Minisymposium Presentation
Panel Discussion – Foundational models for Computational Fluid Dynamics
Presenter
Dr. Philipp Bekemeyer is head of the Group “Surrogates and Uncertainty Management” at the Institute of Aerodynamics and Flow Technology at the German Aerospace Center (DLR). Together with his team he is investigation how machine learning techniques can be used to tackle existing aerodynamic challenges. With an interest in wind turbines in subsonic conditions, commercial aircraft in transonic speeds and also supersonic configurations he has the ambition to industrialize ML techniques for a wide range of industrial-grade applications. Moreover, he is actively involved in several AIAA, GARTEUR and NATO AVT working groups with the aim of extending the usage of machine learning for aerospace. He has a Bachelor’s and Master’s degree in Aerospace Engineering from the Technical University Braunschweig, Germany as well as a Ph.D. from the University of Liverpool, UK.
Presenter
Johannes Brandstetter did his PhD studying Higgs boson decays at the CMS experiment at the Large Hadron Collider at CERN. In 2018, he joined Sepp Hochreiter’s group in Linz, Austria. In 2021, he became ELLIS PostDoc at Max Welling’s lab at the University of Amsterdam, before joining the newly founded Microsoft Lab in Amsterdam. During his time at Microsoft Research, Johannes was working on scaling up of AI driven physics surrogates, most notably for weather and climate simulations. In October 2023, Johannes Brandstetter moved back to Austria and started a new group “AI for data-driven simulations” at the Institute of Machine Learning at the Johannes Kepler University (JKU) in Linz. Additionally, in 2024 Johannes was Chief Researcher at NXAI GmbH. In February 2025, and co-founded Emmi AI in February 2025 where he is currently is the Chief Scientist.
Description
In this panel session, we will bring together the speakers to discuss the development of ‘Foundational Models’ a key topic in the field of Machine Learning for Computational Fluid Dynamics. In particular, we will discuss the technical challenges surrounding data generation, generalizability, ML architecture choice as well as broader commercial and legal concerns. We will invite the audience to share in this panel discussion and have a debate on aspects surrounding accuracy, computational cost, commercialization and overall feasibility.