Mathematics and Computer Science Division
Argonne National Laboratory
"Reduced-order modeling of high-dimensional systems using machine learning"
Nov 19, 2021 Schedule:
- 10:00 to 11:00 AM Eastern Time (US and Canada)
Meeting # 91481831026
In this talk, I will discuss some recent research that builds fast and accurate reduced-order models (ROMs) for various high-dimensional systems. These systems may be steady-state, where the ROM is tasked with making predictions given varying parametric inputs, or they may be dynamical where the ROM must make accurate forecasts in time, given parameters and/or varying initial and boundary conditions. In both endeavors, we will outline the development of customized machine learning strategies, based on deep learning-based compression and forecasting, to dramatically improve accuracy and/or time-to-solution and for extended computational campaigns. Furthermore, in addition to canonical experiments, our algorithms will be demonstrated for real-world applications of strategic importance such as for geophysical forecasting from ship and satellite observation data and wind-turbine wake/urban-flow predictions from meteorological and LIDAR measurements.