Dear all,

The next speaker in our seminar for machine learning and UQ in scientific computing will be our new postdoc Marius Kurz, formerly at the University of Stuttgart. His talk will concern GPU-based simulation codes and the integration of machine learning methods for stable large eddy simulations, see the abstract below. The talk will take place on April 30th at 11h00 CET. For those at CWI, the location is L017, and for online attendees the zoom link is posted below. Feel free to share it. More upcoming talks can be seen here: https://www.cwi.nl/en/groups/scientific-computing/uq-seminar/seminar-ml-uq-s....

Best regards,

Wouter Edeling

Join Zoom Meeting https://cwi-nl.zoom.us/j/88489988455?pwd=NUZwRXN1alU1ZGJTbVhJc2o3L000dz09

Meeting ID: 884 8998 8455 Passcode: 303356

30 April 2024 11h00 CET: Marius Kurz (Centrum Wiskunde & Informatica): Learning to Flow: Machine Learning and Exascale Computing for Next-Generation Fluid Dynamics

The computational sciences have become an essential driver for understanding the dynamics of complex, nonlinear systems ranging from the dynamics of the earth’s climate to obtaining information about a patient’s characteristic blood flow to derive personalized approaches in medical therapy. These advances can be ascribed on one hand to the exponential increase in available computing power, which has allowed the simulation of increasingly large and complex problems and has led to the emerging generation of exascale systems in high-performance computing (HPC). On the other hand, methodological advances in discretization methods and the modeling of turbulent flow have increased the fidelity of simulations in fluid dynamics significantly. Here, the recent advances in machine learning (ML) have opened a whole field of novel, promising modeling approaches.

This talk will first introduce the potential of GPU-based simulation codes in terms of energy-to-solution using the novel GALÆXI code. Next, the integration of machine learning methods for large eddy simulation will be discussed with emphasis on their a posteriori performance, the stability of the simulation, and the interaction between the turbulence model and the discretization. Based on this, Relexi is introduced as a potent tool that allows employing HPC simulations as training environments for reinforcement learning models at scale and thus to converge HPC and ML.