S4 EP3 - Prof. Ricardo Vinuesa on AI for Fluid Mechanics

Foundation models, explainable AI and autonomous discovery in fluid mechanics are the focus of this conversation with Professor Ricardo Vinuesa, Associate Chair for Research and Associate Professor of Aerospace Engineering at the University of Michigan. Neil and Ricardo discuss latent representations, turbulence, reduced-order modeling, flow control and whether AI can discover physical mechanisms that humans might miss. Full episode, corrected transcript and resources: https://neilashton.co.uk/podcasts/s4-e3-prof-ricardo-vinuesa-on-ai-for-fluid-mechanics/ Topics Can fluid mechanics have a “ChatGPT moment”? Foundation models and latent representations for turbulent flows Explainable AI, causality and identifying the mechanisms that matter Why classical coherent structures may tell only part of the turbulence story Physics-informed vs purely data-driven machine learning Reduced-order modeling, autoencoders, transformers and nonlinear compression Deep reinforcement learning for flow control and optimization Agentic AI and autonomous scientific discovery in PDE-governed systems How academia, computer science and engineering education must adapt to AI Papers Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations — Abhijeet Vishwasrao et al. https://arxiv.org/abs/2604.09584 Multi-agent LLMs and latent foundation models autonomously explore flow physics in a tandem-cylinder problem. Enhancing computational fluid dynamics with machine learning — Ricardo Vinuesa, Steven L. Brunton https://doi.org/10.1038/s43588-022-00264-7 A roadmap for useful ML in CFD, including faster simulations, turbulence models and reduced-order models. Identifying regions of importance in wall-bounded turbulence through explainable deep learning — Andrés Cremades et al. https://doi.org/10.1038/s41467-024-47954-6 Explainable AI identifies flow structures that matter for prediction and control. β-Variational autoencoders and transformers for reduced-order modelling of fluid flows — Alberto Solera-Rico et al. https://doi.org/10.1038/s41467-024-45578-4 Disentangled latent spaces, autoencoders and transformers support interpretable reduced-order models. Improving turbulence control through explainable deep learning — Miguel Beneitez et al. https://arxiv.org/abs/2504.02354 Explainable AI and deep reinforcement learning target turbulence-sustaining mechanisms. Links VinuesaLab https://www.vinuesalab.com/ Ricardo Vinuesa — University of Michigan Aerospace Engineering https://aero.engin.umich.edu/people/ricardo-vinuesa/ AI and ML for Fluid Dynamics course — Ricardo Vinuesa and Sergio Hoyas https://www.flowthermolab.com/courses/ai-ml-for-fluids/ VinuesaLab YouTube channel https://www.youtube.com/@VinuesaLab AI for Fluid Mechanics, Sustainability & XAI — Ricardo Vinuesa https://www.youtube.com/watch?v=TOfwf4ffPnU Modelling and controlling turbulent flows through deep learning — Ricardo Vinuesa https://www.youtube.com/watch?v=0AOY_agZ8WM Chapters 00:00 Podcast intro 03:20 The Evolution of Foundation Models in Fluid Dynamics 10:22 Understanding Explainable AI in Fluid Mechanics 15:34 Challenges in Data Fidelity for Foundation Models 20:29 Machine Learning vs. Reduced-Order Modeling 24:22 The Shift from Turbulence Modeling to Surrogate Models 29:48 Exploring Agentic Systems for Scientific Discovery 37:21 Exploring Latent Representations in Fluid Dynamics 40:40 The Role of AI in Autonomous Discovery 41:57 Bridging Fluid Mechanics and Computer Science 45:28 Data-Driven vs. Physics-Driven Models 51:34 The Role of Academia in AI and Fluid Mechanics 56:27 Optimization and Control in Machine Learning 01:00:28 The Future of AI in Fluid Dynamics: Beyond ChatGPT