Group invariant convolutional neural networks-based deep reinforcement learning for effective flow control

Joongoo Jeon¹, Jean Rabault², Joel Vasanth³, Francisco Alcántara-Á vila³, Ricardo Vinuesa³

¹Jeonbuk National University, Graduate School of Integrated Energy-AI, 54896 Jeonju-si, South Korea; ²Independent Researcher, Oslo, Norway; ³KTH Royal Institute of Technology, FLOW, Engineering Mechanics, SE-100 44 Stockholm, Sweden

Geometry-informed Deep Learning approach for predicting fluid flow in reactors

Nausheen Basha¹, Mosayeb Shams¹, Amrutha Sreekumar¹, Sibo Cheng², Rossella Arcucci³, Omar K. Matar¹

¹Department of Chemical Engineering, Imperial College London, UK; ²Data Science Institute, Department of Computing, Imperial College London, UK; ³Department of Earth Science & Engineering, Imperial College London, UK

Flow field and body shape reconstruction for compressible flows using ODIL & JAX-Fluids

Deniz Bezgin¹, Aaron Buhendwa¹, Petr Karnakov², Nikolaus Adams¹, Petros Koumoutsakos²

¹Technical University of Munich, School of Engineering and Design, Chair of Aerodynamics and Fluid Mechanics; ²Computational Science and Engineering Laboratory, Harvard John A. Paulson School of Engineering and Applied Sciences

Extracting similarity from data

Nikos Bempedelis¹, Luca Magri^2,3,4, Kostas Steiros²

¹School of Engineering and Materials Science, Queen Mary University of London, E1 4NS, London, UK; ²Department of Aeronautics, Imperial College London, SW7 2AZ London, UK; ³The Alan Turing Institute, London NW1 2DB, UK; ⁴Politecnico di Torino, DIMEAS, Corso Duca degli Abruzzi, 24 10129 Torino, Italy

Explainable deep learning to identify coherent structures in turbulence

Ricardo Vinuesa¹, Andrés Cremades¹, Rahul Deshpande², Pedro Quintero³, Martin Lellep⁴, Moritz Linkmann⁴, Ivan Marusic², Sergio Hoyas³

¹KTH Royal Institute of Technology; ²University of Melbourne; ³Polytechnic University of Valencia; ⁴University of Edinburgh