Emerging Trends in Fluid Dynamics: Physics-Informed Machine Learning and Dynamic Modeling

Presentations

• A Physics-Informed Machine Learning Approach for Predicting Atomized Drop Distributions in Liquid Jet Simulations

  ORAL

  Nov. 20, 2023, 1:50 PM – Nov. 20, 2023, 2:03 PM

  Presenters

  • Chris J Cundy

    Stanford University

  Authors

  • Chris J Cundy

    Stanford University

  • Shahab Mirjalili

    Center for Turbulence Research, Stanford University, Stanford University

  • Charlelie Laurent

    Stanford University

  • Stefano Ermon

    Stanford University

  • Ali Mani

    Stanford University, Standard University, Department of Mechanical Engineering, Stanford University

  View abstract →

• Physics-Informed Neural Networks (PINN) for Enhanced Dynamic Modeling and Reverse Problem Solving in an Electro-Wetting Operated Microfluid Prism

  ORAL

  Nov. 20, 2023, 2:03 PM – Nov. 20, 2023, 2:16 PM

  Publication: 1 Lee, Duck-Gyu, et al.:"Dynamics of a microliquid prism actuated by electrowetting." Lab on a Chip 13.2 (2013): 274-279.

  Presenters

  • Chihoon Song

    Gachon University

  Authors

  • Chihoon Song

    Gachon University

  • Duck Gyu Lee

    Korea Institute of Machinery & Materials

  • Jeongsu LEE

    Gachon University

  • Keunhwan Park

    Gachon University

  View abstract →

• Predicting the three-dimensional separating flow in a diffuser using physics-informed neural networks

  ORAL

  Nov. 20, 2023, 2:16 PM – Nov. 20, 2023, 2:29 PM

  Publication: Reconstructing the three-dimensional flow field of a turbulent separation bubble using physics-informed neural networks (planned submission)

  Presenters

  • Ben Steinfurth

    Tech Univ Berlin

  Authors

  • Ben Steinfurth

    Tech Univ Berlin

  • Julien Weiss

    TU Berlin

  View abstract →

• DNS and physics-informed surrogate models of surfactant-laden dispersed flows

  ORAL

  Nov. 20, 2023, 2:29 PM – Nov. 20, 2023, 2:42 PM

  Presenters

  • Juan Pablo Valdes

    Imperial College London

  Authors

  • Juan Pablo Valdes

    Imperial College London

  • Fuyue Liang

    Imperial College London

  • Lyes Kahouadji

    Imperial College London

  • Sibo Cheng

    Imperial College London

  • Seungwon Shin

    Department of Mechanical and System Design Engineering, Hongik University, Seoul 04066, Republic of Korea, Hongik University

  • Jalel Chergui

    Université Paris Saclay, Centre National de la Recherche Scientifique (CNRS), Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), 91400 Orsay, France, LISN-CNRS

  • Damir Juric

    Université Paris Saclay, Centre National de la Recherche Scientifique (CNRS), Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), 91400 Orsay, France, LISN-CNRS

  • Omar K Matar

    Imperial College London

  View abstract →

• Discovering self-similar blow-up solutions using physics-informed neural networks

  ORAL

  Nov. 20, 2023, 2:42 PM – Nov. 20, 2023, 2:55 PM

  Publication: Wang, Y., Lai, C. Y., Gómez-Serrano, J., & Buckmaster, T. (2023). Asymptotic Self-Similar Blow-Up Profile for Three-Dimensional Axisymmetric Euler Equations Using Neural Networks. Physical Review Letters, 130(24), 244002.
  
  Wang, Y., & Lai, C. Y. (2023). Multi-stage Neural Networks: Function Approximator of Machine Precision. arXiv preprint arXiv:2307.08934.

  Presenters

  • Yongji Wang

    Stanford University

  Authors

  • Yongji Wang

    Stanford University

  • Ching-Yao Lai

    Stanford University

  • Tristan Buckmaster

    University of Maryland

  • Javier Gomez Serrano

    Brown University

  View abstract →

• Semi-supervised machine learning model for Lagrangian state estimation

  ORAL

  Nov. 20, 2023, 2:55 PM – Nov. 20, 2023, 3:08 PM

  Publication: Planned to submit to arXiv.

  Presenters

  • Reno Miura

    Keio University

  Authors

  • Reno Miura

    Keio University

  • Koji Fukagata

    Keio University, Keio Univ

  View abstract →

• Cooperative swimming at low Reynolds numbers using deep reinforcement learning

  ORAL

  Nov. 20, 2023, 3:08 PM – Nov. 20, 2023, 3:21 PM

  Publication: Liu, Y., Zou, Z., Pak, O.S. et al. Learning to cooperate for low-Reynolds-number swimming: a model problem for gait coordination. Sci Rep 13, 9397 (2023). https://doi.org/10.1038/s41598-023-36305-y

  Presenters

  • Yangzhe Liu

    The University of Hong Kong

  Authors

  • Yangzhe Liu

    The University of Hong Kong

  • Zonghao Zou

    Cornell University

  • On Shun Pak

    Santa Clara University

  • Alan C. H. Tsang

    The University of Hong Kong

  View abstract →

• Reinforcement learning of reconfigurable microswimmers

  ORAL

  Nov. 20, 2023, 3:21 PM – Nov. 20, 2023, 3:34 PM

  Presenters

  • Alan C. H. Tsang

    The University of Hong Kong

  Authors

  • Alan C. H. Tsang

    The University of Hong Kong

  • On Shun Pak

    Santa Clara University

  View abstract →