Skip to main content
SpringerLink
Log in

Modeling Fluids Through Neural Networks

  • Chapter
  • First Online:
Deep Learning for Fluid Simulation and Animation

Part of the book series: SpringerBriefs in Mathematics ((BRIEFSMATH))

  • 253 Accesses

Abstract

The process of applying neural networks to yield data-driven models for fluid simulation can be described in six steps [29]: (1) Problem formulation; (2) Data generation, annotation, and preparation for training and testing; (3) Project a neural network architecture to work as a surrogate model; (4) Design a Loss function to quantify the error of the model prediction; (5) Model training based on the optimization of the Loss function; (6) Test the trained model to access its performance and generalization capability. In this chapter, we first discuss these steps and some related issues. Then, we revise fundamental elements for CNNs and GANs due to their importance for fluid modeling, as highlighted in a summary of related methodologies presented.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 16.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Alvaro Abucide-Armas, Koldo Portal-Porras, Unai Fernández-Gámiz, Ekaitz Zulueta, and Adrián Teso-Fz-Betoño. A data augmentation-based technique for deep learning applied to CFD simulations. Mathematics, 2021.

    Google Scholar 

  2. Nadeem Akhtar and U Ragavendran. Interpretation of intelligence in CNN-pooling processes: A methodological survey. Neural Computing and Applications, pages 1–20, 2020.

    Google Scholar 

  3. Yohai Bar-Sinai, Stephan Hoyer, Jason Hickey, and Michael P. Brenner. Learning data-driven discretizations for partial differential equations. Proceedings of the National Academy of Sciences of the United States of America, 116:15344–15349, 2019.

    Article  MathSciNet  Google Scholar 

  4. Imanol Bilbao and Javier Bilbao. Overfitting problem and the over-training in the era of data: Particularly for artificial neural networks. In 2017 Eighth International Conference on Intelligent Computing and Information Systems (ICICIS), pages 173–177, 2017.

    Google Scholar 

  5. J.U. Brackbill, D.B. Kothe, and H.M. Ruppel. Flip: A low-dissipation, particle-in-cell method for fluid flow. Computer Physics Communications, 48(1):25–38, 1988.

    Article  Google Scholar 

  6. S. L. Brunton and J. N. Kutz. Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control. Cambridge University Press, 2019.

    Book  Google Scholar 

  7. Steven L. Brunton. Applying Machine Learning to Study Fluid Mechanics. Acta Mechanica Sinica, pages 1–15, 2021.

    Google Scholar 

  8. Steven L. Brunton, Bernd R. Noack, and Petros Koumoutsakos. Machine Learning for Fluid Mechanics. Annual Review of Fluid Mechanics, 52(1):477–508, 2020.

    Article  MathSciNet  Google Scholar 

  9. Qian Chen, Yue Wang, Hui Wang, and Xubo Yang. Data-driven simulation in fluids animation: A survey. Virtual Reality and Intelligent Hardware, 3(2):87–104, 2021.

    Article  Google Scholar 

  10. Chen Cheng and Guang-Tao Zhang. Deep learning method based on physics informed neural network with resnet block for solving fluid flow problems. Water, 13, 02 2021.

    Article  Google Scholar 

  11. Mengyu Chu, Nils Thuerey, Hans Peter Seidel, Christian Theobalt, and Rhaleb Zayer. Learning meaningful controls for fluids. ACM Transactions on Graphics, 40(4), 2021.

    Google Scholar 

  12. Mengyu Chu and Nils Thürey. Data-driven synthesis of smoke flows with CNN-based feature descriptors. ACM Transactions on Graphics (TOG), 36:1–14, 2017.

    Article  Google Scholar 

  13. Richard Connor, Franco Alberto Cardillo, Robert Moss, and Fausto Rabitti. Evaluation of Jensen-Shannon distance over sparse data. In Nieves Brisaboa, Oscar Pedreira, and Pavel Zezula, editors, Similarity Search and Applications, pages 163–168, Berlin, Heidelberg, 2013. Springer Berlin Heidelberg.

    Google Scholar 

  14. Pandu Akbar Dwikatama, Dody Dharma, and Achmad I. Kistijantoro. Fluid simulation based on material point method with neural network. 2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT), pages 244–249, 2019.

    Google Scholar 

  15. Tom M George, Georgy E. Manucharyan, and Andrew F. Thompson. Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence. Nature communications, 12 1:800, 2021.

    Google Scholar 

  16. A. Géron. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. O’Reilly Media, 2019.

    Google Scholar 

  17. Gilson Antonio Giraldi. Machine Learning and Pattern Recognition, Lecture Notes - Graduate Program in Nanobiosystems, UFRJ-FIOCRUZ-INMETRO-LNCC, 2021.

    Google Scholar 

  18. I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. Adaptive Computation and Machine Learning series. MIT Press, 2016.

    Google Scholar 

  19. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. Generative adversarial nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8–13 2014, Montreal, Quebec, Canada, pages 2672–2680, 2014.

    Google Scholar 

  20. Simon Haykin. Neural Networks - A Comprehensive Foundation, Second Edition. Prentice Hall, 2 edition, 1998.

    Google Scholar 

  21. K. He and J. Sun. Convolutional neural networks at constrained time cost. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5353–5360, 2015.

    Google Scholar 

  22. Xin He, Kaiyong Zhao, and Xiaowen Chu. Automl: A survey of the state-of-the-art. Knowledge-Based Systems, 212:106622, 2021.

    Article  Google Scholar 

  23. Ihab F. Ilyas and Xu Chu. Data Cleaning. ACM, 2019.

    Book  Google Scholar 

  24. Byungsoo Kim, Vinicius C Azevedo, Nils Thuerey, Theodore Kim, Markus Gross, and Barbara Solenthaler. Deep fluids: A generative network for parameterized fluid simulations. In Computer graphics forum, volume 38, pages 59–70. Wiley Online Library, 2019.

    Google Scholar 

  25. Hyojin Kim, Junhyuk Kim, Sungjin Won, and Changhoon Lee. Unsupervised deep learning for super-resolution reconstruction of turbulence. Journal of Fluid Mechanics, 910, 2021.

    Google Scholar 

  26. J. Nathan Kutz. Deep learning in fluid dynamics. Journal of Fluid Mechanics, 814:1–4, 2017.

    Article  Google Scholar 

  27. Y. Lecun, Y. Bengio, and G Hinton. Deep learning. Nature, 521(7553):436–444, 2015.

    Google Scholar 

  28. Julia Ling, Andrew Kurzawski, and Jeremy Templeton. Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. Journal of Fluid Mechanics, 807:155–166, 2016.

    Article  MathSciNet  Google Scholar 

  29. S. Marsland. Machine Learning: An Algorithmic Perspective. Chapman & Hall/CRC The R Series. CRC Press, 2009.

    Google Scholar 

  30. Xuhui Meng and George Em Karniadakis. A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems. J. Comput. Phys., 401, 2020.

    Google Scholar 

  31. Arvind T. Mohan, Don Daniel, Michael Chertkov, and Daniel Livescu. Compressed convolutional LSTM: An efficient deep learning framework to model high fidelity 3d turbulence. arXiv: Fluid Dynamics, 2019.

    Google Scholar 

  32. Arvind T. Mohan, Nicholas Lubbers, Daniel Livescu, and Michael Chertkov. Embedding hard physical constraints in neural network coarse-graining of 3d turbulence, 2020.

    Google Scholar 

  33. Jeremy Morton, Antony Jameson, Mykel J. Kochenderfer, and Freddie D. Witherden. Deep dynamical modeling and control of unsteady fluid flows. In Samy Bengio, Hanna M. Wallach, Hugo Larochelle, Kristen Grauman, Nicolò Cesa-Bianchi, and Roman Garnett, editors, Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3–8, 2018, Montréal, Canada, pages 9278–9288, 2018.

    Google Scholar 

  34. I. Pointer. Programming PyTorch for Deep Learning: Creating and Deploying Deep Learning Applications. O’Reilly Media, 2019.

    Google Scholar 

  35. Jean Rabault, Miroslav Kuchta, Atle Jensen, Ulysse Réglade, and Nicolas Cerardi. Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control. Journal of Fluid Mechanics, 865:281–302, 2019.

    Article  MathSciNet  Google Scholar 

  36. Karam Sahoo, Ridam Hazra, Muhammad Fazal Ijaz, SeongKi Kim, Pawan Singh, and Mufti Mahmud. MIC_FuzzyNET: Fuzzy integral based ensemble for automatic classification of musical instruments from audio signals. IEEE Access, 9:1–1, 2022. https://doi.org/0.1109/ACCESS.2022.3208126.

  37. Fabrizio Sarghini, Giuseppe de Felice, and Stefania Santini. Neural networks based subgrid scale modeling in large eddy simulations. Computers & Fluids, 32:97–108, 2003.

    Article  Google Scholar 

  38. Connor Schenck and Dieter Fox. Spnets: Differentiable fluid dynamics for deep neural networks. In Aude Billard, Anca Dragan, Jan Peters, and Jun Morimoto, editors, Proceedings of The 2nd Conference on Robot Learning, volume 87 of Proceedings of Machine Learning Research, pages 317–335. PMLR, 29–31 Oct 2018.

    Google Scholar 

  39. P. Tan, M. Steinbach, and V. Kumar. Introduction to Data Mining. Addison-Wesley, 2005.

    Google Scholar 

  40. Kiwon Um, Xiangyu Hu, and Nils Thuerey. Liquid splash modeling with neural networks. Computer Graphics Forum, 37(8):171–182, 2018.

    Article  Google Scholar 

  41. Benjamin Ummenhofer, Lukas Prantl, Nils Thuerey, and Vladlen Koltun. Lagrangian fluid simulation with continuous convolutions. In International Conference on Learning Representations, 2020.

    Google Scholar 

  42. Benjamin Ummenhofer, Lukas Prantl, Nils Thuerey, and Vladlen Koltun. Lagrangian fluid simulation with continuous convolutions. In International Conference on Learning Representations, 2019.

    Google Scholar 

  43. Vladimir N. Vapnik. Statistical Learning Theory. John Wiley & Sons, INC., 1998.

    Google Scholar 

  44. Qi Wang, Yue Ma, Kun Zhao, and Yingjie Tian. A comprehensive survey of loss functions in machine learning. Annals of Data Science, 9, 04 2022.

    Article  Google Scholar 

  45. Ying Da Wang, Traiwit Chung, Ryan T. Armstrong, and Peyman Mostaghimi. Ml-lbm: Machine learning aided flow simulation in porous media. ArXiv, abs/2004.11675, 2020.

    Google Scholar 

  46. Qingsong Wen, Liang Sun, Xiaomin Song, Jingkun Gao, Xue Wang, and Huan Xu. Time series data augmentation for deep learning: A survey. CoRR, abs/2002.12478, 2020.

    Google Scholar 

  47. Gabriel D Weymouth. Data-driven multi-grid solver for accelerated pressure projection, 2021.

    Google Scholar 

  48. Steffen Wiewel, Moritz Becher, and Nils Thuerey. Latent Space Physics: Towards Learning the Temporal Evolution of Fluid Flow. Computer Graphics Forum, 2019.

    Google Scholar 

  49. You Xie, Erik Franz, Mengyu Chu, and Nils Thuerey. Tempogan: A temporally coherent, volumetric gan for super-resolution fluid flow. ACM Trans. Graph., 37(4), Jul 2018.

    Google Scholar 

  50. Cheng Yang, Xubo Yang, and Xiangyun Xiao. Data-driven projection method in fluid simulation. Computer Animation and Virtual Worlds, 27(3–4):415–424, 2016.

    Google Scholar 

  51. Matteo Zancanaro, Markus Mrosek, Giovanni Stabile, Carsten Othmer, and Gianluigi Rozza. Hybrid neural network reduced order modelling for turbulent flows with geometric parameters. Fluids, 6(8), 2021.

    Google Scholar 

  52. Linyang Zhu, Weiwei Zhang, Xuxiang Sun, Yilang Liu, and Xianxu Yuan. Turbulence closure for high reynolds number airfoil flows by deep neural networks. Aerospace Science and Technology, 110:106452, 2021.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. National Laboratory for Scientific Computing, Petrópolis, Rio de Janeiro, Brazil

    Gilson Antonio Giraldi & Liliane Rodrigues de Almeida

  2. Institute of Computing, Federal University of Bahia, Salvador, Bahia, Brazil

    Antonio Lopes Apolinário Jr.

  3. Campus Petrópolis, Federal Center for Technological Education Celso Suckow da Fonseca – RJ, Petrópolis, Rio de Janeiro, Brazil

    Leandro Tavares da Silva

Authors
  1. Gilson Antonio Giraldi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Liliane Rodrigues de Almeida
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Antonio Lopes Apolinário Jr.
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Leandro Tavares da Silva
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Antonio Giraldi, G., Almeida, L.R.d., Lopes Apolinário Jr., A., Silva, L.T.d. (2023). Modeling Fluids Through Neural Networks. In: Deep Learning for Fluid Simulation and Animation. SpringerBriefs in Mathematics. Springer, Cham. https://doi.org/10.1007/978-3-031-42333-8_6

Download citation

Publish with us

Policies and ethics

Search

Navigation