The Neil Ashton Podcast

In this episode, Professor Paola Cinnella - Professor of Fluid Mechanics at Sorbonne University and Director of the Sorbonne Cluster for Artificial Intelligence (SCAI) - joins Neil to discuss her path from classical fluid mechanics and high-order numerical methods into uncertainty quantification, Bayesian methods, data-driven turbulence modeling and AI for Science.Paola has built a career at the intersection of CFD, compressible and turbulent flows, dense gas dynamics, uncertainty quantification, robust optimization and machine learning. We discuss academic careers, dense gases, RANS uncertainty, AirfRANS, surrogate modeling, scientific publishing, education in the age of AI, and the idea of the "centaur scientist".Key topicsFluid mechanics, CFD and high-order schemesDense gases, real-gas effects and expansion shockwavesUncertainty quantification and Bayesian methodsRANS turbulence-model uncertaintyAirfRANS and CFD datasets for machine learningTurbulence modeling vs surrogate modelingScientific publishing and ML-for-CFD standardsSCAI and AI for ScienceEducation, ChatGPT and centaur scientistsPapersQuantification of model uncertainty in RANS simulations: A review - Heng Xiao, Paola Cinnellahttps://doi.org/10.1016/j.paerosci.2018.10.001Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression - Martin Schmelzer, Richard P. Dwight, Paola Cinnellahttps://doi.org/10.1007/s10494-019-00089-xBayesian estimates of parameter variability in the k-epsilon turbulence model - W.N. Edeling, P. Cinnella, R.P. Dwight, H. Bijlhttps://doi.org/10.1016/j.jcp.2013.10.027AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionshttps://arxiv.org/abs/2212.07564Data-driven turbulence modeling - Paola Cinnellahttps://arxiv.org/abs/2404.09074Direct numerical simulations of supersonic turbulent channel flows of dense gases - Luca Sciacovelli, Paola Cinnella, Xavier Gloerfelthttps://doi.org/10.1017/jfm.2017.237LinksPaola Cinnella named Director of SCAIhttps://scai.sorbonne-universite.fr/news/paola-cinnella-new-directorSCAIhttps://scai.sorbonne-universite.fr/Paola Cinnella - HAL publicationshttps://cv.hal.science/paola-cinnellaPaola Cinnella - Google Scholarhttps://scholar.google.com/citations?hl=fr&user=wBRA0JAAAAAJERCOFTAC SIG 54 - Machine Learning for Fluid Dynamicshttps://www.ercoftac.org/special_interest_groups/54-machine-learning-for-fluid-dynamics/master-of-science-internships/Chapters00:00 Podcast intro00:39 Introducing Prof. Paola Cinnella03:28 Conversation begins03:56 How Paola found fluid mechanics07:09 Moving from Italy to France08:37 High-order schemes and compressible flows09:30 Building an academic career12:06 Dense gases and uncertainty quantification15:16 Expansion shockwaves and real-gas effects19:17 Returning to Paris and academic mobility24:52 Academia, passion and persistence27:51 Bayesian methods and turbulence uncertainty30:47 Learning statistics across disciplines33:07 LearnFluidS, AirfRANS and CFD datasets36:33 Skepticism and physics in ML turbulence modeling40:41 Could ML lead to a universal turbulence model?42:59 Turbulence models, surrogate models and RANS45:03 Why LES alone cannot solve optimization47:15 Multi-fidelity modeling49:08 What Computers & Fluids looks for in ML-for-CFD papers54:05 CFD metrics vs machine-learning metrics57:13 Overselling, publication pressure and quality62:22 SCAI and AI for Science66:07 Cross-disciplinary AI for Science69:26 Education in the AI era72:44 Critical thinking and AI outputs78:15 AI as a companion, not a replacement81:42 AlphaFold and the future of discovery83:43 Training centaur scientists85:11 Closing thoughts

In this episode, Professor Ricardo Vinuesa - Associate Chair for Research and Associate Professor of Aerospace Engineering at the University of Michigan - explores with Neil one of the biggest questions in modern fluid mechanics: can AI help us move beyond faster CFD and toward genuine autonomous scientific discovery? Drawing on his work at the intersection of turbulence, machine learning, explainable AI, reduced-order modeling, and flow control, Neil and Prof. Vineusa discusses the promise and limits of foundation models for fluids, why the right latent representations may matter more than simply scaling data, and how agentic AI systems could uncover physical mechanisms that humans might otherwise miss.Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations — Abhijeet Vishwasrao et al.
https://arxiv.org/abs/2604.09584
The episode’s most direct follow-up: multi-agent LLMs and latent foundation models autonomously explore flow physics in a tandem-cylinder setup.

Enhancing computational fluid dynamics with machine learning — Ricardo Vinuesa, Steven L. Brunton
https://doi.org/10.1038/s43588-022-00264-7
A concise roadmap for useful ML in CFD, from faster simulations and turbulence modelling to 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
Uses explainable AI to identify flow structures that matter for prediction and control, not just visually striking turbulence features.

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
Shows how disentangled latent spaces, autoencoders, and transformers can support interpretable reduced-order models of nonlinear flows.

Improving turbulence control through explainable deep learning — Miguel Beneitez et al.
https://arxiv.org/abs/2504.02354
Links explainable AI with deep reinforcement learning to target turbulence-sustaining mechanisms, with relevance for flow control, drag reduction, and energy efficiency.LinksVinuesaLabhttps://www.vinuesalab.com/Ricardo Vinuesa — University of Michigan Aerospace Engineeringhttps://aero.engin.umich.edu/people/ricardo-vinuesa/AI and ML for Fluid Dynamics course — Ricardo Vinuesa & Sergio Hoyashttps://www.flowthermolab.com/courses/ai-ml-for-fluids/VinuesaLab YouTube channelhttps://www.youtube.com/@VinuesaLabAI for Fluid Mechanics, Sustainability & XAI — Ricardo Vinuesahttps://www.youtube.com/watch?v=TOfwf4ffPnURicardo Vinuesa — Modelling and controlling turbulent flows through deep learninghttps://www.youtube.com/watch?v=0AOY_agZ8WMChapters00:00 Podcast Intro03:20 The Evolution of Foundation Models in Fluid Dynamics10:22 Understanding Explainable AI in Fluid Mechanics15:34 Challenges in Data Fidelity for Foundation Models20:29 Machine Learning vs. Reduced Order Modeling24:22 The Shift in Focus: Turbulence Modeling to Surrogate Models29:48 Exploring Agentic Systems for Scientific Discovery37:21 Exploring Latent Representations in Fluid Dynamics40:40 The Role of AI in Autonomous Discovery41:57 Bridging Fluid Mechanics and Computer Science45:28 Data-Driven vs Physics-Driven Models51:34 The Role of Academia in AI and Fluid Mechanics56:27 Optimization and Control in Machine Learning01:00:28 Future of AI in Fluid Dynamics: Beyond ChatGPT

In this in-depth conversation, Professor J. Nathan Kutz — Director of Physics-Informed AI at Autodesk and one of the leading figures in data-driven modeling, dynamical systems, and scientific machine learning — shares his journey from academia to industry and reflects on how AI is reshaping engineering. Known for influential contributions to methods such as Dynamic Mode Decomposition and Sparse Identification of Nonlinear Dynamics, Kutz offers a rare perspective on the evolution of machine learning in the physical sciences, the role of physics in building trustworthy AI systems, and the future of automation, agents, and human expertise in engineering design.Key topicsHistory of machine learning in engineeringDynamic Mode Decomposition (DMD) and Sparse Identification of Nonlinear Dynamics (SINDy)Physics-informed AI and reduced order modelingThe debate between physics-based and data-driven modelsThe future of autonomous agents and their impact on industryPapers

Flower discrimination by pollinators in a dynamic chemical environment — Jeffrey A. Riffell, Eli Shlizerman, Elischa Sanders, Leif Abrell, Billie Medina, Armin J. Hinterwirth, J. Nathan Kutz
https://doi.org/10.1126/science.1251041
Nathan’s early move into neuroscience and data-driven biological modeling.

Data assimilation and discrepancy modeling with shallow recurrent decoders — Yuxuan Bao, J. Nathan Kutz
https://arxiv.org/abs/2512.01170
Using ML to close the gap between simulation and reality.

Discovering governing equations from data by sparse identification of nonlinear dynamical systems — Steven L. Brunton, Joshua L. Proctor, J. Nathan Kutz
https://doi.org/10.1073/pnas.1517384113
The foundational paper introducing SINDy.

On Dynamic Mode Decomposition: Theory and Applications — Jonathan H. Tu, Clarence W. Rowley, Dirk M. Luchtenburg, Steven L. Brunton, J. Nathan Kutz
https://doi.org/10.3934/jcd.2014.1.391
A key reference for Dynamic Mode Decomposition.

Data-driven discovery of partial differential equations — Samuel H. Rudy, Steven L. Brunton, Joshua L. Proctor, J. Nathan Kutz
https://doi.org/10.1126/sciadv.1602614
Extends equation discovery to PDEs and physical systems.

Deep learning for universal linear embeddings of nonlinear dynamics — Bethany Lusch, J. Nathan Kutz, Steven L. Brunton
https://doi.org/10.1038/s41467-018-07210-0
Connects deep learning with Koopman theory.

Articraft: An Agentic System for Scalable Articulated 3D Asset Generation — Matt Zhou, Ruining Li, Xiaoyang Lyu, Zhaomou Song, Zhening Huang, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi, Shangzhe Wu
https://arxiv.org/abs/2605.15187
Project page: https://articraft3d.github.io/
A practical example of agentic AI for engineering design.Chapters00:40 Introduction to Episode
05:00 Welcoming Prof Kutz10:34 The Evolution of Data-Driven Modeling16:13 Understanding the SINDy Algorithm and Its Implications22:14 Comparing Reduced Order Modeling and Modern Machine Learning28:29 The Role of Data in Machine Learning and Physics34:23 Challenges in Extrapolation and Real-World Applications40:46 Insights from McLaren and Team Dynamics46:07 The Shift from Academia to Industry48:53 Collaboration and Innovation in Engineering51:57 The Role of Human Expertise in Design54:45 Leveraging AI in Formula One57:32 The Future of AI and Workforce Dynamics59:06 Navigating Career Choices in a Changing Landscape01:03:02 The Evolution of Thought in Engineering01:09:06 Preparing for the Future of Technology01:14:04 Responsible Use of AI in Engineering

In this episode, Neil explores how agents, foundation models, and AI are set to transform the Computer-Aided Engineering (CAE) and Electronic Design Automation (EDA) landscapes. He shares a comprehensive historical perspective and predicts a near-future where AI-driven automation redefines engineering workflows, productivity, and innovation.
Main Topics:
The evolution of simulation codes from the 1960s to modern commercial software
The rise of cloud computing, GPUs, and their impact on CAE and EDA industries
The integration of AI, surrogate modeling, and foundation models into simulation workflows
The emergence of agentic AI systems capable of autonomously performing complex engineering tasks
The strategic responses of major software companies to AI and agent technologies
The potential democratization and automation of engineering design through AI agents
Critical questions on model ownership, transparency, and industry adoption

Timestamps:
00:40 - Introduction: How agents and foundation models will disrupt CAE & EDA
01:40 - Historical overview: From code writing in the 60s to commercial software
03:10 - Growth of aerospace and automotive industry codes and commercialization
04:40 - The impact of HPC, cloud computing, and hardware evolution
06:25 - Rise of cloud SaaS models and "sassification" of simulation tools
07:40 - Big tech entrance: AWS, Microsoft, and Google in CAE & EDA
09:00 - GPU acceleration: Changed landscape in past three to four years
09:10 - The role of AI startups offering surrogate models and real-time simulation
10:40 - Industry consolidation: Mergers and acquisitions among software giants
11:40 - The emergence of foundation models and surrogate systems in simulation
13:00 - The significance of agents: Combining AI, models, and automation
14:10 - Capabilities of autonomous AI agents in complex engineering workflows
15:25 - Practical use cases: Running simulations, setting up experiments, and data analysis
16:40 - How agent-driven automation could democratize engineering expertise
16:10 - Questions about model ownership, open source codes, and licensing
19:40 - The future of AI in engineering: Collaboration, transparency, and scientific rigor
21:25 - Final thoughts: Opportunities, challenges, and the transformative potential of AI

* Please note that this a personal opinion and not that of NVIDIA

In this conversation, Neil Ashton and Prof. Siddhartha Mishra, and Prof. Johannes Brandstetter discuss their recent paper on AI foundation models in computational fluid dynamics (CFD). They explore the backgrounds of the speakers, the journey to writing the paper, the role of AI in CFD, and the challenges of scaling laws and data generation. The discussion also covers model training costs, open questions, and future directions for research in this field.

Fluid Intelligence: A Forward Look on AI Foundation Models in Computational Fluid Dynamics : https://arxiv.org/abs/2511.20455v1