【Academic Seminar】Gaussian Process Modeling and Optimization of Simulators for Physical Systems
- Topic: Gaussian Process Modeling and Optimization of Simulators for Physical Systems
- Speaker: Tan Matthias HY, City University of Hong Kong
- Time and Date: 2:00 pm - 3:00 pm, February 28, 2019
- Venue: Room 103, Dao Yuan Building
Gaussian process (GP) emulators are typically constructed to replace time consuming simulators of physical systems to expedite quantitative analysis that depends on the functional relationship between inputs and outputs of the simulator. However, standard stationary GP emulators with Matérn or Gaussian correlation function are typically used, which ignores valuable engineering and mathematical knowledge about the behavior of the simulator. In the first part of the talk, I will present my research on the use of known behavior/ properties of partial differential equation models solved numerically by computer codes to improve construction of GP emulators for this type of simulators. In the second part of the talk, I will present a real case study on optimizing the engineering design of a centrifugal compressor based on a very time-consuming simulator.
Tan Matthias HY is an assistant professor in the School of Data Science at City University of Hong Kong. He received his B.Eng. degree in Mechanical-Industrial Engineering from the Universiti Teknologi Malaysia, an M.Eng. degree in Industrial and Systems Engineering from the National University of Singapore and a Ph.D. degree in Industrial and Systems Engineering from Georgia Institute of Technology. His research interests include uncertainty quantification, design and analysis of computer experiments, and applied statistics.