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

Curtis Storlie, William A. Lane, Emily M. Ryan, James R. Gattiker, David M. Higdon

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

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

Original languageEnglish (US)
Pages (from-to)68-82
Number of pages15
JournalJournal of the American Statistical Association
Volume110
Issue number509
DOIs
StatePublished - Jan 2 2015
Externally publishedYes

Fingerprint

Smoothing Splines
Categorical
Computational Model
Calibration
Output
Model
Computer Model
Absorber
Fluid Model
Computational Fluid Dynamics
Gaussian Process
Alternate
Computational Efficiency
Discrepancy
Dynamic Model
Physics
Analysis of variance
Computational model
Smoothing splines
Experimental Data

Keywords

  • Categorical inputs
  • Emulator
  • Inverse problem
  • Model calibration
  • Multiple outputs
  • Uncertainty quantification

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Calibration of Computational Models With Categorical Parameters and Correlated Outputs via Bayesian Smoothing Spline ANOVA. / Storlie, Curtis; Lane, William A.; Ryan, Emily M.; Gattiker, James R.; Higdon, David M.

In: Journal of the American Statistical Association, Vol. 110, No. 509, 02.01.2015, p. 68-82.

Research output: Contribution to journalArticle

Storlie, Curtis ; Lane, William A. ; Ryan, Emily M. ; Gattiker, James R. ; Higdon, David M. / Calibration of Computational Models With Categorical Parameters and Correlated Outputs via Bayesian Smoothing Spline ANOVA. In: Journal of the American Statistical Association. 2015 ; Vol. 110, No. 509. pp. 68-82.
@article{0aff94cad3214b9f8a701be546fcdd65,
title = "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 need to be calibrated and validated using some experimental data, which often consists of multiple correlated outcomes. In addition, some of the model parameters may be categorical in nature, such as a pointer variable to alternate models (or submodels) for some of the physics of the system. Here, we present a general approach for calibration in such situations where an emulator of the computationally demanding models and a discrepancy term from the model to reality are represented within a Bayesian smoothing spline (BSS) ANOVA framework. The BSS-ANOVA framework has several advantages over the traditional Gaussian process, including ease of handling categorical inputs and correlated outputs, and improved computational efficiency. Finally, this framework is then applied to the problem that motivated its design; a calibration of a computational fluid dynamics (CFD) model of a bubbling fluidized which is used as an absorber in a CO2 capture system. Supplementary materials for this article are available online.",
keywords = "Categorical inputs, Emulator, Inverse problem, Model calibration, Multiple outputs, Uncertainty quantification",
author = "Curtis Storlie and Lane, {William A.} and Ryan, {Emily M.} and Gattiker, {James R.} and Higdon, {David M.}",
year = "2015",
month = "1",
day = "2",
doi = "10.1080/01621459.2014.979993",
language = "English (US)",
volume = "110",
pages = "68--82",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "509",

}

TY - JOUR

T1 - Calibration of Computational Models With Categorical Parameters and Correlated Outputs via Bayesian Smoothing Spline ANOVA

AU - Storlie, Curtis

AU - Lane, William A.

AU - Ryan, Emily M.

AU - Gattiker, James R.

AU - Higdon, David M.

PY - 2015/1/2

Y1 - 2015/1/2

N2 - It has become commonplace to use complex computer models to predict outcomes in regions where data do not exist. Typically these models need to be calibrated and validated using some experimental data, which often consists of multiple correlated outcomes. In addition, some of the model parameters may be categorical in nature, such as a pointer variable to alternate models (or submodels) for some of the physics of the system. Here, we present a general approach for calibration in such situations where an emulator of the computationally demanding models and a discrepancy term from the model to reality are represented within a Bayesian smoothing spline (BSS) ANOVA framework. The BSS-ANOVA framework has several advantages over the traditional Gaussian process, including ease of handling categorical inputs and correlated outputs, and improved computational efficiency. Finally, this framework is then applied to the problem that motivated its design; a calibration of a computational fluid dynamics (CFD) model of a bubbling fluidized which is used as an absorber in a CO2 capture system. Supplementary materials for this article are available online.

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

KW - Categorical inputs

KW - Emulator

KW - Inverse problem

KW - Model calibration

KW - Multiple outputs

KW - Uncertainty quantification

UR - http://www.scopus.com/inward/record.url?scp=84928248310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928248310&partnerID=8YFLogxK

U2 - 10.1080/01621459.2014.979993

DO - 10.1080/01621459.2014.979993

M3 - Article

AN - SCOPUS:84928248310

VL - 110

SP - 68

EP - 82

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 509

ER -