Illinois Institute of Technology’s Department of Chemical and Biological Engineering welcomes Bethany Lusch, assistant computer scientist in the data science group at the Argonne Leadership Computing Facility at Argonne National Lab, for a lecture titled “Integrating Machine-Learned Surrogate Models with Simulations” on Wednesday, October 19, 2022, from 3:15–4:30 p.m. in Room 108 of Perlstein Hall. 

Abstract

Simulations can be computationally expensive, so it can be advantageous to use machine learning to train a surrogate model that is orders of magnitude faster. However, completely data-driven black-box models often have disadvantages such as limited generalizability and the chance of physically impossible predictions. Bethany Lusch will describe her recent work on surrogate modeling for applications such as automotive engines and weather, as well as how she and her team are creating hybrid models by integrating surrogate models back into simulations.

Biography

Bethany Lusch is an assistant computer scientist in the data science group at the Argonne Leadership Computing Facility at Argonne National Lab. Her research expertise includes developing methods and tools to integrate artificial intelligence with science, especially for dynamical systems and PDE-based simulations. Her recent work includes developing machine-learning emulators to replace expensive parts of simulations, such as computational fluid dynamics simulations of engines and climate simulations. She is also working on methods that incorporate domain knowledge in machine learning, representation learning, and using machine learning to analyze supercomputer logs. She holds a M.S. and Ph.D. in applied mathematics from the University of Washington and a B.S. in mathematics from the University of Notre Dame.