Nonparametric functional calibration of computer models

D. Andrew Brown, Sez Atamturktur

Research output: Contribution to journalEditorial

2 Citations (Scopus)

Abstract

Standard methods in computer model calibration treat the calibration parameters as constant throughout the domain of control inputs. In many applications, systematic variation may cause the best values for the calibration parameters to change across different settings. When not accounted for in the code, this variation can make the computer model inadequate. We propose a framework for modeling the calibration parameters as functions of the control inputs to account for a computer model's incomplete system representation in this regard, while simultaneously allowing for possible constraints imposed by prior expert opinion. We demonstrate how inappropriate modeling assumptions can mislead a researcher into thinking a calibrated model is in need of an empirical discrepancy term when it is only needed to allow for a functional dependence of the calibration parameters on the inputs. We apply our approach to plastic deformation of a visco-plastic self-consistent material in which the critical resolved shear stress is known to vary with temperature.

Original languageEnglish (US)
Pages (from-to)721-742
Number of pages22
JournalStatistica Sinica
Volume28
Issue number2
DOIs
StatePublished - Apr 2018

Fingerprint

Computer Model
Calibration
Expert Opinion
Model Calibration
Plastic Deformation
Shear Stress
Modeling
Discrepancy
Plastics
Vary
Term
Demonstrate
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Andrew Brown, D. ; Atamturktur, Sez. / Nonparametric functional calibration of computer models. In: Statistica Sinica. 2018 ; Vol. 28, No. 2. pp. 721-742.
@article{7df34d17558c4b11beb6d7000844dcb5,
title = "Nonparametric functional calibration of computer models",
abstract = "Standard methods in computer model calibration treat the calibration parameters as constant throughout the domain of control inputs. In many applications, systematic variation may cause the best values for the calibration parameters to change across different settings. When not accounted for in the code, this variation can make the computer model inadequate. We propose a framework for modeling the calibration parameters as functions of the control inputs to account for a computer model's incomplete system representation in this regard, while simultaneously allowing for possible constraints imposed by prior expert opinion. We demonstrate how inappropriate modeling assumptions can mislead a researcher into thinking a calibrated model is in need of an empirical discrepancy term when it is only needed to allow for a functional dependence of the calibration parameters on the inputs. We apply our approach to plastic deformation of a visco-plastic self-consistent material in which the critical resolved shear stress is known to vary with temperature.",
author = "{Andrew Brown}, D. and Sez Atamturktur",
year = "2018",
month = "4",
doi = "10.5705/ss.202015.0344",
language = "English (US)",
volume = "28",
pages = "721--742",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "2",

}

Nonparametric functional calibration of computer models. / Andrew Brown, D.; Atamturktur, Sez.

In: Statistica Sinica, Vol. 28, No. 2, 04.2018, p. 721-742.

Research output: Contribution to journalEditorial

TY - JOUR

T1 - Nonparametric functional calibration of computer models

AU - Andrew Brown, D.

AU - Atamturktur, Sez

PY - 2018/4

Y1 - 2018/4

N2 - Standard methods in computer model calibration treat the calibration parameters as constant throughout the domain of control inputs. In many applications, systematic variation may cause the best values for the calibration parameters to change across different settings. When not accounted for in the code, this variation can make the computer model inadequate. We propose a framework for modeling the calibration parameters as functions of the control inputs to account for a computer model's incomplete system representation in this regard, while simultaneously allowing for possible constraints imposed by prior expert opinion. We demonstrate how inappropriate modeling assumptions can mislead a researcher into thinking a calibrated model is in need of an empirical discrepancy term when it is only needed to allow for a functional dependence of the calibration parameters on the inputs. We apply our approach to plastic deformation of a visco-plastic self-consistent material in which the critical resolved shear stress is known to vary with temperature.

AB - Standard methods in computer model calibration treat the calibration parameters as constant throughout the domain of control inputs. In many applications, systematic variation may cause the best values for the calibration parameters to change across different settings. When not accounted for in the code, this variation can make the computer model inadequate. We propose a framework for modeling the calibration parameters as functions of the control inputs to account for a computer model's incomplete system representation in this regard, while simultaneously allowing for possible constraints imposed by prior expert opinion. We demonstrate how inappropriate modeling assumptions can mislead a researcher into thinking a calibrated model is in need of an empirical discrepancy term when it is only needed to allow for a functional dependence of the calibration parameters on the inputs. We apply our approach to plastic deformation of a visco-plastic self-consistent material in which the critical resolved shear stress is known to vary with temperature.

UR - http://www.scopus.com/inward/record.url?scp=85045661775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045661775&partnerID=8YFLogxK

U2 - 10.5705/ss.202015.0344

DO - 10.5705/ss.202015.0344

M3 - Editorial

AN - SCOPUS:85045661775

VL - 28

SP - 721

EP - 742

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 2

ER -