The Neil Ashton Podcast

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.Chapters00:00 Introduction to the Podcast and Topic01:09 Foundational Models in Fluid Dynamics10:09 The Evolution of AI in CFD19:52 Future Predictions and Industry Dynamics

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.Chapters00:00 Introduction to the Podcast and Themes04:55 Kurt Bergin-Taylor: Background and Role at Tudor Pro Cycling10:08 The Structure and Dynamics of a Pro Cycling Team12:59 Innovation in Cycling: Aerodynamics, Thermal Management, and Safety19:14 Nutrition, Training, and Performance in Cycling29:18 Future Innovations in Cycling Equipment and Systems30:42 Understanding Individualization in Cycling Gear34:30 Collaborative Innovation in Cycling Equipment38:20 The Evolving Mindset of Young Cyclists42:28 Enhancing Viewer Engagement in Cycling46:24 The Future of Data and AI in Cycling50:05 Advice for Aspiring Engineers in CyclingTakeaways- 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.

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. 

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.Chapters00:00 Introduction to Engineering Careers03:01 Exploring Company Types in Engineering06:05 Understanding Job Roles in Engineering09:00 The Shift Towards Software in Engineering11:52 Diverse Career Paths Beyond Traditional Engineering14:47 The Role of Consulting in Engineering18:03 Navigating the Job Market in Engineering20:57 The Importance of Software Skills in Engineering24:03 Conclusion and Future Trends in Engineering Careers30:08 The Rise of Software Development in Engineering31:59 The Tech Sector's Growing Relevance to Engineers36:41 Career Paths in Tech: Software Development and Management44:27 Understanding Product Management in Tech48:15 The Role of Solution Architects in Tech52:04 Consulting and Support Roles in Tech55:54 AI's Impact on Engineering and Software Development#careers #engineering #tech #sde #amazon #aws #google #jobs

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=enYoutube version: https://youtu.be/lk4lvKQsqWUChapters00:00 Introduction to the Podcast and Guest05:51 Understanding Randomized Linear Algebra19:09 Foundational Models for Science32:29 Physics-Informed vs Data-Driven Approaches38:36 The Practical Application of Randomized Linear Algebra39:32 Creative Destruction in Linear Algebra and Machine Learning40:32 The Role of Randomness in Scientific Machine Learning41:56 Identifying Commonalities Across Scientific Domains42:52 The Horizontal vs. Vertical Application of Machine Learning44:19 The Challenge of Common Architectures in Science46:31 Data Availability and Licensing Issues50:04 The Future of Foundation Models in Science54:21 The Commercial Viability of Machine Learning Solutions58:05 Emerging Opportunities in Scientific Machine Learning01:00:24 Navigating Academia and Industry in Machine Learning01:11:15 Advice for Aspiring Scientific Machine Learning ResearchersKeywordsmachine 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

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/B0B7LZPDZWYoutube version of this episode: https://youtu.be/9Ic5xgJt6BQChapters00:00 Introduction to the Podcast and Guest05:18 Dr. Prith Banerjee's Journey: From Academia to CTO09:10 The Role of Academia, Startups, and Industry17:22 Advice for Startups: Motivation and Market Sizing24:04 The Impact of AI and ML on Simulation35:07 Future of AI in Physics and Simulation36:10 The Power of Data in AI Models40:33 Incentivizing Data Sharing for Better Models42:55 Physics-Driven vs Data-Driven Approaches47:30 The Role of Open Source in AI Innovation52:06 Foundational Models and Simulation Data58:22 The Future of CAE and Quantum Computing01:06:29 Advice for Aspiring InnovatorsKeywordsNeil 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

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.LinksNASA Quesst mission: https://www.nasa.gov/mission/quesst/AIAA Low-Boom Prediction Workshop: https://lbpw.larc.nasa.govX-59 (Lockheed Martin website): https://www.lockheedmartin.com/en-us/products/x-59-quiet-supersonic.htmlChapters00:00 Introduction to Supersonic Travel04:05 The History of Supersonic Flight09:56 Challenges Faced by Concorde16:02 Technological Challenges of Supersonic Travel25:48 NASA's X-59 and the Quest Mission33:45 Future of Supersonic Travel and Regulations38:04 Understanding Shockwaves in Supersonic Flight40:02 Design Innovations for Sonic Boom Reduction43:16 Advancements in Pilot Visibility Technology46:27 Human Factors in Aircraft Design48:23 The Role of Simulation in Aircraft Development51:42 Engine Noise and Its Impact on Supersonic Travel54:31 The Future of Commercial Supersonic Travel57:13 Challenges in Engine Technology for Supersonic Aircraft01:00:17 The Intersection of Military and Supersonic Travel01:02:09 Exploring Hypersonic Passenger Travel01:06:39 The Future of Battery Technology in Aviation01:09:09 Career Advice for Aspiring Aeronautics ProfessionalsKeywordssupersonic 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

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.Chapters00:00 Introduction to Computational Fluid Dynamics and Professor Jameson05:02 Professor Jameson's Early Life and Influences20:00 Academic Journey and Contributions to Aerodynamics34:50 Career in Industry and Transition to Academia48:52 Pivotal Moments in Computational Fluid Dynamics50:19 Navigating Numerical Methods for Fluid Flow57:02 Transitioning to Academia and Teaching Challenges01:06:25 Developing Flow Codes FLO & SYN and Their Impact01:12:21 The Evolution of Computational Fluid Dynamics01:19:10 Commercialization and the Future of CFD01:30:34 Journey to Success: From Code to Commercialization01:37:02 Innovations in Aerodynamics: Control Theory and Design01:43:06 The Impact of Industry Experience on Academic Research01:51:24 The Evolution of Computational Power in Aerodynamics02:01:29 Advice for Aspiring Aeronautics ProfessionalsSummary 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.  Its most striking application was the aerodynamic design of the Gulfstream G650 in 2006, when he performed the calculations with Syn107 on a server in his garage.

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 Chapters00:00 Introduction to the Podcast and Cycling Passion02:57 The Intersection of Cycling and Aerodynamics06:02 Dr. Hutch's Journey into Competitive Cycling08:57 The Evolution of Aerodynamics in Cycling12:13 The Role of Power Meters in Cycling Performance15:01 Training Techniques and the Shift to Power Metrics17:58 Transitioning from Cycling to Media and Writing20:50 The Cultural Landscape of Cycling in the UK24:13 Technical Innovations and Personal Experiments in Aerodynamics27:01 The Impact of Power Meters on Training and Performance32:51 The Power of Training Less34:15 Evolution of Cycling Performance38:30 Nutrition: The Game Changer39:47 Diverse Training Approaches42:31 The Professionalism of Cyclists48:11 The Rise of Women's Cycling50:33 Aerodynamics: The Key to Speed56:06 The Impact of Equipment on Performance01:05:08 Balancing Power and Aerodynamics in Cycling01:07:05 The Evolution of Rider Trust in Aerodynamics01:10:55 The Impact of Wind Tunnels on Cycling Performance01:12:21 Challenges of Wind Tunnel Testing and Real-World Validation01:20:26 The Role of CFD in Cycling Aerodynamics01:25:31 Regulatory Challenges in Cycling Technology01:31:08 The Future of Cycling: Balancing Technology and TraditionKeywordscycling, 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

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.TakeawaysGPUs 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.KeywordsCFD, GPUs, AI, Machine Learning, Cloud Computing, Trends, Digital Certification, Mergers, Acquisitions, SimulationChapters00:00 Introduction to CFD Trends02:04 The Rise of GPUs in CFD14:06 The Impact of AI and Machine Learning29:39 The Shift to Cloud Computing38:41 Digital certification: Higher-fidelity methods43:00 Future of CFD: Mergers and Innovations

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.Chapters00:00 Introduction to the Podcast and Season Two03:38 Nicolas Tambazis: A Key Figure in Formula One04:56 Early Influences and Passion for Engineering08:52 The Journey Through Cambridge and PhD Studies12:57 Entering Formula One: The Path to Benetton18:25 The Evolution of Aerodynamics in Formula One24:06 The Role of CFD and Wind Tunnel Technology38:53 Balancing Technology and Entertainment in F144:47 The Future of AI in Formula One54:56 Understanding Team Dynamics and Performance Variability01:03:44 Advice for Aspiring Engineers in Formula One

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!

Professor Anima Anandkumar is one of the worlds leading scientists in the field of AI & ML with more than 30k citations, a h-index of 80 and numerous landmark papers such as FourCastNet, which got world-wide coverage for demonstrating how AI can be used to speed up weather prediction. She is the Bren Professor at Caltech, leading a large team of PhD students and post-docs in her AI+Science lab, and has had extensive experience in industry, previously being the Senior Director of AI Resarch 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. Prof. Anandkumar also emphasizes the importance of integrating AI with scientific knowledge and the need for interdisciplinary collaboration between ML specialists and domain experts. She also emphasizes the importance of integrating AI with traditional numerical solvers and the need for interdisciplinary collaboration between ML specialists and domain experts. Finall she provides advice for PhD students and highlights the significance of attending smaller workshops and conferences to stay updated on emerging ideas in the field.Links:LinkedIn: https://www.linkedin.com/in/anima-anandkumar/Ted Video: https://www.youtube.com/watch?v=6bl5XZ8kOzI FourCastNet: https://arxiv.org/abs/2202.11214Google Scholar: https://scholar.google.com/citations?hl=en&user=bEcLezcAAAAJLab 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.Chapters00:00 Introduction and Overview04:29 Professor Anima Anandkumar's Career Journey09:14 Moving to the US for PhD and Transitioning to Industry13:00 Academia vs Industry: Personal Choices and Opportunities17:49 Defining AI for Science and Its Importance22:05 AI's Promise in Enhancing Scientific Discovery28:18 The Success of AI-Based Wea

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 discusses AI4Science, 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 foundational 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/viewTrillion parameter consortium  : https://tpc.devTurbulence Modelling in the age of data: https://www.annualreviews.org/content/journals/10.1146/annurev-fluid-010518-040547LinkedIn:  https://www.linkedin.com/showcase/micde/Chapters00:00 Introduction09:41 Turbulence Modeling and Machine Learning21:30 Surrogate Models and Physics-Informed Neural Networks28:42 Foundational Models for Science35:23 The Power of Large Language Models47:43 Tools for Foundation Models48:39 Interfacing with Specialized Agents53:31 The Importance of Collaboration58:57 The Role of Agents and Solvers01:08:26 Balancing AI and Existing Expertise01:21:28 Predicting the Future of AI in Fluid Dynamics01:23:18 Closing Gaps in Turbulence Modeling01:25:42 Achieving Productivity Benefits with Existing ToolsTakeaways-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.-Foundational 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

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=enAI4Science NeurIPS 2023 workshop: https://neurips.cc/virtual/2023/workshop/66548 AI4Science NeurIPS 2022 workshop: https://nips.cc/virtual/2022/workshop/50019Aurora paper: https://arxiv.org/abs/2405.13063 Chapters00:00 Introduction to the Neil Ashton Podcast00:39 Guest Introduction: Professor Max Welling11:12 Data-Driven vs. Physics-Driven Approaches in Machine Learning for Science17:00 Foundational models for science23:08 Discussion around Open-Sourcing Models and Data29:26 Ethical Considerations in Releasing Powerful Models for Public Use33:14 Collaboration and Shared Resources in Addressing Global Challenges34:07 The Role of Academia, Industry, and Startups43:27 Material Discovery for Carbon Capture52:02 Career Advice for Early-stage Researchers01:01:07 The Future of AI for Science and SustainabilityKeywordsAI 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

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.Chapters00:30 Introduction: AI for Science and Machine Learning02:29 The Importance of Computational Fluid Dynamics04:53 The Limitations of Physical Testing and Simulation05:53 Accelerating Simulations and Predictions with Machine Learning09:51 Data-Driven vs Physics-Informed Approaches in Machine Learning13:10 The Future of Machine Learning in Science: Foundational Models

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 podcast01:09 Focus on Computational Fluid Dynamics and Turbulence Modeling06:51 Chris Rumsey's Journey to NASA09:13 From Art to Aeronautical Engineering13:08 Transitioning to Turbulence Modeling15:34 The Origins of the Turbulence Modeling Website20:40 Verification and Validation in Turbulence Modeling24:34 The Role of Machine Learning in Turbulence Modeling26:00 Advancements in High Lift Prediction27:28 Challenges in High Lift Prediction28:25 Thoughts on Working at NASA29:42 Certification by Analysis: Reducing the Cost of Aircraft Certification31:09 The Role of Machine Learning in CFD and Certification by Analysis34:03 The Value of Conferences in Networking and Specialized Learning40:30 Career Advice for Aspiring Aerospace Professionals48:45 Curating and Documenting Knowledge in the Aerospace Community

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/Chapters00:00 Introduction 04:18 Defining HPC and its Impact08:11 Challenges and Opportunities in HPC28:20 The Competitiveness of the United States in HPC44:31 The Future of HPC: Technologies and Innovations49:30 Insights and Advice from Professor Jack Dongarra

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.

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 Background09:11 Early Interest in Aerospace Engineering12:13 From Academia to Industry15:11 Decision to Stay in Academia17:11 Balancing Fundamental Science and Applied Research22:14 Early Aims and Focus on High Performance Computing29:18 Emergence of GPU Computing and Cloud Computing32:23 Conditions for Innovation and Entrepreneurship35:01 The Importance of the Bay Area35:37 Challenges and Requirements in Developing Solvers41:00 The Role of the Bay Area in Attracting Computational Science Talent44:16 The Difficulty and Respect for Building High-Quality Commercial Software47:03 The Transition of the Aerospace Industry towards Commercial Software49:30 The Potential of Cloud Computing in Revolutionizing CFD53:59 Progress towards the Goals of the 2030 CFD Vision Report01:00:53 The Role of Machine Learning and AI in Simulation-Driven Workflows01:04:01 Applications of ML and AI in Engineering01:05:36 Optimization and Design Optimization with ML and AI01:06:04 Outer Loops and Uncertainty Quantification01:07:04 Digital Twin Frameworks and Constant Retraining01:12:36 The Value of Open-Source Codes in Academia01:16:19 Challenges of Integrating Commercial Tools with Research01:25:20 The Future of Computational-Driven Science01:29:01 Continued Innovation and Replacement of Physical Experimentation

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.Chapters06:40 Introduction and Background11:10 UCI Regulations and Bike Design17:48 Evolution of Bike Design and UCI Regulations25:27 Influence of Weight and Aerodynamics on Bike Performance32:01 Pushing the Limits of Aerodynamics37:16 Yaw Sensitivity and Aerofoil Sections40:53 Continual Improvement in Bike Design42:25 The Evolution of Bike Design42:51 Aerodynamics and System Drag Reduction44:21 Track vs. Road Bike Design47:05 Interactions Between Bike and Rider48:02 The Importance of Aero in Solo Breakaways53:00 Weight vs. Aero Debate56:00 The Impact of Weight on Performance58:04 The Role of Stiffness in Bike Design01:04:01 Stiffness and Comfort in Bike Frames01:11:56 Materials in Bike Design: Steel, Aluminum, Titanium, and Carbon Fiber01:18:08 The Potential of 3D Printing and Additive Manufacturing01:19:45 The Limitations of Carbon Fiber01:21:41 The Potential of 3D Printing01:24:10 The Surprising Lightness of 3D Printed Titanium01:28:02 The Future of Mass Customization01:34:06 The Impact of Regulations on Bike Design01:43:09 Speculating on the Bike of the Future

SummaryIn 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.TakeawaysDoing 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.Timestamps00:00 Introduction05:22 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 Industry41:00 Conclusions

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!

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. 

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.