the statistical properties of the synthesized and LES flow fields, which agree excellently. We also show the ability of the conditional GAN to generalize over changes of geometry by generating turbulent flow fields for positions of the wake that are not included in the training data.
引用
收藏
页数:19
相关论文
共 50 条
  • [21] Symmetries and turbulence modeling
    Klingenberg, D.
    Oberlack, M.
    Pluemacher, D.
    PHYSICS OF FLUIDS, 2020, 32 (02)
  • [22] Score mismatching for generative modeling
    Ye, Senmao
    Liu, Fei
    NEURAL NETWORKS, 2024, 175
  • [23] Domain independent generative modeling
    Kusy, B
    Lédeczi, A
    Maróti, M
    Völgyesi, P
    11TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOP ON THE ENGINEERING OF COMPUTER-BASED SYSTEMS, PROCEEDINGS, 2004, : 29 - 34
  • [24] Generative Modeling with Failure in PRISM
    Sato, Taisuke
    Kameya, Yoshitaka
    Zhou, Neng-Fa
    19TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-05), 2005, : 847 - 852
  • [25] Generative Modeling of Atmospheric Convection
    Mooers, Griffin
    Tuyls, Jens
    Mandt, Stephan
    Pritchard, Mike
    Beucler, Tom
    PROCEEDINGS OF 2020 10TH INTERNATIONAL CONFERENCE ON CLIMATE INFORMATICS (CI2020), 2020, : 98 - 105
  • [26] Generative modeling for renal microanatomy
    Murali, Leema Krishna
    Lutnick, Brendon
    Ginley, Brandon
    Tomaszewski, John E.
    Sarder, Pinaki
    MEDICAL IMAGING 2020: DIGITAL PATHOLOGY, 2021, 11320
  • [27] Generative Modeling for Protein Structures
    Anand, Namrata
    Huang, Po-Ssu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [28] Distribution Augmentation for Generative Modeling
    Jun, Heewoo
    Child, Rewon
    Chen, Mark
    Schulman, John
    Ramesh, Aditya
    Radford, Alec
    Sutskever, Ilya
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 119, 2020, 119
  • [29] An introduction to deep generative modeling
    Ruthotto L.
    Haber E.
    GAMM Mitteilungen, 2021, 44 (02)
  • [30] CHALLENGES IN GENERATIVE MODELING AND FUNCTIONING NATURE OF GENERATIVE ADVERSARIAL NETWORKS
    Sripada, Naresh Kumar
    Ismail, Mohammed B.
    JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES, 2019, 14 (06): : 83 - 91