APS Logo

Turbulence: Modeling & Simulations I: Data-Driven and Machine Learning Approaches

ORAL · A11 · ID: 22792

Presentations

  • Data Driven Learning of Mori-Zwanzig Operators for Isotropic Turbulence

    ORAL

    –

    Publication: Y. Tian, Y. T. Lin, M. Anghel, and D. Livescu, "Data Driven Learning of Mori-Zwanzig Operators for Isotropic Turbulence" (planned).

    Presenters

    • Yifeng Tian

      Los Alamos National Laboratory

    Authors

    • Yifeng Tian

      Los Alamos National Laboratory

    • Yen Ting Lin

      Los Alamos National Laboratory

    • Marian Anghel

      Los Alamos National Laboratory

    • Daniel Livescu

      Los Alamos Natl Lab, Los Alamos National Laboratory

    View abstract →

  • Reconstruction of turbulent data from TURB-Rot database with deep generative models and Gappy POD

    ORAL

    –

    Publication: Buzzicotti, M., Bonaccorso, F., Di Leoni, P. C., & Biferale, L. (2021). Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database. Physical Review Fluids, 6(5), 050503.

    Presenters

    • Michele Buzzicotti

      Department of Physics and INFN University of Rome Tor Vergata., Department of Physics & INFN, University of Rome Tor Vergata, Via della Ricerca Scientifica 1, 00133 Rome, Italy

    Authors

    • Michele Buzzicotti

      Department of Physics and INFN University of Rome Tor Vergata., Department of Physics & INFN, University of Rome Tor Vergata, Via della Ricerca Scientifica 1, 00133 Rome, Italy

    • Tianyi Li

      Department of Mechanics and Aerospace Engineering, SUSTech, Shenzhen, China

    • Fabio Bonaccorso

      Center for Life Nano Science@La Sapienza, Istituto Italiano di Tecnologia, 00161 Roma, Italy

    • Patricio Clark Di Leoni

      Johns Hopkins University, Department of Mechanical Engineering, Johns Hopkins University, Baltimore, Maryland 21218, USA, Dept. of Mechanical Engineering, Johns Hopkins University, Baltimore, Maryland 21218, USA

    • Luca Biferale

      University of Rome "Tor Vergata", Italy, University of Rome "Tor Vergata", INFN, University of Rome Tor Vergata, INFN - Rome, Department of Physics & INFN, University of Rome Tor Vergata, Via della Ricerca Scientifica 1, 00133 Rome, Italy

    View abstract →

  • Non-intrusive sensing from coarse measurements by means of generative adversarial networks (GANs)

    ORAL

    –

    Publication: https://arxiv.org/abs/2103.07387

    Presenters

    • Ricardo Vinuesa

      SimEx/FLOW, KTH Engineering Mechanics, Royal Institute of Technology, Stockholm, Sweden, KTH Royal Institute of Technology, KTH, SimEx/FLOW, KTH Engineering Mechanics

    Authors

    • Ricardo Vinuesa

      SimEx/FLOW, KTH Engineering Mechanics, Royal Institute of Technology, Stockholm, Sweden, KTH Royal Institute of Technology, KTH, SimEx/FLOW, KTH Engineering Mechanics

    • Alejandro G\"uemes

      Carlos III University

    • Hao Hu

      KTH Royal Institute of Technolgoy

    • Stefano Discetti

      Aerospace Engineering Research Group, Universidad Carlos III de Madrid, Leganes, Spain, Carlos III University

    • Andrea Ianiro

      Aerospace Engineering Research Group, Universidad Carlos III de Madrid, Leganes, Spain, Carlos III University

    • Beril Sirmacek

      Smart Cities, School of Creative Technology, Saxion University of Applied Sciences

    • Hossein Azizpour

      Robotics, Perception and Learning (RPL), KTH Royal Institute of Technology, KTH Royal Institute of Technology

    View abstract →

  • Data-driven subgrid-scale parameterization of turbulence in the small-data limit

    ORAL

    –

    Publication: [1] Subel, Adam, Ashesh Chattopadhyay, Yifei Guan, and Pedram Hassanzadeh. "Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning." Physics of Fluids 33, no. 3 (2021): 031702.<br>[2] Guan, Yifei, Ashesh Chattopadhyay, Adam Subel, and Pedram Hassanzadeh. "Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning." arXiv preprint arXiv:2102.11400 (2021).<br>[3] Guan, Yifei, Adam Subel, Ashesh Chattopadhyay, and Pedram Hassanzadeh. "Developing data-driven subgrid-scale models for stable LES in the small-data limit: Applications of physics-constrained convolutional neural networks and data augmentation" (in preparation).

    Presenters

    • YIFEI GUAN

      Rice University

    Authors

    • YIFEI GUAN

      Rice University

    • Adam Subel

      Rice Univ

    • Ashesh K Chattopadhyay

      Rice University, Rice Univ

    • Pedram Hassanzadeh

      Rice, Rice Univ

    View abstract →

  • Wall-models of turbulent flows via scientific multi-agent reinforcement learning

    ORAL

    –

    Publication: 1. Automating turbulence modelling by multi-agent reinforcement learning, Guido Novati, Hugues Lascombes de Laroussilhe & Petros Koumoutsakos, Nature Machine Intelligence, volume 3, pages 87–96 (2021)<br>2. Scientific multi-agent reinforcement learning for wall-models of turbulent flows, Jane Bae and Petros Koumoutsakos, arXiv:2106.11144

    Presenters

    • Petros Koumoutsakos

      Harvard University, ETH Zurich / Harvard University

    Authors

    • Petros Koumoutsakos

      Harvard University, ETH Zurich / Harvard University

    • H. Jane Bae

      California Institute of Technology, Caltech

    View abstract →

  • Machine Learning Lagrangian Large Eddy Simulations with Smoothed Particle Hydrodynamics

    ORAL

    –

    Presenters

    • Michael Chertkov

      University of Arizona

    Authors

    • Yifeng Tian

      Los Alamos National Laboratory

    • Michael Chertkov

      University of Arizona

    • Michael Woodward

      University of Arizona

    • Mikhail Stepanov

      University of Arizona

    • Chris Fryer

      Los Alamos Natl Lab, Los Alamos National Laboratory

    • Criston M Hyett

      University of Arizona, The University of Arizona

    • Daniel Livescu

      Los Alamos Natl Lab, Los Alamos National Laboratory

    View abstract →