S1, EP2 - Dr Florian Menter - Turbulence Modelling Pioneer

The Neil Ashton Podcast

#Science #Tech #Neil Ashton #Engineering #Formula 1 #Cycling #Cfd #Physics #Machine Learning #NASA

29:53

Living together in a group is a strategy many animals use to survive and thrive. And a big part of what makes that living situation successful is listening. In this episode, we explore the collaborative world of the naked mole rat. Threshold is nonprofit, listener-supported, and independently produced. You can support Threshold by donating today . To stay connected, sign up for our newsletter . Operation frog sound! Send us your frog sounds for an upcoming episode. We want you to go out, listen for frogs and toads, and record them. Just find someone croaking, and hit record on your phone. It doesn’t matter if there’s background noise. It doesn’t even matter if you’re not sure whether or not you’re hearing an amphibian—if you think you are, we would love to get a recording from you. Please also say your name and where you are in the world, and then email the recording to us at outreach@thresholdpodcast.org…

год назад 1:20:54

MP3•Главная эпизода

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.

24 эпизодов

S1, EP2 - Dr Florian Menter - Turbulence Modelling Pioneer

The Neil Ashton Podcast

published год назад

MP3•Главная эпизода

24 эпизодов

#Science #Tech #Neil Ashton #Engineering #Formula 1 #Cycling #Cfd #Physics #Machine Learning #NASA

Все серии

1
S2 EP10 - Dr. Kurt Bergin-Taylor, Head of Innovation - Tudor Pro Cycling 1:01:04

24 дня назад1:01:04

1:01:04

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.…

1
S2, EP9 - New Job Update! (and a small apology..) 8:46

6 weeks назад8:46

8:46

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.

1
S2, EP8 - Neil Ashton - Career advice for Engineers 1:00:09

12 weeks назад1:00:09

1:00:09

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…

1
S2, EP7 - Prof. Michael Mahoney - Perspectives on AI4Science 1:16:44

14 weeks назад1:16:44

1:16:44

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…

1
S2, EP6 - Dr. Prith Banerjee - ANSYS CTO 1:10:37

15 weeks назад1:10:37

1:10:37

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…

1
S2, EP5 - NASA's Quesst for Quieter Supersonic Flight with Peter Coen 1:15:14

17 weeks назад1:15:14

1:15:14

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…

1
S2, EP4 - Celebrating Prof. Antony Jameson: A CFD Pioneer 2:11:34

19 weeks назад2:11:34

2:11:34

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. 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.…

1
S2, EP3 - Dr Michael Hutchinson - Cycling aerodynamics and the lifelong pursuit to go faster 1:38:00

21 weeks назад1:38:00

1:38:00

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…

1
S2, EP2: The Future of CFD: 5 Key Trends to Watch 46:26

23 weeks назад46:26

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…

1
S2, EP1 - Dr. Nikolas Tombazis - From Poacher to Gamekeeper, Defining the future of Formula 1 1:12:14

25 weeks назад1:12:14

1:12:14

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…

1
S1, EP14 - Season 1 Recap and what's next 20:09

34 weeks назад20:09

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!

1
S1, EP13 - Prof. Anima Anandkumar - The future of AI+Science 1:06:56

35 weeks назад1:06:56

1:06:56

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/2202.11214 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…

1
S1, EP12 - Prof Karthik Duraisamy - Scientific Foundational Models 1:32:39

36 weeks назад1:32:39

1:32:39

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 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/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 Foundational 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. -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…

1
S1, EP11 - Prof. Max Welling - Machine Learning Pioneer & AI4Science Visionary 1:07:33

38 weeks назад1:07:33

1:07:33

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…

1
S1, EP10 - AI4Science - Personal Thoughts and Perspectives 20:03

39 weeks назад20:03