Focus Session: Recent Advances in Data-driven and Machine Learning Methods for Turbulent Flows I

Presentations

• Unsteady Flow Field Predictions Using Multi-level Deep Convolutional Autoencoder Networks

  ORAL

  Nov. 24, 2019, 8:00 AM – Nov. 24, 2019, 8:13 AM

  Authors

  • Jiayang Xu

    • University of Michigan

  • Karthik Duraisamy

    • University of Michigan
    • University of Michigan, Ann Arbor

  View abstract →

• Physics-Constrained Convolutional LSTM Neural Networks for Generative Modeling of Turbulence

  ORAL

  Nov. 24, 2019, 8:13 AM – Nov. 24, 2019, 8:26 AM

  Authors

  • Arvind Mohan

    • Los Alamos National Laboratory

  • Daniel Livescu

    • Los Alamos National Laboratory

  • Michael Chertkov

    • University of Arizona

  View abstract →

• Physics Informed Learning of Lagrangian Turbulence: Velocity Gradient Tensor over Inertial-Range Geometry

  ORAL

  Nov. 24, 2019, 8:26 AM – Nov. 24, 2019, 8:39 AM

  Authors

  • Yifeng Tian

    • Los Alamos National Laboratory

  • Daniel Livescu

    • Los Alamos National Laboratory

  • Misha Chertkov

    • University of Arizona
    • Los Alamos National Laboratory, Los Alamos

  View abstract →

• Prediction of Aerodynamic Flow Fields Using Spectral Convolutions on Graph Networks

  ORAL

  Nov. 24, 2019, 8:39 AM – Nov. 24, 2019, 8:52 AM

  Authors

  • James Duvall

    • University of Michigan

  • Karthik Duraisamy

    • University of Michigan
    • University of Michigan, Ann Arbor

  • Yaser Afshar

    • University of Michigan

  View abstract →

• Potential of using deep neural networks for turbulent-flow predictions

  ORAL

  Nov. 24, 2019, 8:52 AM – Nov. 24, 2019, 9:05 AM

  Authors

  • Ricardo Vinuesa

    • Linn\'e Flow Centre, KTH Mechanics
    • KTH Mechanics
    • KTH Royal Institute of Technology

  • Prem A. Srinivasan

    • KTH Royal Institute of Technology

  • Luca Guastoni

    • KTH Royal Institute of Technology

  • Hossein Azizpour

    • KTH Royal Institute of Technology

  • Philipp Schlatter

    • KTH Royal Institute of Technology

  View abstract →

• Turbulence inflow generation using generative adversarial network

  ORAL

  Nov. 24, 2019, 9:05 AM – Nov. 24, 2019, 9:18 AM

  Authors

  • Junhyuk Kim

    • Yonsei University

  • Changhoon Lee

    • Yonsei University

  View abstract →

• Physics-informed Spatio-temporal Deep Learning Models

  POSTER

  Nov. 24, 2019, 9:18 AM – Nov. 24, 2019, 9:31 AM

  Authors

  • Karthik Kashinath

    • Lawrence Berkeley Lab

  • Adrian Albert

    • Lawrence Berkeley Lab

  • Rui Wang

    • Lawrence Berkeley Lab

  • Mustafa Mustafa

    • Lawrence Berkeley Lab

  • Rose Yu

    • Northeastern University

  View abstract →

• Neural Network Optimization Under Partial Differential Equation Constraints

  ORAL

  Nov. 24, 2019, 9:31 AM – Nov. 24, 2019, 9:44 AM

  Authors

  • Karthik Kashinath

    • Lawrence Berkeley Lab

  • Chiyu Jiang

    • U C Berkeley

  • Gavin Eli Jergensen

    • Lawrence Berkeley Lab

  • Mr Prabhat

    • Lawrence Berkeley Lab

  • Philip Marcus

    • University of California, Berkeley
    • UC Berkeley
    • U.C. Berkeley
    • U C Berkeley

  View abstract →

• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using a hierarchy of deep learning methods: Reservoir computing, ANN, and RNN-LSTM.

  ORAL

  Nov. 24, 2019, 9:44 AM – Nov. 24, 2019, 9:57 AM

  Authors

  • Pedram Hassanzadeh

    • Rice University

  • Ashesh Chattopadhyay

    • Rice University

  • Krishna Palem

    • Rice University

  • Devika Subramanian

    • Rice University

  View abstract →

• Data-driven super-parametrization using deep learning for large scale turbulent flow in weather/climate modeling

  ORAL

  Nov. 24, 2019, 9:57 AM – Nov. 24, 2019, 10:10 AM

  Authors

  • Ashesh Chattopadhyay

    • Rice University

  • Adam Subel

    • Rice University

  • Pedram Hassanzadeh

    • Rice University

  • Krishna Palem

    • Rice University

  View abstract →