Lecturer：Prof. Nicolas R. Gauger, University of Kaiserslautern-Landau (RPTU), Germany
Topic: Linking classical optimization with PDEs/ODEs to the training of ANNs - with application to aerospace
Abstract: The so-called "grey-box modeling" approach cleverly combines insights from simulations (“white-box modeling”) on high-performance computing (HPC) architectures with data-driven approaches (“black-box modeling”) using artificial intelligence (AI) methods. As an example, we consider here the so-called "field inversion" method in data-driven turbulence modeling for the Navier-Stokes equations. For the field inversion, classical methods from the area of optimization with partial differential equations are used. Furthermore, in the data-driven part, the training of certain artificial neural networks shows analogies to the optimization for ordinary differential equations. In all approaches, we keep an eye on automation and parallelization on the computing systems to be used.
Biography:
Prof. Dr. Nicolas R. Gauger is now the Chairholder for Scientific Computing and Director of Computing Center at University of Kaiserslautern-Landau (RPTU). He received his Master in Mathematics from Leibniz University of Hanover in 1998, and his Ph.D. in Applied Mathematics from Braunschweig University of Technology in 2003. From 1998 to 2010 he was Research Scientist in the field of Numerical Methods for Aerodynamics at German Aerospace Center (DLR) in Braunschweig. From 2010 to 2014, he was Associate Professor for Computational Mathematics at RWTH Aachen University. Since September 2014, he is Chairholder for Scientific Computing at RPTU, where he is Full Professor at the Department of Mathematics as well as Department of Computer Science. Additionally, since February 2015, he is Director of the Computing Center at RPTU. In August 2018 he has been named an Associate Fellow of the AIAA. He has published more than 210 scientific papers and his research areas are: Nonlinear Optimization, Numerical Optimization, Optimization and Control with PDEs, Aerodynamic Shape Optimization in Multidisciplinary Design Context, Machine Learning in CFD, and High-Performance Computing, etc.
Time: 16:00, 20th Feb, 2023
Zoom ID: 881 8219 3533, Password: 728343
Host: Prof. Zhonghua Han, School of Aeronautics
