Panos Stinis specializes in scientific computing with application interests in model reduction of complex systems, multiscale modeling, uncertainty quantification, and machine learning. He studied aeronautical engineering at the Technical University of Athens, Greece. He earned his PhD in applied mathematics in 2003, from Columbia University in New York, in model reduction. He began his career at Lawrence Berkeley National Laboratory and the Stanford Center for Turbulence Research, where he worked on applying model reduction methods to hyperbolic systems and in developing techniques for locating and tracking singularities of partial differential equations. In 2008, he became a faculty member at the Mathematics Department at the University of Minnesota, where he worked on renormalization, mesh refinement, particle filtering and optimization. He moved to the Pacific Northwest National Laboratory in 2014, where he is currently leading the Computational Mathematics group.
Presentation Title:
Better solvers, better scientific AI: Developing stable hybrid solvers and quantifying accurately the uncertainty of machine learning surrogates
Presentation Abstract:
Scientific AI is a rapidly developing field within scientific machine learning. For example, agentic and foundation model frameworks require solvers to provide predictions for the scenarios/approaches that these frameworks dictate. Thus, fast, accurate and reliable solvers are essential to successful agentic AI. Hybrid solvers that couple machine-learnt (ML) surrogates with traditional numerical methods for partial differential equations (PDEs) are important but they can suffer from instabilities when the coupled system is simulated. In addition, the reliable use of ML surrogates requires accurate uncertainty quantification of the surrogate predictions. In recent years, we have developed a collection of different approaches to stabilize PDE-ML coupled systems and quantify the uncertainty of ML surrogate predictions. In this talk, we will present these approaches along with application to various benchmark problems including fluid mechanics.