Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Reconstructing Turbulent Flows Using Physics-Aware Spatio-Temporal Dynamics and Test-Time Refinement (2304.12130v3)

Published 24 Apr 2023 in physics.flu-dyn and cs.LG

Abstract: Simulating turbulence is critical for many societally important applications in aerospace engineering, environmental science, the energy industry, and biomedicine. Large eddy simulation (LES) has been widely used as an alternative to direct numerical simulation (DNS) for simulating turbulent flows due to its reduced computational cost. However, LES is unable to capture all of the scales of turbulent transport accurately. 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 spatio-temporal complexity of turbulent flows. In this work, we propose a new physics-guided neural network for reconstructing the sequential DNS from low-resolution LES data. The proposed method leverages the partial differential equation that underlies the flow dynamics in the design of spatio-temporal model architecture. A degradation-based refinement method is also developed to enforce physical constraints and further reduce the accumulated reconstruction errors over long periods. The results on two different types of turbulent flow data confirm the superiority of the proposed method in reconstructing the high-resolution DNS data and preserving the physical characteristics of flow transport.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (63)
  1. Fast, accurate, and lightweight super-resolution with cascading residual network. In Proceedings of the European conference on computer vision (ECCV). 252–268.
  2. Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET). IEEE, 1–6.
  3. Physics Guided Neural Networks for Spatio-temporal Super-resolution of Turbulent Flows. In The 38th Conference on Uncertainty in Artificial Intelligence.
  4. MAgnet: Mesh agnostic neural PDE solver. Advances in Neural Information Processing Systems 35 (2022), 31972–31985.
  5. The Taylor-Green vortex and fully developed turbulence. Journal of Statistical Physics 34, 5 (1984), 1049–1063.
  6. John Butcher. 2007. Runge-kutta methods. Scholarpedia 2, 9 (2007), 3147.
  7. Physics-guided machine learning from simulated data with different physical parameters. Knowledge and Information Systems 65, 8 (2023), 3223–3250.
  8. Reconstructing high-resolution turbulent flows using physics-guided neural networks. In 2021 IEEE International Conference on Big Data (Big Data). IEEE, 1369–1379.
  9. Physics-guided graph meta learning for predicting water temperature and streamflow in stream networks. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2752–2761.
  10. Fsrnet: End-to-end learning face super-resolution with facial priors. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2492–2501.
  11. Mfagan: A compression framework for memory-efficient on-device super-resolution gan. arXiv preprint arXiv:2107.12679 (2021).
  12. Second-Order Attention Network for Single Image Super-Resolution. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11057–11066. https://doi.org/10.1109/CVPR.2019.01132
  13. Physics-guided neural networks (pgnn): An application in lake temperature modeling. In Knowledge Guided Machine Learning. Chapman and Hall/CRC, 353–372.
  14. Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework. Physics of Fluids 31, 12 (2019), 125111.
  15. Learning a deep convolutional network for image super-resolution. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13. Springer, 184–199.
  16. Multi-scale message passing neural pde solvers. arXiv preprint arXiv:2302.03580 (2023).
  17. Cross-modality high-frequency transformer for mr image super-resolution. In Proceedings of the 30th ACM International Conference on Multimedia. 1584–1592.
  18. A hybrid network of cnn and transformer for lightweight image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 1103–1112.
  19. Super-resolution reconstruction of turbulent flows with machine learning. Journal of Fluid Mechanics 870 (2019), 106–120.
  20. Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows. Journal of Fluid Mechanics 909 (2021), A9.
  21. P. Givi. 1994. Spectral and Random Vortex Methods in Turbulent Reacting Flows. In Turbulent Reacting Flows, P. A. Libby and F. A. Williams (Eds.). Academic Press, London, England, Chapter 8, 475–572.
  22. Paul C Hanson et al. 2020. Predicting lake surface water phosphorus dynamics using process-guided machine learning. Ecological Modelling 430 (2020), 109136.
  23. Physics Guided Neural Networks for Time-Aware Fairness: An Application in Crop Yield Prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 14223–14231.
  24. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.
  25. Physics-guided Graph Diffusion Network for Combining Heterogeneous Simulated Data: An Application in Predicting Stream Water Temperature. In Proceedings of the 2023 SIAM International Conference on Data Mining (SDM). SIAM, 361–369.
  26. 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. SIAM, 558–566.
  27. Fuzzy weighted average filter. In WCC 2000-ICSP 2000. 2000 5th International Conference on Signal Processing Proceedings. 16th World Computer Congress 2000, Vol. 1. IEEE, 525–528.
  28. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017).
  29. Physics guided machine learning methods for hydrology. arXiv preprint arXiv:2012.02854 (2020).
  30. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  31. Temporal convolutional networks: A unified approach to action segmentation. In European conference on computer vision. Springer, 47–54.
  32. Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4681–4690.
  33. Fourier neural operator for parametric partial differential equations. arXiv preprint arXiv:2010.08895 (2020).
  34. Light field image super-resolution with transformers. IEEE Signal Processing Letters 29 (2022), 563–567.
  35. Deep learning methods for super-resolution reconstruction of turbulent flows. Physics of Fluids 32, 2 (2020), 025105.
  36. KGML-ag: a modeling framework of knowledge-guided machine learning to simulate agroecosystems: a case study of estimating N 2 O emission using data from mesocosm experiments. Geoscientific Model Development 15, 7 (2022), 2839–2858.
  37. Transformer for single image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 457–466.
  38. Forced Isotropic Turbulence Data Set (Extended). (2012).
  39. PhyNet: Physics Guided Neural Networks for Particle Drag Force Prediction in Assembly. In Proceedings of the 2020 SIAM International Conference on Data Mining. SIAM, 559–567.
  40. Self-contained filtered density function. Physical Review Fluids 2, 9 (2017), 094603.
  41. Super-resolution image reconstruction: a technical overview. IEEE signal processing magazine 20, 3 (2003), 21–36.
  42. Image transformer. In International conference on machine learning. PMLR, 4055–4064.
  43. Process-guided deep learning predictions of lake water temperature. Water Resources Research 55, 11 (2019), 9173–9190.
  44. Pierre Sagaut. 2005. Large eddy simulation for incompressible flows: an introduction. Springer Science & Business Media.
  45. Image super-resolution via deep recursive residual network. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3147–3155.
  46. Uddeshya Upadhyay and Suyash P Awate. 2019. Robust super-resolution GAN, with manifold-based and perception loss. In 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE, 1372–1376.
  47. A fast and efficient super-resolution network using hierarchical dense residual learning. In 2021 IEEE International Conference on Image Processing (ICIP). IEEE, 1809–1813.
  48. Attention is all you need. Advances in neural information processing systems 30 (2017).
  49. Detail-preserving transformer for light field image super-resolution. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 2522–2530.
  50. Recovering realistic texture in image super-resolution by deep spatial feature transform. In Proceedings of the IEEE conference on computer vision and pattern recognition. 606–615.
  51. Esrgan: Enhanced super-resolution generative adversarial networks. In ECCV Workshops.
  52. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing 13, 4 (2004), 600–612.
  53. RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 10 (2021), 1–1.
  54. Wikipedia contributors. 2022a. Finite difference method — Wikipedia, The Free Encyclopedia. https://en.wikipedia.org/w/index.php?title=Finite_difference_method&oldid=1126400243 [Online; accessed 25-January-2023].
  55. Wikipedia contributors. 2022b. Laplace operator — Wikipedia, The Free Encyclopedia. https://en.wikipedia.org/w/index.php?title=Laplace_operator&oldid=1127277109 [Online; accessed 23-January-2023].
  56. Integrating scientific knowledge with machine learning for engineering and environmental systems. Comput. Surveys 55, 4 (2022), 1–37.
  57. tempogan: A temporally coherent, volumetric gan for super-resolution fluid flow. ACM Transactions on Graphics (TOG) 37, 4 (2018), 1–15.
  58. Super-resolution reconstruction of turbulent flows with a transformer-based deep learning framework. Physics of Fluids 35, 5 (2023).
  59. Learning texture transformer network for image super-resolution. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 5791–5800.
  60. Super-resolution reconstruction for the three-dimensional turbulence flows with a back-projection network. Physics of Fluids 35, 5 (2023).
  61. Image super-resolution using very deep residual channel attention networks. In Proceedings of the European conference on computer vision (ECCV). 286–301.
  62. Residual Dense Network for Image Super-Resolution. arXiv preprint arXiv:1802.08797 (2018).
  63. Self-calibrated efficient transformer for lightweight super-resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 930–939.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now