Calibration of Computational Models With Categorical Parameters and Correlated Outputs via Bayesian Smoothing Spline ANOVA

Abstract

It has become commonplace to use complex computer models to predict outcomes in regions where data do not exist. Typically these models
\nneed to be calibrated and validated using some experimental data, which often consists of multiple correlated outcomes. In addition, some
\nof the model parameters may be categorical in nature, such as a pointer variable to alternate models (or submodels) for some of the physics
\nof the system. Here, we present a general approach for calibration in such situations where an emulator of the computationally demanding
\nmodels and a discrepancy term from the model to reality are represented within a Bayesian smoothing spline (BSS) ANOVA framework.
\nThe BSS-ANOVA framework has several advantages over the traditional Gaussian process, including ease of handling categorical inputs
\nand correlated outputs, and improved computational efficiency. Finally, this framework is then applied to the problem that motivated its
\ndesign; a calibration of a computational fluid dynamics (CFD) model of a bubbling fluidized which is used as an absorber in a CO2 capture
\nsystem. Supplementary materials for this article are available online.