Professor John Harlim, Pennsylvania State University
Will present a talk entitled:
Reduced Order Modeling with Neural Networks
Abstract: The recent success of machine learning has drawn tremendous interest in applied mathematics and scientific computations. I will discuss how to leverage neural networks to approximate model error induced by missing dynamics or reduced-order modeling. The proposed framework reformulates the model error problem into a supervised learning task to approximate a very high-dimensional target function involving the Mori-Zwanzig representation of projected dynamical systems. Theoretical convergence and numerical demonstration on various applications ranging from geophysical fluid dynamics to power systems will be presented.
Bio: John Harlim is a Professor of Mathematics and Meteorology at the Pennsylvania State University. He earned a Ph.D. in Applied Mathematics and Scientific Computation from the University of Maryland in 2006. His research contribution covers a wide area in applied mathematics, including data assimilation, statistical closure of dynamical systems, linear response theory, kernel regression, manifold learning, machine learning of dynamical systems, and numerical PDEs.
CAMP176
Friday September 26, 2025
12:00 pm
________________________________________________________________
C3S2 Clarkson Center for Complex Systems Science l http://webspace.clarkson.edu/~ebollt/Website-C3S2/index.html
CLARKSON UNIVERSITY l Potsdam, New York 13699-5720