Abstract
Model calibration uses outputs from a simulator and field data to build a predictive model for the physical system and to estimate unknown inputs. The conventional approach to model calibration assumes that the observations are continuous outcomes. In many applications this is not the case. The methodology proposed was motivated by an application in modeling photon counts at the Center for Exascale Radiation Transport. There, high performance computing is used for simulating the flow of neutrons through various materials. In this article, new Bayesian methodology for computer model calibration to handle the count structure of our observed data allows closer fidelity to the experimental system and provides flexibility for identifying different forms of model discrepancy between the simulator and experiment. Supplementary materials for this article are available online.
Acknowledgments
The authors would like to thank Les Braby at Texas A&M University for his assistance on the CERT experiments.
Supplementary Materials
Supplemental sampling details: PDF document containing additional details about the sampling approach discussed in Section 3.1.
Further discussion on the choice of prior distributions: PDF document containing further discussion on the choice of prior distributions in Sections 3.1 and 5.2.
R-package for CERT calibration analyses in this manuscript: R-package certcalibration containing code to perform the analyses described in the article. The package also contains all datasets used as examples in the article. (GNU zipped tar file)