Interact: Machine Learning for Fluid Mechanics
ORAL · C36 · ID: 3585744
Presentations
-
Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Generative Models
ORAL
–
Publication: Dong, X., Yang, H., & Wu, J. L. (2025). Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models. arXiv preprint arXiv:2506.20771.
Presenters
-
Xinghao Dong
University of Wisconsin - Madison
Authors
-
Xinghao Dong
University of Wisconsin - Madison
-
Huchen Yang
University of Wisconsin - Madison
-
Jinlong Wu
University of Wisconsin - Madison
-
-
Extracting time-varying causal modes of aerodynamic flows with information-theoretic machine learning
ORAL
–
Publication: Fukami, K., & Araki, R. (2025). Information-theoretic machine learning for time-varying mode decomposition of separated aerodynamic flows. AIAA Journal.
Presenters
-
Kai Fukami
Tohoku University
Authors
-
Kai Fukami
Tohoku University
-
Ryo Araki
Tokyo University of Science
-
-
Space-time model reduction using SPOD modes
ORAL
–
Publication: Space-time model reduction in the frequency domain, Frame and Towne, arXiv, 2024<br>Linear model reduction using SPOD modes, Frame, Lin, Schmidt, Towne, arXiv 2024
Presenters
-
Peter Keaton Frame
University of Michigan
Authors
-
Peter Keaton Frame
University of Michigan
-
Aaron S. Towne
University of Michigan
-
-
Tensor Train-based cross interpolation method for solving high-dimensional PDF transport equation of turbulent flows
ORAL
–
Presenters
-
Behzad Ghahremani
University of Pittsburgh
Authors
-
Behzad Ghahremani
University of Pittsburgh
-
Peyman Givi
University of Pittsburgh
-
Hessam Babaee
University of Pittsburgh
-
-
No more adjoints: Calibrating chaotic dynamical systems with weak-form learning
ORAL
–
Presenters
-
Romit Maulik
The Pennsylvania State University, Argonne National Laboratory
Authors
-
Xuyang Li
The Pennsylvania State University
-
John Harlim
The Pennsylvania State University
-
Romit Maulik
The Pennsylvania State University, Argonne National Laboratory
-
-
Super-resolution of turbulence with a 4DVar training algorithm
ORAL
–
Publication: Page, J. "Super-resolution of turbulence with dynamics in the loss", Journal of Fluid Mechanics 1002, R3 (2025)<br>Scherer, M. & Linkmann, M. & Page, J. "State estimation with a combination of 4DVar and super-resolution in body-forced turbulence" (in preparation -- working title)
Presenters
-
Jacob Page
University of Edinburgh
Authors
-
Jacob Page
University of Edinburgh
-
Markus Weyrauch
Karlsruhe Institute of Technology
-
Moritz F Linkmann
University of Edinburgh
-
-
Field Inversion Machine Learning for Predicting Time-Resolved Unsteady Flows in Dynamic Stall
ORAL
–
Presenters
-
Ping He
Iowa State University
Authors
-
Ping He
Iowa State University
-
Zilong Li
Iowa State University
-
Lean Fang
Iowa State University
-
Anupam Sharma
Iowa State University
-
-
The role of the law of the wall in enabling generalization of data-driven turbulence models
ORAL
–
Presenters
-
Jiaqi Li
Pennsylvania State University
Authors
-
Jiaqi Li
Pennsylvania State University
-
Xiang I. A. Yang
Pennsylvania State University
-
Robert F Kunz
Pennsylvania State University
-
George P Huang
Wright State University
-
-
Non-Linear Super-Stencils for RANS turbulence model corrections
ORAL
–
Publication: https://doi.org/10.1038/s42005-025-02149-3
Presenters
-
Jonas Luther
Eth Zurich
Authors
-
Jonas Luther
Eth Zurich
-
Patrick Jenny
ETH Zurich
-
-
Equivariant Machine Learning of Sub-Grid Scale Closure Models for Large Eddy Simulation
ORAL
–
Presenters
-
Ryley McConkey
Massachusetts Institute of Technology
Authors
-
Ryley McConkey
Massachusetts Institute of Technology
-
Julia Balla
Massachusetts Institute of Technology
-
Elyssa F Hofgard
Massachusetts Institute of Technology
-
Tess E Smidt
Massachusetts Institute of Technology
-
-
FIRST INTERACT DISCUSSION WITH POSTERS
COFFEE_KLATCH
–
-
Symmetry-aware Reynolds-averaged turbulence modeling with equivariant neural networks
ORAL
–
Publication: A planned paper is currently in the final stages of preparation.
Presenters
-
Aaron Miller
Harvard University
Authors
-
Aaron Miller
Harvard University
-
Sahil Kommalapati
University of Texas at Austin
-
Robert D Moser
University of Texas at Austin
-
Petros Koumoutsakos
Harvard University
-
-
GenAI meets Turbulence: From Super-resolution to Forecasting and Full Field Reconstruction from Sparse Observations
ORAL
–
Presenters
-
Vivek Oommen
Brown University
Authors
-
Vivek Oommen
Brown University
-
Aniruddha Bora
Brown University
-
George Em Karniadakis
Division of Applied Mathematics and School of Engineering, Brown University, Providence, RI, 02912, USA, Division of Applied Mathematics, Brown University
-
Siavash Khodakarami
Brown University, Division of Applied Mathematics, Brown University
-
Zhicheng Wang
Brown University, Division of Applied Mathematics, Brown University
-
-
Machine Learning-Assisted Model Blending for Generalizable Turbulence Corrections
ORAL
–
Presenters
-
Mourad Oulghelou
Sorbonne Universite, Sorbonne University
Authors
-
Mourad Oulghelou
Sorbonne Universite, Sorbonne University
-
Paola Cinnella
Sorbonne Université
-
Xavier Merle
Ecole Nationale Supérieure d'Arts et Métiers
-
-
Capturing Low-Wavenumber Near-Wall Structures via Conditional Generative Modeling
ORAL
–
Publication: M H Parikh, X. Fan, J.-X. Wang, Conditional flow matching for generative modeling of near-wall turbulence with quantified uncertainty, Under review, JFM
Presenters
-
Meet H Parikh
Cornell University
Authors
-
Meet H Parikh
Cornell University
-
Xiantao Fan
Cornell University
-
Meng Wang
University of Notre Dame
-
Jian-Xun Wang
Cornell University, University of Notre Dame
-
-
Reynolds Number Effects in Data-driven Learning of Mori-Zwanzig Memory Operators for Lagrangian Particle Dynamics
ORAL
–
Presenters
-
Rohini Uma-Vaideswaran
Georgia Institute of Technology
Authors
-
Rohini Uma-Vaideswaran
Georgia Institute of Technology
-
Xander M de Wit
Eindhoven University of Technology
-
Michael Woodward
Los Alamos National Laboratory (LANL)
-
Alessandro Gabbana
Los Alamos National Laboratory (LANL)
-
André Freitas
Dept. Physics and INFN, University of Rome "Tor Vergata", Information Processing and Communications Laboratory, Télécom Paris, IP Paris
-
Pui-Kuen Yeung
Georgia Institute of Technology
-
Daniel Livescu
Los Alamos National Laboratory (LANL)
-
-
Generative modeling for closure and linearized stability of chaotic dynamical systems
ORAL
–
Publication: Williams, E., and Darmofal, D., "Stochastic generative methods for stable and accurate closure modeling of chaotic dynamical systems", arXiv:2504.09750, April 2025.
Presenters
-
Emily Williams
Massachusetts Institute of Technology
Authors
-
Emily Williams
Massachusetts Institute of Technology
-
David Darmofal
Massachusetts Institute of Technology
-
-
Large Language Model Driven Development of Turbulence Models
ORAL
–
Publication: Large Language Model Driven Development of Turbulence Models DOI: 10.48550/arXiv.2505.01681
Presenters
-
Zhongxin Yang
Peking University
Authors
-
Zhongxin Yang
Peking University
-
Yuanwei Bin
Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, 315200, Zhejiang, China
-
Yipeng Shi
Peking University
-
Xiang I. A. Yang
Pennsylvania State University
-
-
HydroGym: A Reinforcement Learning Platform for Fluid Dynamics
ORAL
–
Presenters
-
Steven L Brunton
University of Washington
Authors
-
Christian Lagemann
University of Washington
-
Jared Callaham
University of Washington
-
Ludger Paehler
Tech Univ Muenchen
-
Sajeda Mokbel
University of Washington
-
Samuel Ahnert
University of Washington
-
Kai Lagemann
Statistics and Machine Learning, German Center for Neurodegenerative Diseases (DZNE), Bonn, Germany
-
Miro Gondrum
RWTH Aachen
-
Mario Ruettgers
Pohang Univ of Sci & Tech
-
Matthias Meinke
Institue of Aerodynamics and Chair of Fluid Mechanics, RWTH Aachen University
-
Nikolaus A Adams
Tech Univ Muenchen
-
Esther Lagemann
AI Institute in Dynamic Systems, University of Washington
-
Steven L Brunton
University of Washington
-
-
Reinforcement Learning for Collaborative Wind Farm Control and Power Optimization
ORAL
–
Publication: Mole, A., Weissenbacher, M., Rigas, G., & Laizet, S. (2025). Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control. arXiv preprint arXiv:2506.20554.
Presenters
-
Sylvain Laizet
Imperial College London
Authors
-
Sylvain Laizet
Imperial College London
-
Andrew Mole
Imperial College London
-
Max Weissenbacher
Imperial College London
-
Georgios Rigas
Imperial College London
-
-
SECOND INTERACT DISCUSSION WITH POSTERS
COFFEE_KLATCH
–