Joint Modeling of Point and Integral Responses in Computer Experiments

• Activity Number: 581
• Type: Invited
• Date/Time: Thursday, August 7, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Section on Physical and Engineering Sciences
• Author(s): Heng Su*+ and Rui Tuo and C. F. Jeff Wu
• Companies: Georgia Institute of Technology and Chinese Academy of Science and Georgia Institute of Technology
• Keywords: computer experiment ; Gaussian process ; integral

Abstract

In some computer experiments, the quantity of interest may be the average value of the responses over a specific region. One example from building energy simulation is the diffuse solar irradiance on a building façade representing the integral of the irradiance over the sky dome that the façade is exposed to. Treating this information as point data will lead to estimation efficiency loss. In this work we extend the standard Gaussian process framework so that it can handle both point and integral data. This method requires complicated integration in the parameter estimation process, which may be computationally inefficient. We find that, under certain conditions, a closed-form expression can be derived, and the predictions on new points and regions can be obtained pretty fast and with high accuracy. An illustration is made with data from the irradiance study.