Retour

Explorez tous les épisodes du podcast The Neil Ashton Podcast

Plongez dans la liste complète des épisodes de The Neil Ashton Podcast. Chaque épisode est catalogué accompagné de descriptions détaillées, ce qui facilite la recherche et l'exploration de sujets spécifiques. Suivez tous les épisodes de votre podcast préféré et ne manquez aucun contenu pertinent.

Rows per page:

1–40 of 40

TitreDateDurée
S4 EP5 - Prof. Nils Thuerey on Differentiable Physics and Foundation Models23 Jul 202601:14:47

Differentiable physics, neural emulators and foundation models for PDEs are the focus of this conversation with Professor Nils Thuerey, head of the Physics-based Simulation group at TUM. Neil and Nils discuss PhiFlow, PICT, Tadpole, scalable 3D transformers, online synthetic data, open datasets, world models and agents that call physics simulators.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s4-e5-prof-nils-thuerey-on-differentiable-physics-and-foundation-models/


Topics


Differentiable physics and physics-based deep learning

PhiFlow and differentiable simulation across ML frameworks

When neural emulators can outperform their training data

Foundation models for PDEs and synthetic online training

Scalable 3D transformers and high-resolution simulations

LES, temporal data and correlated CFD datasets

Open-source tools, startups and physics-aware world models

AI agents that call physics simulators


Papers


Neural Emulator Superiority: When Machine Learning for PDEs Surpasses its Training Data

https://arxiv.org/abs/2510.23111


Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning

https://arxiv.org/abs/2605.15284


P3D: Scalable Neural Surrogates for High-Resolution 3D Physics Simulations with Global Context

https://arxiv.org/abs/2509.10186


PICT — A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics

https://arxiv.org/abs/2505.16992


PhiFlow: Differentiable Simulations for PyTorch, TensorFlow and JAX

https://proceedings.mlr.press/v235/holl24a.html


Physics-based Deep Learning

https://arxiv.org/abs/2109.05237


Learning to Control PDEs with Differentiable Physics

https://arxiv.org/abs/2001.07457


Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers

https://arxiv.org/abs/2007.00016


tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow

https://arxiv.org/abs/1801.09710


Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows

https://arxiv.org/abs/1810.08217


WeatherBench: A Benchmark Dataset for Data-Driven Weather Forecasting

https://arxiv.org/abs/2002.00469


SuperWing: A Comprehensive Transonic Wing Dataset for Data-Driven Aerodynamic Design

https://arxiv.org/abs/2512.14397


Links


Nils Thuerey and the Physics-based Simulation group

https://ge.in.tum.de/about/n-thuerey/


Chapters


00:00 Podcast intro

00:39 Introducing Prof. Nils Thuerey

04:13 Conversation begins

05:13 From Computational Numerics to Graphics and Visual Effects

07:17 Physics-Based Deep Learning Before ChatGPT

10:01 CNNs, Graphics and the Move into Engineering Applications

12:37 PhiFlow and Differentiable Physics

14:13 Can Neural Emulators Surpass Their Training Data?

18:00 The Promise and Limits of Foundation Models for PDEs

20:43 Tadpole and Synthetic Online Pre-Training

24:07 From Canonical PDEs to Navier-Stokes and Industrial CFD

26:35 What Do Foundation Models Actually Learn?

28:36 PDE Pre-Training vs. Millions of CFD Simulations

33:08 Scaling 3D Transformers and Training Infrastructure

35:58 Generating and Training on Data in Real Time

38:00 LES, Temporal Data and Turbulence

42:15 Overfitting and Correlated Simulation Data

44:27 Bringing Differentiable Solvers Back into the Loop

45:31 WeatherBench, APEBench and the Value of Benchmarks

47:09 SuperWing, Open Datasets and Commercial Data

51:31 Open Source, Commercial Models and a Technical Oscar

56:17 Academia, Startups and Industry

01:00:55 What Will Change Over the Next Five Years?

01:02:07 World Models and the Need for Physics

01:08:19 Agents, Tool Use and Calling Physics Simulators

01:11:22 Career Advice for AI and Simulation

01:13:54 Closing Thoughts

S4 EP4 - Prof. Paola Cinnella on AI for Science and Fluid Mechanics09 Jul 202601:25:39

RANS uncertainty, data-driven turbulence modeling and AI for Science are the focus of this conversation with Professor Paola Cinnella, Professor of Fluid Mechanics at Sorbonne University and Director of SCAI. Neil and Paola discuss high-order methods, dense gases, Bayesian uncertainty, AirfRANS, surrogate modeling, scientific publishing and education in the AI era.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s4-e4-prof-paola-cinnella-on-ai-for-science-and-fluid-mechanics/


Topics


Fluid mechanics, CFD and high-order schemes

Dense gases, real-gas effects and expansion shockwaves

Uncertainty quantification and Bayesian methods

RANS turbulence-model uncertainty

AirfRANS and CFD datasets for machine learning

Turbulence modeling vs. surrogate modeling

Scientific publishing and ML-for-CFD standards

SCAI and AI for Science

Education, ChatGPT and centaur scientists


Papers


Quantification of model uncertainty in RANS simulations: A review — Heng Xiao, Paola Cinnella

https://doi.org/10.1016/j.paerosci.2018.10.001


Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression — Martin Schmelzer, Richard P. Dwight, Paola Cinnella

https://doi.org/10.1007/s10494-019-00089-x


Bayesian estimates of parameter variability in the k-epsilon turbulence model — W.N. Edeling, P. Cinnella, R.P. Dwight, H. Bijl

https://doi.org/10.1016/j.jcp.2013.10.027


AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions

https://arxiv.org/abs/2212.07564


Data-driven turbulence modeling — Paola Cinnella

https://arxiv.org/abs/2404.09074


Direct numerical simulations of supersonic turbulent channel flows of dense gases — Luca Sciacovelli, Paola Cinnella, Xavier Gloerfelt

https://doi.org/10.1017/jfm.2017.237


Links


Paola Cinnella named Director of SCAI

https://scai.sorbonne-universite.fr/news/paola-cinnella-new-director


SCAI

https://scai.sorbonne-universite.fr/


Paola Cinnella — HAL publications

https://cv.hal.science/paola-cinnella


Paola Cinnella — Google Scholar

https://scholar.google.com/citations?hl=fr&user=wBRA0JAAAAAJ


ERCOFTAC SIG 54 — Machine Learning for Fluid Dynamics

https://www.ercoftac.org/special_interest_groups/54-machine-learning-for-fluid-dynamics/master-of-science-internships/


Chapters


00:00 Podcast intro

00:39 Introducing Prof. Paola Cinnella

03:28 Conversation begins

03:56 How Paola Found Fluid Mechanics

07:09 Moving from Italy to France

08:37 High-Order Schemes and Compressible Flows

09:30 Building an Academic Career

12:06 Dense Gases and Uncertainty Quantification

15:16 Expansion Shockwaves and Real-Gas Effects

19:17 Returning to Paris and Academic Mobility

24:52 Academia, Passion and Persistence

27:51 Bayesian Methods and Turbulence Uncertainty

30:47 Learning Statistics Across Disciplines

33:07 LearnFluidS, AirfRANS and CFD Datasets

36:33 Skepticism and Physics in ML Turbulence Modeling

40:41 Could ML Lead to a Universal Turbulence Model?

42:59 Turbulence Models, Surrogate Models and RANS

45:03 Why LES Alone Cannot Solve Optimization

47:15 Multi-Fidelity Modeling

49:08 What Computers & Fluids Looks for in ML-for-CFD Papers

54:05 CFD Metrics vs. Machine-Learning Metrics

57:13 Overselling, Publication Pressure and Quality

01:02:22 SCAI and AI for Science

01:06:07 Cross-Disciplinary AI for Science

01:09:26 Education in the AI Era

01:12:44 Critical Thinking and AI Outputs

01:18:15 AI as a Companion, Not a Replacement

01:21:42 AlphaFold and the Future of Discovery

01:23:43 Training Centaur Scientists

01:25:11 Closing Thoughts

S3 EP4 - 5 tips for CAE engineers in the era of AI02 Sep 202500:23:48

In this episode of the Neil Ashton podcast, Neil discusses the impact of AI on CAE engineering, providing five essential tips for engineers to thrive in this evolving landscape. The conversation covers the importance of maintaining an open mind, continuous education, and preparing for AI physics applications. It also delves into the build vs. buy dilemma for AI solutions and the emerging concept of agentic AI, which promises to revolutionize engineering practices.


Chapters


00:00 Introduction to the Podcast and AI in Engineering

01:03 Five Tips for CAE Engineers in the Era of AI

01:24 1: Keeping an Open Mind 

07:39 2: Understanding AI Physics and Its Applications

13:30 3: Preparing for AI Implementation in Engineering

18:54 4: The Build vs. Buy Dilemma in AI Solutions

22:20 5: The Future of Agentic AI in Engineering


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e4-five-tips-for-cae-engineers-in-the-era-of-ai/

S3 EP3 - Professor Johannes Brandstetter on AI for Computational Fluid Dynamics19 Aug 202501:18:02

In this conversation, Neil Ashton interviews Prof. Johannes Brandstetter, a physicist turned machine learning expert, about his journey from academia to industry, focusing on the application of machine learning in engineering and computational fluid dynamics (CFD). They discuss the Aurora project, the challenges of integrating machine learning with engineering, and the importance of data in training models. Johannes shares insights on the use of transformers in modeling, the significance of resolution independence, and the role of open-source practices in advancing the field. The conversation also touches on the challenges of founding a startup and the need for multidisciplinary collaboration in tackling complex engineering problems.

Links: 

Github: https://brandstetter-johannes.github.io
Emmi AI: https://www.emmi.ai
Google scholar: https://scholar.google.com/citations?user=KiRvOHcAAAAJ&hl=de

AB-UPT transform paper: https://arxiv.org/abs/2502.09692

Chapters

00:00 Introduction to Johannes Brandstetter
07:10 The Aurora Project and Key Learnings
11:15 Machine Learning in Engineering and CFD
17:19 Challenges with Mesh Graph Networks
20:16 Transformers in Physics Modeling
31:14 Tokenization in CFD with Transformers
39:58 Challenges in High-Dimensional Meshes
41:08 Inference Time and Mesh Generation
41:36 Neural Operators and CAD Geometry
45:59 Anchor Tokens and Scaling in CFD
48:40 Data Dependency and Multi-Fidelity Models
50:32 The Role of Physics in Machine Learning
54:28 Temporal Modeling in Engineering Simulations
56:58 Learning from Temporal Dynamics
1:00:58 Stability in Rollout Predictions
1:03:48 Multidisciplinary Approaches in Engineering
1:05:18 The Startup Journey and Lessons Learned


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e3-prof-johannes-brandstetter-on-ai-for-computational-fluid-dynamics/

S3 EP2 - Prof. Russell Cummings - World leader in Aerospace Engineering and Hypersonics05 Aug 202501:43:14

In this episode of the Neil Ashton podcast, Professor Russell Cummings shares his extensive journey through the fields of aerodynamics, computational fluid dynamics and hypersonics. He discusses his early inspirations, his early days at University and the Hughes Aircraft Company - a key time during this life. He also talks about  the cyclical nature of hypersonics research, and the challenges faced in computational fluid dynamics (CFD). Prof. Cummings emphasizes the importance of perseverance in engineering careers and the need for collaboration between experimental and computational methods. He also shares insights on the role of AI in hypersonics and offers valuable advice for aspiring engineers.

Prof. Russ Cummings graduated from California Polytechnic State University (Cal Poly) with a B.S. and M.S. in Aeronautical Engineering, before receiving his Ph.D. in Aerospace Engineering from the University of Southern California; he also received a B.A. in music from Cal Poly. He is currently Professor of Aeronautics at the U.S. Air Force Academy and Director of the Hypersonic Vehicle Simulation Institute. Prior to this he was Professor of Aerospace Engineering at Cal Poly, where he also served as department chairman for four years. He also worked at Hughes Aircraft Company, and completed a National Research Council postdoctoral research fellowship at NASA Ames Research Center, working on the computation of high angle-of-attack flowfields. He is a Fellow of the Royal Aeronautical Society and the American Institute of Aeronautics and Astronautics.

Distribution Statement A: approved for public release, PA# USAFA-DF-2025-652. The views expressed in this interview are those of the author and do not necessarily reflect the official policy or position of the United States Air Force Academy, the Air Force, the Department of Defense, or the U.S. Government.

Links

Aerodynamics for engineers: https://www.cambridge.org/us/universitypress/subjects/engineering/aerospace-engineering/aerodynamics-engineers-7th-edition?format=HB&isbn=9781009501309
RAeS Lanchester Named Lecture 2024: Frederick W. Lanchester and 'Aerodynamics' https://www.youtube.com/watch?app=desktop&v=lApNzYaZOmk&t=884s 
NASA at 50 (Prof Cummings is in the picture): https://images.nasa.gov/details/ARC-1989-AC89-0276-6 

Chapters

00:00 Introduction to the Podcast and Guest
04:56 Professor Russell Cummings: A Journey Through Engineering
31:14 The Evolution of Hypersonics Research
58:26 The Role of AI in Hypersonics and CFD
01:37:55 Advice for Aspiring Engineers


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e2-prof-russell-cummings-aerospace-engineering-and-hypersonics/

S3 EP1 - Prof. Mike Giles - A CFD and Computational Finance Pioneer21 Jul 202502:07:11

In this episode of the Neil Ashton podcast, Professor Mike Giles shares his extensive journey through the fields of computational fluid dynamics (CFD), computational finance and HPC. He discusses his early academic influences, his early days at Cambridge, internships at Rolls-Royce, his transition to MIT and Oxford where he made significant contributions to high-performance computing and numerical analysis. The conversation highlights his hands-on approach to research and teaching, as well as his pioneering work in Monte Carlo methods and GPU computing. This conversation explores the journey of a mathematician and engineer from MIT to Rolls-Royce and then to Oxford, highlighting the evolution of computational engineering, the development of the Hydra code, and the transition from CFD to financial applications.  In this conversation, the speaker reflects on their journey through burnout, career transitions, and the evolution of their work in computational finance and numerical analysis. They discuss the challenges of managing large software projects, the shift from Hydra code development to finance, and the integration of advanced methodologies in their work. The conversation also touches on the role of high-performance computing, the impact of AI on research, and advice for the next generation of students pursuing careers in mathematics and programming.

Links:
https://people.maths.ox.ac.uk/gilesm/


Chapters

00:00 Introduction 
06:25 Professor Mike Giles: A Journey Through CFD and Finance
17:30 Early Academic Influences and Career Path
29:34 Transition to MIT and Early Research
40:01 High-Performance Computing and Its Impact
41:30 Navigating Between MIT and Rolls-Royce
44:54 The Evolution of Research at MIT
48:47 Transitioning to Oxford and the Role of Rolls-Royce
51:07 The Genesis of the Hydra Code
01:00:47 The Role of Conferences in Engineering
01:10:58 The Shift from CFD to Financial Applications
01:21:30 Navigating Burnout and Career Transitions
01:24:04 Shifting Focus: From Hydrocode to Computational Finance
01:29:30 Bridging Mathematics and Finance: Methodologies and Techniques
01:35:09 The Role of High-Performance Computing in Modern Research
01:39:20 AI's Impact on Research and Future Directions
01:54:00 Advice for the Next Generation: Pursuing Passion and Skills


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e1-prof-mike-giles-a-cfd-and-computational-finance-pioneer/

S2 EP11 - Foundational AI Models for Fluids24 Apr 202500:22:33

In this episode of the Neil Ashton podcast, the discussion revolves around foundational models in fluid dynamics, particularly in the context of computational fluid dynamics (CFD). Neil shares insights from a recent panel discussion and explores the potential of AI in predicting fluid behavior. He discusses the evolution of AI in CFD, the challenges of data availability, and the differing adoption rates between industries. The episode concludes with predictions about the future of foundational models and their impact on the engineering landscape.

Chapters

00:00 Introduction to the Podcast and Topic
01:09 Foundational Models in Fluid Dynamics
10:09 The Evolution of AI in CFD
19:52 Future Predictions and Industry Dynamics


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e11-foundational-ai-models-for-fluids/

S2 EP10 - Dr. Kurt Bergin-Taylor, Head of Innovation - Tudor Pro Cycling10 Mar 202501:01:05

In this episode of the Neil Ashton podcast,  Neil discusses the intersection of cycling and engineering with Kurt Bergin-Taylor, head of innovation at Tudor Pro Cycling. They explore how technology and science are transforming cycling into a more competitive and innovative sport, akin to Formula One. The conversation covers various aspects of cycling, including the importance of aerodynamics, nutrition, and the holistic approach to rider performance. Kurt shares insights from his academic background and experiences in professional cycling, emphasizing the need for tailored training and the integration of technology in enhancing performance. They discuss the future of cycling innovation, emphasizing the importance of individualization in gear, collaborative relationships with partners, and the evolving mindset of young cyclists. Kurt highlights the significance of data and AI in optimizing performance and strategies in cycling, while also addressing the need for viewer engagement in the sport. Finally Kurt shares valuable advice for aspiring engineers looking to enter the cycling industry, stressing the importance of mentorship and practical experience.

Chapters

00:00 Introduction to the Podcast and Themes
04:55 Kurt Bergin-Taylor: Background and Role at Tudor Pro Cycling
10:08 The Structure and Dynamics of a Pro Cycling Team
12:59 Innovation in Cycling: Aerodynamics, Thermal Management, and Safety
19:14 Nutrition, Training, and Performance in Cycling
29:18 Future Innovations in Cycling Equipment and Systems
30:42 Understanding Individualization in Cycling Gear
34:30 Collaborative Innovation in Cycling Equipment
38:20 The Evolving Mindset of Young Cyclists
42:28 Enhancing Viewer Engagement in Cycling
46:24 The Future of Data and AI in Cycling
50:05 Advice for Aspiring Engineers in Cycling

Takeaways

- Cycling is increasingly influenced by technology and engineering.
- Tudor Pro Cycling is focused on long-term performance and innovation.
- Aerodynamics plays a crucial role in cycling performance.
- Thermal management is essential for riders in extreme conditions.
- Nutrition has dramatically improved in cycling over the last decade.
- Training methodologies must be tailored to individual riders.
- The relationship between power output and speed is complex.
- Safety innovations are critical as speeds increase in cycling.
- Understanding the whole system of rider and equipment is vital.
- Professional cyclists have different recovery capabilities compared to amateurs. Individualization in cycling gear is crucial for performance.
- Collaborative innovation with partners enhances product development.
- Young cyclists are more educated but sometimes overlook tactical aspects.
- Data-driven insights are essential for optimizing race strategies.
- Viewer engagement can be improved through real-time data sharing.
- AI and machine learning are emerging tools in cycling optimization.
- Mentorship is vital for aspiring professionals in the cycling industry.
- Practical experience and initiative can open doors in professional sports.
- Cycling offers a holistic approach to engineering and performance.
- The cycling industry is growing, providing more opportunities for engineers.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e10-dr-kurt-bergin-taylor-head-of-innovation-tudor-pro-cycling/

S2, EP9 - New Job Update! (and a small apology..)21 Feb 202500:08:46

A short episode to give a brief update on what I've been doing and to say sorry for not putting out episodes recently. I've joined NVIIDA as a Distinguished CAE Architect and have been rather busy! New episodes will be coming soon! Listen to the episode to learn more. 


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e9-new-job-update/

S2, EP8 - Neil Ashton - Career advice for Engineers09 Jan 202501:00:09

In this episode of the Neil Ashton podcast, Neil discusses career advice for aspiring engineers, focusing on the differences between various types of companies, job roles, and the growing importance of software skills in the engineering field. The conversation highlights the pros and cons of working in large enterprises, startups, and consulting firms, as well as the diverse career paths available beyond traditional engineering roles. In this conversation, Neil discusses the evolving landscape of engineering careers, particularly focusing on the increasing relevance of software development and the tech sector. He highlights the diverse career paths available within tech, including software development, product management, and solution architecture, as well as the growing importance of AI in engineering. Neil emphasizes the opportunities for engineers to transition into tech roles and the need for a strong understanding of the tech ecosystem to navigate career decisions effectively.

Chapters

00:00 Introduction to Engineering Careers
03:01 Exploring Company Types in Engineering
06:05 Understanding Job Roles in Engineering
09:00 The Shift Towards Software in Engineering
11:52 Diverse Career Paths Beyond Traditional Engineering
14:47 The Role of Consulting in Engineering
18:03 Navigating the Job Market in Engineering
20:57 The Importance of Software Skills in Engineering
24:03 Conclusion and Future Trends in Engineering Careers
30:08 The Rise of Software Development in Engineering
31:59 The Tech Sector's Growing Relevance to Engineers
36:41 Career Paths in Tech: Software Development and Management
44:27 Understanding Product Management in Tech
48:15 The Role of Solution Architects in Tech
52:04 Consulting and Support Roles in Tech
55:54 AI's Impact on Engineering and Software Development

#careers #engineering #tech #sde #amazon #aws #google #jobs


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e8-neil-ashton-career-advice-for-engineers/

S2, EP7 - Prof. Michael Mahoney - Perspectives on AI4Science26 Dec 202401:16:44

In this episode of the Neil Ashton podcast, Professor Michael Mahoney discusses the intersection of machine learning, mathematics, and computer science. The conversation covers topics such as randomized linear algebra, foundational models for science, and the debate between physics-informed and data-driven approaches. Prof. Mahoney shares insights on the relevance of his research, the potential of using randomness in algorithms, and the evolving landscape of machine learning in scientific disciplines. He also discusses the evolution and practical applications of randomized linear algebra in machine learning, emphasizing the importance of randomness and data availability. He explores the tension between traditional scientific methods and modern machine learning approaches, highlighting the need for collaboration across disciplines. Prof Mahoney also addresses the challenges of data licensing and the commercial viability of machine learning solutions, offering insights for aspiring researchers in the field.

Prof. Mahoney website: https://www.stat.berkeley.edu/~mmahoney/
Google scholar: https://scholar.google.com/citations?user=QXyvv94AAAAJ&hl=en
Youtube version: https://youtu.be/lk4lvKQsqWU

Chapters

00:00 Introduction to the Podcast and Guest
05:51 Understanding Randomized Linear Algebra
19:09 Foundational Models for Science
32:29 Physics-Informed vs Data-Driven Approaches
38:36 The Practical Application of Randomized Linear Algebra
39:32 Creative Destruction in Linear Algebra and Machine Learning
40:32 The Role of Randomness in Scientific Machine Learning
41:56 Identifying Commonalities Across Scientific Domains
42:52 The Horizontal vs. Vertical Application of Machine Learning
44:19 The Challenge of Common Architectures in Science
46:31 Data Availability and Licensing Issues
50:04 The Future of Foundation Models in Science
54:21 The Commercial Viability of Machine Learning Solutions
58:05 Emerging Opportunities in Scientific Machine Learning
01:00:24 Navigating Academia and Industry in Machine Learning
01:11:15 Advice for Aspiring Scientific Machine Learning Researchers

Keywords

machine learning, randomized linear algebra, foundational models, physics-informed neural networks, data-driven science, computational efficiency, academic advice, numerical methods, AI in science, engineering, Randomized Linear Algebra, Machine Learning, Scientific Computing, Data Availability, Foundation Models, Academia, Industry, Research, Algorithms, Innovation


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e7-prof-michael-mahoney-perspectives-on-ai-for-science/

S2, EP6 - Dr. Prith Banerjee - ANSYS CTO16 Dec 202401:10:37

In this episode of the Neil Ashton Podcast, Dr. Prith Banerjee, CTO of Ansys, shares his extensive journey from academia to the corporate world, discussing the interplay between academia and industry, the role of startups in innovation, and the transformative potential of AI and ML in simulation. He emphasizes the importance of solving real-world problems and the need for collaboration between academia, startups, and large corporations to foster disruptive innovation. He discusses innovative business models for data sharing, the intersection of data-driven and physics-informed approaches, the role of open source in AI innovation, the potential of foundational models in computer-aided engineering (CAE), the future of quantum computing in simulation, and offers advice for aspiring innovators and entrepreneurs. He emphasizes the importance of collaboration, data governance, and the need for interdisciplinary approaches to solve complex problems in engineering and technology.

Dr. Banerjee's book - The Innovation factory: https://www.amazon.com/Innovation-Factory-Prith-Banerjee-PH/dp/B0B7LZPDZW

Youtube version of this episode: https://youtu.be/9Ic5xgJt6BQ

Chapters

00:00 Introduction to the Podcast and Guest
05:18 Dr. Prith Banerjee's Journey: From Academia to CTO
09:10 The Role of Academia, Startups, and Industry
17:22 Advice for Startups: Motivation and Market Sizing
24:04 The Impact of AI and ML on Simulation
35:07 Future of AI in Physics and Simulation
36:10 The Power of Data in AI Models
40:33 Incentivizing Data Sharing for Better Models
42:55 Physics-Driven vs Data-Driven Approaches
47:30 The Role of Open Source in AI Innovation
52:06 Foundational Models and Simulation Data
58:22 The Future of CAE and Quantum Computing
01:06:29 Advice for Aspiring Innovators

Keywords

Neil Ashton, Prith Banerjee, CAE, AI, ML, simulation, academia, startups, industry, innovation, AI, data sharing, physics-driven, open source, foundational models, quantum computing, CAE, simulation, innovation, engineering


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e6-dr-prith-banerjee-ansys-cto/

S4 EP3 - Prof. Ricardo Vinuesa on AI for Fluid Mechanics25 Jun 202601:05:48

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

S2, EP5 - NASA's Quesst for Quieter Supersonic Flight with Peter Coen04 Dec 202401:15:14

In this episode of the Neil Ashton podcast, Peter Coen from NASA discusses the evolution and future of supersonic travel, focusing on the challenges faced by the Concorde, the technological hurdles of modern supersonic aircraft, and the innovative NASA Quesst mission (and X-59 demonstrator) that aims to provide crucial data to rewrite the aviation noise regulations. The conversation delves into the history of supersonic flight, the impact of sonic booms, and the regulatory landscape that will shape the future of aviation. In this conversation, Peter discusses the complexities of supersonic flight, focusing on the physics of shockwaves, innovative design strategies to mitigate sonic booms, and advancements in pilot visibility technology. He emphasizes the importance of human factors in aircraft design and the role of simulation in the development process. The discussion also covers the challenges of engine technology for commercial supersonic travel, the potential for hypersonic passenger travel, and the future of battery technology in aviation. Finally, Peter offers career advice for aspiring professionals in the aeronautics field.

Links
NASA Quesst mission: https://www.nasa.gov/mission/quesst/
AIAA Low-Boom Prediction Workshop: https://lbpw.larc.nasa.gov
X-59 (Lockheed Martin website): https://www.lockheedmartin.com/en-us/products/x-59-quiet-supersonic.html

Chapters

00:00 Introduction to Supersonic Travel
04:05 The History of Supersonic Flight
09:56 Challenges Faced by Concorde
16:02 Technological Challenges of Supersonic Travel
25:48 NASA's X-59 and the Quest Mission
33:45 Future of Supersonic Travel and Regulations
38:04 Understanding Shockwaves in Supersonic Flight
40:02 Design Innovations for Sonic Boom Reduction
43:16 Advancements in Pilot Visibility Technology
46:27 Human Factors in Aircraft Design
48:23 The Role of Simulation in Aircraft Development
51:42 Engine Noise and Its Impact on Supersonic Travel
54:31 The Future of Commercial Supersonic Travel
57:13 Challenges in Engine Technology for Supersonic Aircraft
01:00:17 The Intersection of Military and Supersonic Travel
01:02:09 Exploring Hypersonic Passenger Travel
01:06:39 The Future of Battery Technology in Aviation
01:09:09 Career Advice for Aspiring Aeronautics Professionals

Keywords

supersonic travel, Concorde, NASA, X-59, sonic boom, aviation technology, hypersonic flight, aerospace engineering, aircraft design, noise regulations, supersonic flight, sonic boom, aircraft design, pilot technology, simulation, engine noise, commercial aviation, hypersonic travel, battery technology, aeronautics careers, Peter Coen


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e5-nasa-s-quesst-for-quieter-supersonic-flight-with-peter-coen/

S2, EP4 - Celebrating Prof. Antony Jameson: A CFD Pioneer20 Nov 202402:11:34

In this episode of the Neil Ashton podcast, we celebrate the life and contributions of Professor Antony Jameson, a pioneer in Computational Fluid Dynamics (CFD). The conversation explores his early influences, academic journey, and significant contributions to aerodynamics and engineering. Professor Jameson shares insights from his career in both academia and industry, highlighting pivotal moments that shaped his work in CFD and transonic flow. Prof. Jameson discusses his journey through the complexities of numerical methods for fluid flow, his transition from industry to academia, the development of influential flow codes, and the evolution of computational fluid dynamics (CFD). He reflects on the challenges of teaching, the impact of his work on the aerospace industry, and the commercialization of CFD technologies. In this conversation, he shares his journey from academia to industry, discussing the challenges and successes he faced in the field of aerodynamics and computational fluid dynamics. He reflects on the importance of innovation, the impact of industry experience on academic research, and offers valuable advice for aspiring professionals in aeronautics. The discussion also touches on the evolution of computational power and the role of machine learning in the field.

Chapters

00:00 Introduction to Computational Fluid Dynamics and Professor Jameson
05:02 Professor Jameson's Early Life and Influences
20:00 Academic Journey and Contributions to Aerodynamics
34:50 Career in Industry and Transition to Academia
48:52 Pivotal Moments in Computational Fluid Dynamics
50:19 Navigating Numerical Methods for Fluid Flow
57:02 Transitioning to Academia and Teaching Challenges
01:06:25 Developing Flow Codes FLO & SYN and Their Impact
01:12:21 The Evolution of Computational Fluid Dynamics
01:19:10 Commercialization and the Future of CFD
01:30:34 Journey to Success: From Code to Commercialization
01:37:02 Innovations in Aerodynamics: Control Theory and Design
01:43:06 The Impact of Industry Experience on Academic Research
01:51:24 The Evolution of Computational Power in Aerodynamics
02:01:29 Advice for Aspiring Aeronautics Professionals

Summary of key work: 

(see http://aero-comlab.stanford.edu/jameson/publication_list.html for the publication number) 
Th first work that had a strong impact on the aircraft industry was Flo22. The numerical algorithm used in Flo22 is analyzed in detail in Publication 31, Iterative solution of transonic flows.
The next work that had a worldwide impact was the JST scheme in 1981. The AIAA Paper 81-1259 (publication 67) has more than 6000 citations on Google Scholar. Prof. Jameson gave two other presentations a few months earlier which describe the numerical method in more detail. These are publications 63 and 65. More recently he gave a history of the JST scheme and its further development in publication 456, which also gives a detailed discussion of the multigrid scheme which was  first  described in publication 78.
The Airplane Code described in AIAA Paper 86-0103 (publication 104) was the first code that could solve the Euler equations for a complete aircraft, the culmination of 15 years of his efforts to calculate transonic flows for progressively more complex configurations and with more complete mathematical models. It was never published as a journal article. The design of algorithms for unstructured grids is comprehensively discussed in his book (publication 500).
He proposed the idea of using control theory for aerodynamic shape optimization in 1988 in publication 127, and its further development for transonic flows modeled by the RANS equations is described publications 222 and 229. 

Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e4-celebrating-prof-antony-jameson-a-cfd-pioneer/

S2, EP3 - Dr Michael Hutchinson - Cycling aerodynamics and the lifelong pursuit to go faster08 Nov 202401:38:00

In this episode of the Neil Ashton podcast, we delve into the fascinating world of cycling, focusing on the critical role of aerodynamics and the evolution of training techniques. Featuring Dr. Michael Hutchinson, a former top-level cyclist and expert in cycling aerodynamics, the conversation explores Dr. Hutch's journey from competitive cycling to becoming a prominent figure in cycling media. The discussion highlights the importance of power meters in training, the cultural landscape of cycling in the UK, and the technical innovations that have transformed the sport. In this conversation, we discuss the evolution of cycling performance, focusing on the impact of training, nutrition, and equipment. We highlight the importance of training less, the advancements in nutrition that allow cyclists to perform better, and the diverse training approaches that exist among athletes. The conversation also touches on the professionalism of cyclists, the rise of women's cycling, and the significant role of aerodynamics and equipment in enhancing performance. In this conversation, Neil and Dr Hutch discusses the intricate balance between power and aerodynamics in cycling, the evolution of rider trust in aerodynamic advice, and the significant impact of wind tunnels on performance. He explores the challenges of wind tunnel testing versus real-world validation, the role of computational fluid dynamics (CFD) in cycling aerodynamics, and the regulatory challenges that arise with advancing technology. 

Dr Hutch X handle: https://x.com/Doctor_Hutch 
Faster: The Obsession, Science and Luck Behind the World's Fastest Cyclists: https://www.amazon.co.uk/Faster-Obsession-Science-Fastest-Cyclists/dp/1408843757 


Chapters

00:00 Introduction to the Podcast and Cycling Passion
02:57 The Intersection of Cycling and Aerodynamics
06:02 Dr. Hutch's Journey into Competitive Cycling
08:57 The Evolution of Aerodynamics in Cycling
12:13 The Role of Power Meters in Cycling Performance
15:01 Training Techniques and the Shift to Power Metrics
17:58 Transitioning from Cycling to Media and Writing
20:50 The Cultural Landscape of Cycling in the UK
24:13 Technical Innovations and Personal Experiments in Aerodynamics
27:01 The Impact of Power Meters on Training and Performance
32:51 The Power of Training Less
34:15 Evolution of Cycling Performance
38:30 Nutrition: The Game Changer
39:47 Diverse Training Approaches
42:31 The Professionalism of Cyclists
48:11 The Rise of Women's Cycling
50:33 Aerodynamics: The Key to Speed
56:06 The Impact of Equipment on Performance
01:05:08 Balancing Power and Aerodynamics in Cycling
01:07:05 The Evolution of Rider Trust in Aerodynamics
01:10:55 The Impact of Wind Tunnels on Cycling Performance
01:12:21 Challenges of Wind Tunnel Testing and Real-World Validation
01:20:26 The Role of CFD in Cycling Aerodynamics
01:25:31 Regulatory Challenges in Cycling Technology
01:31:08 The Future of Cycling: Balancing Technology and Tradition

Keywords

cycling, aerodynamics, Dr. Hutch, power meters, training techniques, cycling culture, performance metrics, cycling history, competitive cycling, cycling media, cycling, training, nutrition, performance, aerodynamics, women's cycling, professional cycling, power meter, skin suits, coaching, cycling, aerodynamics, wind tunnels, biomechanics, CFD, technology, performance, regulations, rider trust, power


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e3-dr-michael-hutchinson-cycling-aerodynamics-and-the-lifelong-pursuit-to-go-faster/

S2, EP2: The Future of CFD: 5 Key Trends to Watch24 Oct 202400:46:26

In this episode, Neil discusses five key trends in Computational Fluid Dynamics (CFD) that are shaping the industry now and in the coming years. He emphasizes the growing importance of GPUs, the integration of AI and machine learning, the shift towards cloud computing, and the potential for mergers and acquisitions in the CFD space. Each trend is explored in detail, highlighting its implications for accuracy, efficiency, and the future of simulation technologies.

Takeaways

GPUs are becoming the primary computing platform for CFD.
AI and ML are driving advancements in CFD methodologies.
Cloud computing is essential for accessing high-performance resources.
The CFD industry is experiencing a shift towards digital certification.
Startups are emerging, focusing on innovative CFD solutions.
Mergers and acquisitions are likely to increase in the CFD market.
Higher fidelity simulations are becoming more feasible with new technologies.
The integration of AI could lead to real-time CFD capabilities.
Cost efficiency is a major driver for adopting new technologies.
The CFD landscape is evolving rapidly, with significant opportunities ahead.

Keywords

CFD, GPUs, AI, Machine Learning, Cloud Computing, Trends, Digital Certification, Mergers, Acquisitions, Simulation

Chapters

00:00 Introduction to CFD Trends
02:04 The Rise of GPUs in CFD
14:06 The Impact of AI and Machine Learning
29:39 The Shift to Cloud Computing
38:41 Digital certification: Higher-fidelity methods
43:00 Future of CFD: Mergers and Innovations


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e2-the-future-of-cfd-five-key-trends-to-watch/

S2, EP1 - Dr. Nikolas Tombazis - From Poacher to Gamekeeper, Defining the future of Formula 110 Oct 202401:12:15

In this episode of the Neil Ashton podcast, Nikolas Tombazis discusses his journey into engineering and Formula One, starting from his passion for mathematics, physics, and design. He shares how his childhood dream of designing Formula One cars led him to pursue engineering. Tombazis also talks about his experience at Cambridge University and the freedom he enjoyed during his university years. He then delves into his decision to pursue a PhD in experimental aerodynamics and the valuable skills he gained from his research. Tombazis reflects on the challenges and responsibilities of being a chief aerodynamicist in Formula One, as well as the evolving role of CFD in the industry. The conversation explores the advancements in wind tunnel technology and computational fluid dynamics (CFD) in Formula One. It discusses the role of CFD as a design tool and the potential for it to become the predominant tool in the future. The conversation also touches on the balance between the technical aspects of the sport and the entertainment value for fans. The importance of teamwork, leadership, and culture in Formula One teams is highlighted, as well as the challenges of maintaining success and avoiding complacency. The conversation concludes with advice for aspiring Formula One professionals, emphasizing the value of a broad skill set and the potential for Formula One as a stepping stone to other industries.

Chapters

00:00 Introduction to the Podcast and Season Two
03:38 Nikolas Tombazis: A Key Figure in Formula One
04:56 Early Influences and Passion for Engineering
08:52 The Journey Through Cambridge and PhD Studies
12:57 Entering Formula One: The Path to Benetton
18:25 The Evolution of Aerodynamics in Formula One
24:06 The Role of CFD and Wind Tunnel Technology
38:53 Balancing Technology and Entertainment in F1
44:47 The Future of AI in Formula One
54:56 Understanding Team Dynamics and Performance Variability
01:03:44 Advice for Aspiring Engineers in Formula One


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s2-e1-dr-nikolas-tombazis-defining-the-future-of-formula-1/

S1, EP14 - Season 1 Recap and what's next08 Aug 202400:20:09

The first season of the Neil Ashton podcast comes to a close with a recap of the episodes and a glimpse into what's to come in the next season. Look out for Season 2 in September with lots more great guests and discussion on hypersonics, CFD, Formula One, cycling,  space exploration and more!


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e14-season-1-recap-and-what-comes-next/

S1, EP13 - Prof. Anima Anandkumar - The future of AI+Science30 Jul 202401:06:56

Professor Anima Anandkumar is one of the world’s leading scientists in AI and machine learning, with more than 30,000 citations, an h-index of 80 and landmark papers including FourCastNet, which received worldwide coverage for demonstrating how AI can accelerate weather prediction. She is the Bren Professor at Caltech, leads the AI+Science Lab and previously served as Senior Director of AI Research at NVIDIA.


In this episode I speak to her about her background in academia and industry, her journey into machine learning, and the importance of AI for science. We discuss the integration of AI and scientific research, the potential of AI in weather modeling, and the challenges of applying AI to other areas of science. Prof Anandkumar shares examples of successful AI applications in science and explains the concept of AI + science. We also touch on the skepticism surrounding machine learning in physics and the need for data-driven approaches. The conversation explores the potential of AI in the field of science and engineering, specifically in the context of physics-based simulations. Prof. Anandkumar discusses the concept of neural operators, highlights the advantages of neural operators, such as their ability to handle multiple domains and resolutions, and their potential to revolutionize traditional simulation methods. She emphasizes the importance of combining AI with scientific knowledge and traditional numerical solvers, supported by collaboration between machine-learning specialists and domain experts. Finally, she offers advice for PhD students and highlights the value of smaller workshops and conferences for following emerging ideas.


Links:

LinkedIn: https://www.linkedin.com/in/anima-anandkumar/

Ted Video: https://www.youtube.com/watch?v=6bl5XZ8kOzI 

FourCastNet: https://arxiv.org/abs/2202.11214

Google Scholar: https://scholar.google.com/citations?hl=en&user=bEcLezcAAAAJ

Lab page: http://tensorlab.cms.caltech.edu/users/anima/


Takeaways


- Anima's background includes both academia and industry, and she sees value in bridging the gap between the two.

- AI for science is the integration of AI and scientific research, with the goal of enhancing and accelerating scientific developments.

- AI has shown promise in weather modeling, with AI-based weather models outperforming traditional numerical models in terms of speed and accuracy.

- The skepticism surrounding machine learning in physics can be addressed by verifying the accuracy of AI models against known physics principles.

- Applying AI to other areas of science, such as aircraft design and fluid dynamics, presents challenges in terms of data availability and computational cost. Neural operators have the potential to revolutionize traditional simulation methods in science and engineering.

- Integrating AI with scientific knowledge is crucial for the development of effective AI models in the field of physics-based simulations.

- Interdisciplinary collaboration between ML specialists and domain experts is essential for advancing AI in science and engineering.

- The future of AI in science and engineering lies in the integration of various modalities, such as text, observational data, and physical understanding.


Chapters


00:00 Introduction and Overview

04:29 Professor Anima Anandkumar's Career Journey

09:14 Moving to the US for PhD and Transitioning to Industry

13:00 Academia vs Industry: Personal Choices and Opportunities

17:49 Defining AI for Science and Its Importance

22:05 AI's Promise in Enhancing Scientific Discovery

28:18 The Success of AI-Based Wea


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e13-prof-anima-anandkumar-the-future-of-ai-and-science/

S1, EP12 - Prof Karthik Duraisamy - Scientific Foundation Models23 Jul 202401:32:39

Prof. Karthik Duraisamy is a Professor at the University of Michigan, the Director of the Michigan Institute for Computational Discovery and Engineering (MICDE) and the founder of the startup Geminus.AI. In this episode, we discuss AI for Science, with a particular focus on fluid dynamics and computational fluid dynamics. Prof. Duraisamy talks about the progress and challenges of using machine learning in turbulence modeling and the potential of surrogate models (both data-driven and physics-informed neural networks). He also explores the concept of foundation models for science and the role of data and physics in AI applications. The discussion highlights the importance of using machine learning as a tool in the scientific process and the potential benefits of large language models in scientific discovery. We also discuss the need for collaboration between academia, tech companies, and startups to achieve the vision of a new platform for scientific discovery. Prof. Duraisamy predicts that in the next few years, there may be major advancements in foundation models for science; however, he cautions against unrealistic expectations and emphasizes the importance of understanding the limitations of AI.


Links:

Summer school tutorials https://github.com/scifm/summer-school-2024 (scroll down for links to specific tutorials)

SciFM24 recordings : https://micde.umich.edu/news-events/annual-symposia/2024-symposium/

SciFM24 Summary : https://drive.google.com/file/d/1eC2HJdpfyZZ42RaT9KakcuACEo4nqAsJ/view

Trillion parameter consortium  : https://tpc.dev

Turbulence Modelling in the age of data: https://www.annualreviews.org/content/journals/10.1146/annurev-fluid-010518-040547

LinkedIn:  https://www.linkedin.com/showcase/micde/


Chapters


00:00 Introduction

09:41 Turbulence Modeling and Machine Learning

21:30 Surrogate Models and Physics-Informed Neural Networks

28:42 Foundation Models for Science

35:23 The Power of Large Language Models

47:43 Tools for Foundation Models

48:39 Interfacing with Specialized Agents

53:31 The Importance of Collaboration

58:57 The Role of Agents and Solvers

01:08:26 Balancing AI and Existing Expertise

01:21:28 Predicting the Future of AI in Fluid Dynamics

01:23:18 Closing Gaps in Turbulence Modeling

01:25:42 Achieving Productivity Benefits with Existing Tools


Takeaways


-Machine learning is a valuable tool in the development of turbulence modeling and other scientific applications.

-Data-driven modeling can provide additional insights and improve the accuracy of scientific models.

-Physics-informed neural networks have potential in solving inverse problems but may not be as effective in solving complex PDEs.

-Foundation models for science can benefit from a combination of data-driven approaches and physics-based knowledge.

-Large language models have the potential to assist in scientific discovery and provide valuable insights in various scientific domains. Having a strong foundation in the domain of study is crucial before applying AI techniques.

-Collaboration between academia, tech companies, and startups is necessary to achieve the vision of a new platform for scientific discovery.

-Understanding the limitations of AI and managing expectations is important.

-AI can be a valuable tool for productivity gains and scientific assistance, but it will not replace human expertise.


Keywords


#computationalfluiddynamics , #ailearning #largelanguagemodels , #cfd , #supercomputing , #fluiddynamics


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e12-prof-karthik-duraisamy-scientific-foundation-models/

S1, EP11 - Prof. Max Welling - Machine Learning Pioneer & AI4Science Visionary09 Jul 202401:07:33

In this episode, Neil interviews Professor Max Welling, one of the foremost experts in Machine Learning about AI4Science: the use of machine learning and AI to solve challenges in various scientific disciplines. They discuss and debate between data-driven and physics-driven approaches, the potential for foundational models, the importance of open sourcing models and data, the challenges of data sharing in science, and the ethical considerations of releasing powerful models. The conversation covers the role of academia, industry, and startups in driving innovation, with a focus on the field of AI. Professor Welling discusses the advantages and limitations of each sector and shares his experience in academia, big tech companies, and startups. The conversation then shifts to Professor Wellings  new company; CuspAI, which focuses on material discovery for carbon capture using metal organic frameworks and machine learning. Prof. Welling provides insights into the potential applications of this technology and the importance of addressing sustainability challenges. The conversation concludes with a discussion on career advice and the future of AI for science.

Links 

CuspAI : https://www.cusp.ai 
University website: https://staff.fnwi.uva.nl/m.welling/
Google scholar: https://scholar.google.com/citations?user=8200InoAAAAJ&hl=en
AI4Science NeurIPS 2023 workshop: https://neurips.cc/virtual/2023/workshop/66548 
AI4Science NeurIPS 2022 workshop: https://nips.cc/virtual/2022/workshop/50019
Aurora paper: https://arxiv.org/abs/2405.13063 

Chapters

00:00 Introduction to the Neil Ashton Podcast
00:39 Guest Introduction: Professor Max Welling
11:12 Data-Driven vs. Physics-Driven Approaches in Machine Learning for Science
17:00 Foundational models for science
23:08 Discussion around Open-Sourcing Models and Data
29:26 Ethical Considerations in Releasing Powerful Models for Public Use
33:14 Collaboration and Shared Resources in Addressing Global Challenges
34:07 The Role of Academia, Industry, and Startups
43:27 Material Discovery for Carbon Capture
52:02 Career Advice for Early-stage Researchers
01:01:07 The Future of AI for Science and Sustainability

Keywords

AI for science, machine learning, data-driven approaches, physics-driven approaches, foundational models, open sourcing, data sharing, ethical considerations, blockchain technology, academia, industry, startups, AI, material discovery, carbon capture, metal organic frameworks, machine learning, sustainability, career advice, future of AI for science


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e11-prof-max-welling-machine-learning-pioneer-and-ai-for-science-visionary/

S1, EP10 - AI4Science - Personal Thoughts and Perspectives02 Jul 202400:20:03

This episode sets the scene for upcoming discussions on AI4Science with world renowned experts on machine learning. The focus is on using machine learning to solve scientific problems, such as computational fluid dynamics, weather modeling, material design, and drug discovery. The episode introduces the concept of machine learning and its potential to accelerate simulations and predictions. The episode also discusses the differences between machine learning for scientific problems and large language models, and the ongoing debate on incorporating physics into machine learning models.


Chapters

00:00 Podcast intro

00:30 Introduction: AI for Science and Machine Learning

02:29 The Importance of Computational Fluid Dynamics

04:53 The Limitations of Physical Testing and Simulation

05:53 Accelerating Simulations and Predictions with Machine Learning

09:51 Data-Driven vs Physics-Informed Approaches in Machine Learning

13:10 The Future of Machine Learning in Science: Foundational Models


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e10-ai-for-science-personal-thoughts-and-perspectives/

S4 EP2 - Prof. Nathan Kutz on Physics-Informed AI and Data-Driven Modeling11 Jun 202601:17:23

Physics-informed AI, DMD, SINDy and data-driven engineering are the focus of this conversation with Professor J. Nathan Kutz, Director of Physics-Informed AI at Autodesk. Neil and Nathan trace machine learning’s evolution in engineering, the role of physics in trustworthy models, and the future of autonomous agents, design automation and human expertise.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s4-e2-prof-nathan-kutz-on-physics-informed-ai-and-data-driven-modeling/


Topics


History of machine learning in engineering

Dynamic Mode Decomposition (DMD) and Sparse Identification of Nonlinear Dynamics (SINDy)

Physics-informed AI and reduced-order modeling

The debate between physics-based and data-driven models

The future of autonomous agents and their impact on industry


Papers


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

A practical example of agentic AI for engineering design.


Links


Articraft project page

https://articraft3d.github.io/


Chapters


00:00 Podcast intro

00:40 Introduction to Episode

05:00 Welcoming Prof. Kutz

10:34 The Evolution of Data-Driven Modeling

16:13 Understanding the SINDy Algorithm and Its Implications

22:14 Comparing Reduced-Order Modeling and Modern Machine Learning

28:29 The Role of Data in Machine Learning and Physics

34:23 Challenges in Extrapolation and Real-World Applications

40:46 Insights from McLaren and Team Dynamics

46:07 The Shift from Academia to Industry

48:53 Collaboration and Innovation in Engineering

51:57 The Role of Human Expertise in Design

54:45 Leveraging AI in Formula One

57:32 The Future of AI and Workforce Dynamics

59:06 Navigating Career Choices in a Changing Landscape

01:03:02 The Evolution of Thought in Engineering

01:09:06 Preparing for the Future of Technology

01:14:04 Responsible Use of AI in Engineering

S1, EP9 - Dr Chris Rumsey - NASA & Computational Fluid Dynamics (CFD)25 Jun 202400:54:17

In this episode of the Neil Ashton podcast, Neil interviews Dr. Chris Rumsey,  Research Scientist at NASA Langley Research Center.  Chris is one of the main CFD experts at NASA Langley is globally reconised as a leader in CFD, particularly for aeronautical applications. The conversation focuses on computational fluid dynamics (CFD) and turbulence modeling. They discuss Chris's career, his role in public dissemination of CFD methods, and his involvement in the Turbulence Modeling website. They also explore the High Lift Prediction Workshop and the role of machine learning in CFD and turbulence modeling. The conversation provides insights into working at NASA and the challenges and advancements in CFD and turbulence modeling. In this conversation, Neil and Chris Rumsey discuss the progress and challenges in solving the problem of high-lift aerodynamics in aircraft design. They explore the concept of certification by analysis and the role of computational fluid dynamics (CFD) in reducing the need for expensive wind tunnel and flight tests. They also delve into the use of machine learning in CFD and the challenges of reproducibility. The conversation then shifts to conferences, with Neil and Chris sharing their experiences and favorite events. They conclude by discussing career advice for aspiring aerospace professionals and the unique aspects of working at NASA.

00:00 Introduction to the Neil Ashton podcast
01:09 Focus on Computational Fluid Dynamics and Turbulence Modeling
06:51 Chris Rumsey's Journey to NASA
09:13 From Art to Aeronautical Engineering
13:08 Transitioning to Turbulence Modeling
15:34 The Origins of the Turbulence Modeling Website
20:40 Verification and Validation in Turbulence Modeling
24:34 The Role of Machine Learning in Turbulence Modeling
26:00 Advancements in High Lift Prediction
27:28 Challenges in High Lift Prediction
28:25 Thoughts on Working at NASA
29:42 Certification by Analysis: Reducing the Cost of Aircraft Certification
31:09 The Role of Machine Learning in CFD and Certification by Analysis
34:03 The Value of Conferences in Networking and Specialized Learning
40:30 Career Advice for Aspiring Aerospace Professionals
48:45 Curating and Documenting Knowledge in the Aerospace Community


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e9-dr-chris-rumsey-nasa-and-computational-fluid-dynamics/

S1, EP8 - Prof Jack Dongarra - High Performance Computing (HPC) Pioneer18 Jun 202400:53:49

In this episode, Neil speaks to Professor Jack Dongarra, a renowned figure in the supercomputing and high-performance computing (HPC) world. He is a Professor at University of Tennessee as well as a Distinguished Researcher at Oak Ridge National Laboratory (ORNL) and a Turing Fellow at the University of Manchester. He is the inventor of the LINPACK library that is still used today to benchmark the Top 500 list of the most powerful supercomputers and was one of the key people involved in the creation of Message-Passing-Inferface (MPI). They discuss what is HPC, the challenges and opportunities in the field, and the future of HPC. They also touch on the role of machine learning and AI in HPC, the competitiveness of the United States in the field, and potential future technologies in HPC. Professor Dongarra shares his insights and advice based on his extensive experience in the field.

As part of their discussion they discuss two papers from Prof Dongarra:

1) High-Performance Computing: Challenges and Opportunities: https://arxiv.org/abs/2203.02544 
2) Can the United States Maintain Its Leadership in High-Performance Computing? - A report from the ASCAC Subcommittee on American Competitiveness and Innovation to the ASCR Office: https://www.osti.gov/biblio/1989107/

Chapters

00:00 Introduction 
04:18 Defining HPC and its Impact
08:11 Challenges and Opportunities in HPC
28:20 The Competitiveness of the United States in HPC
44:31 The Future of HPC: Technologies and Innovations
49:30 Insights and Advice from Professor Jack Dongarra


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e8-prof-jack-dongarra-high-performance-computing-pioneer/

S1, EP7 - Pat Symonds - Formula 1 Legend11 Jun 202401:21:51

In this episode, Neil interviews Pat Symonds, one of the most well known and respected engineers in Formula One. They discuss Pat's career in engineering, his time in Formula One, and the evolution of the sport. Pat shares insights into his early motivations, his work with different teams, and the challenges he faced. They also touch on the growth of Motorsport Valley in the UK and the potential for Formula One teams to be based in other countries. In this conversation, Pat discusses his experience in Formula One and the challenges of being a technical director. He emphasizes the importance of continuous learning and the ability to make compromises in order to achieve success. He shares insights into the culture at Williams and Benetton and how it impacted their success. Additionally, he discusses the future of Formula One, including the use of AI and ML, the potential shift towards sustainable fuels, and the role of motor manufacturers.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e7-pat-symonds-formula-1/

S1, EP6 - Prof Juan Alonso - the Future of Computational Science04 Jun 202401:27:06

In this episode I speak to Prof Juan J. Alonso on his vision of the future of computational science as well as his journey from academia to entrepreneurship - founding Luminary Cloud. He reflects on the revolutions in computational science and the different ways of developing software throughout his career. Alonso emphasizes the importance of academia in creating and perpetuating knowledge, as well as the value of innovation and new ideas. He also discusses the changes in the CFD world, the emergence of new technologies like GPU computing and cloud computing, and the potential for advancements in computational simulations for analysis and design.  We also touch on the transition of the aerospace industry towards commercial software and the potential for cloud computing to revolutionize CFD. The conversation concludes with a discussion on the progress made towards achieving the goals outlined in the 2030 CFD vision report and the role of machine learning and AI in simulation-driven workflows.

 In this final part of the conversation, Juan discusses the potential applications of ML and AI in engineering. He identifies four main areas where these technologies can be beneficial, but emphasizes that these applications will always be based on high-fidelity simulations.  He concludes by envisioning the future of computational-driven science and the continued innovation in the field.

You can check out Luminary Cloud at https://www.luminarycloud.com and Prof Alonso's Stanford research at: https://adl.stanford.edu 


06:00 Introduction and Background
09:11 Early Interest in Aerospace Engineering
12:13 From Academia to Industry
15:11 Decision to Stay in Academia
17:11 Balancing Fundamental Science and Applied Research
22:14 Early Aims and Focus on High Performance Computing
29:18 Emergence of GPU Computing and Cloud Computing
32:23 Conditions for Innovation and Entrepreneurship
35:01 The Importance of the Bay Area
35:37 Challenges and Requirements in Developing Solvers
41:00 The Role of the Bay Area in Attracting Computational Science Talent
44:16 The Difficulty and Respect for Building High-Quality Commercial Software
47:03 The Transition of the Aerospace Industry towards Commercial Software
49:30 The Potential of Cloud Computing in Revolutionizing CFD
53:59 Progress towards the Goals of the 2030 CFD Vision Report
01:00:53 The Role of Machine Learning and AI in Simulation-Driven Workflows
01:04:01 Applications of ML and AI in Engineering
01:05:36 Optimization and Design Optimization with ML and AI
01:06:04 Outer Loops and Uncertainty Quantification
01:07:04 Digital Twin Frameworks and Constant Retraining
01:12:36 The Value of Open-Source Codes in Academia
01:16:19 Challenges of Integrating Commercial Tools with Research
01:25:20 The Future of Computational-Driven Science
01:29:01 Continued Innovation and Replacement of Physical Experimentation


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e6-prof-juan-alonso-the-future-of-computational-science/

S1, EP5 - Dimitris Katsanis - Designing the World's Fastest Bikes28 May 202401:52:17

In this conversation, Neil interviews Dimitris Katsanis, one of the world leading experts in bike design. They discuss the UCI regulations that govern bike design for road and track racing. Dimitris explains the evolution of bike design and the role of carbon fiber and titanium in creating lightweight and aerodynamic bikes. He also talks about his collaboration with Pinarello and the development of the Dogma F8 and F10 bikes. 


Dimitris emphasizes the importance of balancing weight, stiffness, and aerodynamics in bike design and the ongoing pursuit of improvement in the field. In this part of the conversation, Dimitris Katsanis discusses the evolution of bike design, the importance of aerodynamics and system drag reduction, the differences between track and road bike design, the interactions between the bike and rider, the impact of weight and aerodynamics in solo breakaways, the ongoing weight vs. aero debate, the role of stiffness in bike design, the relationship between stiffness and comfort in bike frames, and the potential of 3D printing and additive manufacturing in bike manufacturing. 


In this conversation, we also discuss the limitations of carbon fiber in bike design and the potential of 3D printing to overcome these limitations. He explains how 3D printing allows for the creation of custom shapes and internal structures that can improve the performance and weight of bike components. Katsanis shares examples of 3D printed handlebars and frames that are lighter than their carbon fiber counterparts. He also discusses the future of mass customization in bike design and the impact of regulations on innovation. 


Finally, he speculates on what bikes may look like in the future if design restrictions were lifted.


Chapters


00:00 Podcast intro

06:40 Introduction and Background

11:10 UCI Regulations and Bike Design

17:48 Evolution of Bike Design and UCI Regulations

25:27 Influence of Weight and Aerodynamics on Bike Performance

32:01 Pushing the Limits of Aerodynamics

37:16 Yaw Sensitivity and Aerofoil Sections

40:53 Continual Improvement in Bike Design

42:25 The Evolution of Bike Design

42:51 Aerodynamics and System Drag Reduction

44:21 Track vs. Road Bike Design

47:05 Interactions Between Bike and Rider

48:02 The Importance of Aero in Solo Breakaways

53:00 Weight vs. Aero Debate

56:00 The Impact of Weight on Performance

58:04 The Role of Stiffness in Bike Design

01:04:01 Stiffness and Comfort in Bike Frames

01:11:56 Materials in Bike Design: Steel, Aluminum, Titanium, and Carbon Fiber

01:18:08 The Potential of 3D Printing and Additive Manufacturing

01:19:45 The Limitations of Carbon Fiber

01:21:41 The Potential of 3D Printing

01:24:10 The Surprising Lightness of 3D Printed Titanium

01:28:02 The Future of Mass Customization

01:34:06 The Impact of Regulations on Bike Design

01:43:09 Speculating on the Bike of the Future


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e5-dimitris-katsanis-designing-the-world-s-fastest-bikes/

S1, EP4 - Academia or Industry? PhD or no PhD? Career advice21 May 202400:42:32

Summary

In this episode, Neil discusses four key career questions that you should think about. He explores the pros and cons of pursuing a PhD, the path to becoming a professor, and the opportunities in the tech sector. He highlights the importance of gaining industry experience and the potential for higher salaries in the tech sector. Neil also mentions the option of dual positions, where academics work in both academia and industry. Overall, he encourages listeners to consider all the options and make informed decisions about their careers.

Takeaways

Doing a PhD can provide expertise and specialization in a specific area, but it may delay entry into the job market and result in lower initial salaries.
Becoming a professor requires a PhD and often involves postdoctoral research positions. Advancement to higher ranks, such as associate professor and full professor, requires publishing, securing funding, and taking on leadership roles.
The tech sector offers high-paying jobs and opportunities for engineers, particularly in areas like machine learning and data science. Tech companies value both academic and industry experience.
Consider the trade-offs between academia and industry, such as job security, work-life balance, and the level of freedom and autonomy.
Dual positions, where academics work in both academia and industry, are becoming more common and offer the best of both worlds.

Timestamps
00:00 Introduction
05:22 Question 1: PhD or no PhD 
09:19 Question 2: How do I become a Professor?
23:10 Question 3: Academia or Industry?
31:00 Question 4: The third alternative - tech sector (Amazon, Google, META, Nvidia, Microsoft etc)
38:38 Dual Positions: Bridging the Gap Between Academia and Industry
41:00 Conclusions


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e4-academia-or-industry-phd-or-no-phd-career-advice/

S1, EP3 - Prof Tony Purnell - F1, British Cycling, PI Research and much more14 May 202402:15:28

Professor Tony Purnell discusses his journey from a passion for motor racing and engineering in his youth to founding and leading Pi Research, a company specializing in race car electronics. He shares his experiences at university, including a Kennedy Scholarship to MIT, and his early career in the motor racing industry. Tony also explains how Pi Research expanded into the automotive industry and eventually caught the attention of Ford, leading to the company's acquisition. His story highlights the importance of passion, perseverance, and seizing opportunities in pursuing a successful career. Tony shares his experiences in the world of Formula One, from Ford's interest in buying the team to his role in restructuring the Aero department at Jaguar. He discusses the challenges he faced and the politics and dishonesty he encountered in the industry. Tony also reflects on the stress and burnout he experienced and the difficulties he had working with Red Bull. 
He highlights the contrasting views of Max Mosley and Bernie Ecclestone on the future of Formula One and the changes that occurred under Liberty Media's ownership. In this conversation, Tony discusses his experiences in Formula One and British Cycling. He talks about the challenges of managing Formula One and the difficulties faced by organizations like Toyota in adapting to the sport. He also shares his reasons for leaving the FIA, including the Max Mosley sex scandal. He highlights the innovations he contributed to Formula One, such as the introduction of adjustable ride height and the DRS system. He discusses the politics and paranoia in Formula One and the importance of working with manufacturers. He then transitions to his role in British Cycling, where he emphasizes the impact of engineering on the sport. Tony expresses his concerns about the increasing technicality of cycling and the need to balance technology with talent. He concludes by offering advice for aspiring engineers, emphasizing the importance of following dreams. Enjoy!


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e3-prof-tony-purnell-formula-1-british-cycling-and-pi-research/

S1, EP2 - Dr Florian Menter - Turbulence Modelling Pioneer07 May 202401:20:54

Florian Menter discusses his journey in the field of computational fluid dynamics (CFD) and the development of the K-Omega SST model. He shares his experiences working at NASA Ames and the collaborative environment in the CFD community. Florian also talks about his decision to return to Germany and his role in the early days of what would be become ANSYS. Florian Menter discusses the birth and development of the SST turbulence model, the challenges of transition modeling, and the future of RANS models. He also explores the potential of machine learning in CFD and shares advice for young researchers. The conversation highlights the importance of pursuing valuable ideas, keeping things simple, and envisioning the outcome of one's work. 


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e2-dr-florian-menter-turbulence-modelling-pioneer/

S1, EP1 - Neil Ashton - Podcast Intro07 May 202400:09:42

In this short first episode Neil will explain why he's created the podcast, the guests he'll be interviewing and the topics that will be covered. 


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s1-e1-podcast-introduction/

S4 EP1 - Are AI Agents and Foundation Models About to Rewrite CAE?01 Jun 202600:28:18

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:


00:00 - Podcast intro

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

16:10 - Questions about model ownership, open-source codes, and licensing

16:40 - How agent-driven automation could democratize engineering expertise

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 episode expresses my personal opinion and does not represent the views of NVIDIA.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s4-e1-are-ai-agents-and-foundation-models-about-to-rewrite-cae/

S3 EP9 - Fluid Intelligence with Johannes Brandstetter and Siddhartha Mishra02 Dec 202501:24:54

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




Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e9-fluid-intelligence-with-johannes-brandstetter-and-siddhartha-mishra/

S3 EP8 - The Conference Connection (HPC, CAE, ML & Engineering)01 Nov 202500:22:37

In this episode, Neil Ashton discusses various conferences and workshops in the automotive, aerospace, and machine learning fields. He highlights the importance of these events for networking, education, and staying updated with industry trends. From the SAE and AIAA events to machine learning workshops, Neil provides insights into what attendees can expect and the value of participating in these gatherings.



Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e8-the-conference-connection-hpc-cae-ml-and-engineering/

S3 EP7 - 5 key trends for CFD revisited 15 Oct 202500:20:08

In this episode of the Neil Ashton podcast, the host revisits key trends in Computational Fluid Dynamics (CFD) from the past year, focusing on the rise of GPUs, advancements in AI and machine learning, the shift to cloud computing, the increasing adoption of high fidelity methods, and ongoing mergers and acquisitions in the industry. Each trend is explored in depth, highlighting the implications for the future of engineering and technology


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e7-five-key-trends-for-cfd-revisited/

S3 EP6 Prof. Brian Launder - CFD and Turbulence Modelling Pioneer30 Sep 202501:28:23

Professor Brian Launder, Professor at the University of Manchester and Fellow of the Royal Society and the Royal Academy of Engineering, reflects on more than 50 years of turbulence-modeling and CFD research. Neil and Brian discuss the influence of Professor Brian Spalding, the development of the k-epsilon and second-moment closure models, key collaborators and former students, and advice for early-career researchers.


Chapters


00:00 Podcast intro

00:30 Introduction

05:00 Early Academic Journey

10:06 Transition to MIT and Research Focus

16:21 Return to Imperial College and Early Career

21:06 Research Projects and PhD Students

27:46 Development of the k-epsilon model

33:18 CHAM and Career Changes

36:24 Move to UC Davis and New Research Directions

44:05 Challenges and Opportunities in Research

47:07 The Interview Experience

51:14 Transition to Manchester University

52:23 Research Innovations in Turbulence Modeling

57:45 The Development of the TCL Model

01:03:15 Nonlinear Eddy Viscosity Models

01:05:58 Advanced Wall Functions and Their Applications

01:10:09 Reflections on Career and Contributions

01:15:49 Legacy and Impact on Turbulence Modeling


Top Turbulence Modelling contributions (https://scholar.google.com/citations?user=Y3JbAK8AAAAJ&hl=en)


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e6-prof-brian-launder-cfd-and-turbulence-modelling-pioneer/

S3 EP5 - Joris Poort - CEO and Founder of Rescale17 Sep 202501:39:48

In this episode, Joris Poort, CEO and founder of Rescale, shares his personal journey on founding Rescale as well as his thoughts on the future of CAE. He discusses the challenges of introducing HPC to the cloud market, the traits that make successful founders, and the importance of perseverance and execution in entrepreneurship. Joris reflects on the early days of Rescale, the significance of early investors, and the evolving landscape of cloud computing and AI integration in engineering. The conversation highlights the complexities of transitioning to cloud solutions and the future potential of HPC in various industries. In this conversation, Joris discusses the transformative impact of AI on engineering, particularly in the context of inference, simulation, and automation. He emphasizes the importance of efficiency in engineering processes and how AI can significantly reduce the time required for complex simulations. The discussion also touches on the cultural shifts within organizations as they adapt to AI technologies, the potential for AI surrogates to revolutionize engineering practices, and the challenges of closing the sim-to-real gap. Joris offers insights for aspiring founders, encouraging them to pursue meaningful work that can drive innovation and societal progress.

Chapters

00:00 Introductions
03:30 The Genesis of Rescale: A Cloud Computing Journey
05:21 From Engineering to Entrepreneurship: The Leap of Faith
09:28 Traits of a Successful Founder: Courage and Perseverance
14:51 Tactical Steps to Startup Success: Building from the Ground Up
22:10 Milestones and Breakthroughs: The Early Days of Rescale
30:54 Navigating Challenges: The Role of Cloud Providers in HPC
35:24 The Intersection of HPC and AI Training
37:05 Cloud vs On-Premise: The Cost Debate
39:54 Complexities of HPC in Enterprises
42:27 The Slow Shift to Cloud Adoption
44:34 Optimizing Workloads with Rescale
46:50 Usability Challenges in Enterprise Software
48:32 The Rise of Neo Clouds and Competition
51:18 Speed and Efficiency in AI Training
54:34 AI's Transformative Impact on Engineering
58:54 The Future of AI Surrogates in Design
01:03:28 Agentic AI: The New Paradigm in Engineering
01:14:21 Solving Real Business Problems
01:19:26 The Impact of AI on Engineering
01:22:27 Innovation in Aerospace and Beyond
01:25:19 Cultural Change in Organizations
01:28:34 The Future of AI and Engineering
01:39:09 Advice for Aspiring Founders

Keywords

HPC, cloud computing, startup journey, Rescale, entrepreneurship, AI, technology, innovation, engineering, business, AI, engineering, inference, simulation, automation, digital twin, innovation, aerospace, machine learning, technology


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s3-e5-joris-poort-ceo-and-founder-of-rescale/

S4 EP6 - Daniel Mira on Hydrogen Combustion Modelling and Future Propulsion11 Aug 202601:24:52

Hydrogen combustion, high-fidelity CFD and the future of aircraft propulsion are the focus of this conversation with Dr. Daniel Mira, Head of the Propulsion Technologies Group at the Barcelona Supercomputing Center. Neil and Dani discuss why reacting flows are so difficult to simulate, how hydrogen changes combustion and aircraft design, the limits of RANS, LES and DNS, GPU-native solvers, coding agents and AI surrogate models.


Full episode, corrected transcript and resources:

https://neilashton.co.uk/podcasts/s4-e6-daniel-mira-on-hydrogen-combustion-modelling-and-future-propulsion/


Topics


Why reacting flows are so computationally difficult

Hydrogen versus hydrocarbon combustion

When hydrogen could reach commercial aviation

How engines and aircraft must be redesigned

Industrial trust in high-fidelity combustion CFD

RANS, LES and DNS for reacting flows

Chemistry, load balancing and computational cost

Wall modelling in combustion LES

GPU acceleration and solver redesign

Coding agents for scientific software

AI surrogate models and digital engineering workflows


Selected resources


Daniel Mira and the Propulsion Technologies Group

https://ptg.bsc.es/?p=44


Propulsion Technologies Group — research lines

https://ptg.bsc.es/research-lines/


BSC — Combustion research

https://www.bsc.es/research-development/research-areas/engineering-simulations/combustion


Center of Excellence in Combustion (CoEC)

https://coec-project.eu/


High-fidelity simulations of the mixing and combustion of a technically premixed hydrogen flame

https://upcommons.upc.edu/entities/publication/08a27c10-cb13-4357-a3ab-8e9ec1d706cc


Chapters


00:00 Podcast intro

00:39 Introducing Daniel Mira

03:00 Conversation begins

04:55 Why combustion CFD is so hard

10:23 Daniel’s path into hydrogen and jet-engine combustion

12:48 Hydrogen versus hydrocarbon combustion

17:58 Industrial adoption of hydrogen

20:54 Gas turbines, aviation and fuel infrastructure

25:35 How jet engines must change

30:43 Redesigning the whole aircraft

34:46 What will trigger commercial adoption?

37:27 Why aerospace projects take a decade

42:14 RANS, LES and DNS for reacting flows

44:31 Replacing expensive tests with high-fidelity CFD

46:01 The biggest accuracy gaps in combustion LES

49:26 Where the computational cost goes

52:06 Chemistry, species and source-term bottlenecks

55:35 Wall modelling in combustion LES

59:49 GPUs, algorithms and solver redesign

01:08:52 Can coding agents accelerate combustion CFD?

01:12:27 AI surrogate models for combustion

01:24:20 Closing thoughts


© My Podcast Data · Projet indépendant · Données issues d'Apple & Spotify