APS Logo

Physics Guided Neural Networks for Spatio-temporal Super-resolution of Turbulent Flows

ORAL

Abstract

Direct numerical simulation (DNS) of turbulent flows is computationally expensive and is not practical for simulating flows at high Reynolds numbers. Low-resolution large eddy simulation (LES) is a pragmatic alternative, but its success depends on modeling of the small scale flow dynamics. Reconstructing DNS from low-resolution LES is critical for many scientific and engineering disciplines, but it poses many challenges to existing super-resolution methods due to the complexity of turbulent flows and computational cost of generating frequent LES data. In this work, we propose a physics-guided neural network for reconstructing frequent DNS from sparse LES data by enhancing its spatial resolution and temporal frequency. Our proposed method consists of a partial differential equation (PDE)-based recurrent unit for capturing underlying temporal processes and a physics-guided super-resolution model that incorporates additional physical constraints. We demonstrate the effectiveness of both components in reconstructing the data generated by simulating the Taylor-Green Vortex sparse LES data. Moreover, we show that the proposed recurrent unit can preserve the physical characteristics of turbulent flows by leveraging the physical relationships in the Navier-Stokes equation.

–

Publication: Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn. Fast, accurate, and lightweight super-resolution with cascading residual network. In Proceedings of the European conference on computer vision (ECCV), pages 252–268, 2018.<br><br>Saad Albawi, Tareq Abed Mohammed, and Saad Al-Zawi. Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET), pages 1–6. Ieee, 2017.<br><br>Tianshu Bao, Xiaowei Jia, Jacob Zwart, Jeffrey Sadler, Alison Appling, Samantha Oliver, and Taylor T Johnson. Partial differential equation driven dynamic graph networks for predicting stream water temperature. In 2021 IEEE International Conference on Data Mining (ICDM), pages 11–20. IEEE, 2021.<br><br>Marc E Brachet, D Meiron, S Orszag, B Nickel, R Morf, and Uriel Frisch. The taylor-green vortex and fully developed<br>turbulence. Journal of Statistical Physics, 34(5):1049–1063, 1984.<br><br>John Butcher. Runge-kutta methods. Scholarpedia, 2(9): 3147, 2007.<br><br>Shengyu Chen, Shervin Sammak, Peyman Givi, Joseph P Yurko, and Xiaowei Jia. Reconstructing high-resolution turbulent flows using physics-guided neural networks. In 2021 IEEE International Conference on Big Data (Big Data), pages 1369–1379. IEEE, 2021.<br><br>Yu Chen, Ying Tai, Xiaoming Liu, Chunhua Shen, and Jian Yang. Fsrnet: End-to-end learning face super-resolution with facial priors. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2492–2501, 2018.<br><br>Wenlong Cheng, Mingbo Zhao, Zhiling Ye, and Shuhang Gu. Mfagan: A compression framework for memory efficient on-device super-resolution gan. arXiv preprint arXiv:2107.12679, 2021.<br><br>Tao Dai, Jianrui Cai, Yongbing Zhang, Shu-Tao Xia, and Lei Zhang. Second-order attention network for single image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11065–11074, 2019.<br><br>Zhiwen Deng, Chuangxin He, Yingzheng Liu, and Kyung Chun Kim. Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework. Physics of Fluids, 31(12):125111, 2019.<br><br>Chao Dong, Chen Change Loy, Kaiming He, and Xiaoou Tang. Learning a deep convolutional network for image super-resolution. In European conference on computer vision, pages 184–199. Springer, 2014.<br><br>Kai Fukami, Koji Fukagata, and Kunihiko Taira. Super resolution reconstruction of turbulent flows with machine learning. Journal of Fluid Mechanics, 870:106–120, 2019.<br><br>Kai Fukami, Koji Fukagata, and Kunihiko Taira. Machine learning- based spatio-temporal super resolution reconstruction of turbulent flows. Journal of Fluid Mechanics, 909, Dec 2020. ISSN 1469-7645. doi: 10.1017/jfm.2020. 948. URL http://dx.doi.org/10.1017/jfm.2020.948.<br><br>P. Givi. Spectral and random vortex methods in turbulent reacting flows. In P. A. Libby and F. A. Williams, editors, Turbulent Reacting Flows, chapter 8, pages 475–572. Academic Press, London, England, 1994.<br><br>Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735–1780, 1997. doi: 10.1162/neco.1997.9.8.1735.<br><br>Xiaowei Jia, Jared Willard, Anuj Karpatne, Jordan Read, Jacob Zwart, Michael Steinbach, and Vipin Kumar. Physics guided rnns for modeling dynamical systems: A case study in simulating lake temperature profiles. In Proceedings of the 2019 SIAM International Conference on Data Mining, pages 558–566. SIAM, 2019.<br><br>Xiaowei Jia, Jacob Zwart, Jeffrey Sadler, Alison Appling, Samantha Oliver, Steven Markstrom, Jared Willard, Shaoming Xu, Michael Steinbach, Jordan Read, et al. Physics-guided recurrent graph model for predicting flow and temperature in river networks. In Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), pages 612–620. SIAM, 2021.<br><br>Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196, 2017.<br><br>Christian Ledig, Lucas Theis, Ferenc Huszár, Jose Caballero, Andrew Cunningham, Alejandro Acosta, Andrew Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, et al. Photorealistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4681–4690, 2017.<br><br>Bo Liu, Jiupeng Tang, Haibo Huang, and Xi-Yun Lu. Deep learning methods for super-resolution reconstruction of turbulent flows. Physics of Fluids, 32(2):025105, 2020. A. G. Nouri, M. B. Nik, P. Givi, D. Livescu, and S. B. Pope. Self-Contained Filtered Density Function. Physical Review Fluids, 2:094603, Sep 2017. doi: 10.1103/ PhysRevFluids.2.094603. URL https://link.aps.org/doi/ 10.1103/PhysRevFluids.2.094603.<br><br>Octavi Obiols-Sales, Abhinav Vishnu, Nicholas P Malaya, and Aparna Chandramowlishwaran. Surfnet: Super resolution of turbulent flows with transfer learning using small datasets. In 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT), pages 331–344. IEEE, 2021.<br><br>Sung Cheol Park, Min Kyu Park, and Moon Gi Kang. Super resolution image reconstruction: a technical overview. IEEE signal processing magazine, 20(3):21–36, 2003. Karen Stengel, Andrew Glaws, Dylan Hettinger, and Ryan N King. Adversarial super-resolution of climatological wind and solar data. Proceedings of the National Academy of Sciences, 117(29):16805–16815, 2020.<br><br>Ying Tai, Jian Yang, and Xiaoming Liu. Image super resolution via deep recursive residual network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3147–3155, 2017.<br><br>Uddeshya Upadhyay and Suyash P Awate. Robust super resolution gan, with manifold-based and perception loss. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pages 1372–1376. IEEE, 2019.<br><br>Vinh Van Duong, Thuc Nguyen Huu, Jonghoon Yim, and Byeungwoo Jeon. A fast and efficient super-resolution network using hierarchical dense residual learning. In 2021 IEEE International Conference on Image Processing (ICIP), pages 1809–1813. IEEE, 2021.<br><br>TS Sachin Venkatesh, Rajat Srivastava, Pratyush Bhatt, Prince Tyagi, and Raj Kumar Singh. A comparative study of various deep learning techniques for spatio-temporal super-resolution reconstruction of forced isotropic turbulent flows. In ASME International Mechanical Engineering Congress and Exposition, volume 85666, page V010T10A061. American Society of Mechanical Engineers,<br>2021.<br><br>Xintao Wang, Ke Yu, Chao Dong, and Chen Change Loy. Recovering realistic texture in image super-resolution by deep spatial feature transform. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 606–615, 2018a.<br><br>Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Yu Qiao, and Chen Change Loy. Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops, pages 0–0, 2018b.<br><br>Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.<br><br>Jared Willard, Xiaowei Jia, Shaoming Xu, Michael Steinbach, and Vipin Kumar. Integrating scientific knowledge with machine learning for engineering and environmental systems. ACM Computing Surveys (CSUR), 2021.<br><br>You Xie, Erik Franz, Mengyu Chu, and Nils Thuerey. tempogan: A temporally coherent, volumetric gan for super resolution fluid flow. ACM Transactions on Graphics (TOG), 37(4):1–15, 2018.<br><br>Wenlong Zhang, Yihao Liu, Chao Dong, and Yu Qiao. Ranksrgan: Generative adversarial networks with ranker for image super-resolution. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3096–3105, 2019.<br><br>Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, and Yun Fu. Image super-resolution using very deep residual channel attention networks. In Proceedings of the European conference on computer vision (ECCV), pages 286–301, 2018a.<br><br>Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu. Residual dense network for image super resolution. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2472–2481, 2018b.

Presenters

  • Shengyu Chen

    University of Pittsburgh

Authors

  • Shengyu Chen

    University of Pittsburgh

  • Peyman Givi

    University of Pittsburgh

  • Xiaowei Jia

    University of Pittsburgh