Robust Decisionmaking Applied to Model Selection
Abstract
The scientific and engineering communities are relying more and more on numerical models to simulate everincreasingly complex phenomena. Selecting a model, from among a family of models that meets the simulation requirements, presents a challenge to modernday analysts. To address this concern, a framework is adopted anchored in infogap decision theory. The framework proposes to select models by examining the tradeoffs between prediction accuracy and sensitivity to epistemic uncertainty. The framework is demonstrated on two structural engineering applications by asking the following question: Which model, of several numerical models, approximates the behavior of a structure when parameters that define each of those models are unknown? One observation is that models that are nominally more accurate are not necessarily more robust, and their accuracy can deteriorate greatly depending upon the assumptions made. It is posited that, as reliance on numerical models increases, establishing robustness will become as important as demonstrating accuracy.
 Authors:

 Los Alamos National Laboratory
 Publication Date:
 Research Org.:
 Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
 Sponsoring Org.:
 DOE/LANL
 OSTI Identifier:
 1048366
 Report Number(s):
 LAUR1223854
TRN: US201216%%906
 DOE Contract Number:
 AC5206NA25396
 Resource Type:
 Conference
 Resource Relation:
 Conference: PSAAP Workshop on Verification, Validation, and Uncertainty Quantification ; 20120808  20120810 ; Ann Arbor, Michigan, United States
 Country of Publication:
 United States
 Language:
 English
 Subject:
 17 WIND ENERGY; 97 MATHEMATICAL METHODS AND COMPUTING; ACCURACY; COMMUNITIES; DECISION MAKING; FORECASTING; SENSITIVITY; SIMULATION; VALIDATION; VERIFICATION
Citation Formats
Hemez, Francois M. Robust Decisionmaking Applied to Model Selection. United States: N. p., 2012.
Web.
Hemez, Francois M. Robust Decisionmaking Applied to Model Selection. United States.
Hemez, Francois M. 2012.
"Robust Decisionmaking Applied to Model Selection". United States. https://www.osti.gov/servlets/purl/1048366.
@article{osti_1048366,
title = {Robust Decisionmaking Applied to Model Selection},
author = {Hemez, Francois M},
abstractNote = {The scientific and engineering communities are relying more and more on numerical models to simulate everincreasingly complex phenomena. Selecting a model, from among a family of models that meets the simulation requirements, presents a challenge to modernday analysts. To address this concern, a framework is adopted anchored in infogap decision theory. The framework proposes to select models by examining the tradeoffs between prediction accuracy and sensitivity to epistemic uncertainty. The framework is demonstrated on two structural engineering applications by asking the following question: Which model, of several numerical models, approximates the behavior of a structure when parameters that define each of those models are unknown? One observation is that models that are nominally more accurate are not necessarily more robust, and their accuracy can deteriorate greatly depending upon the assumptions made. It is posited that, as reliance on numerical models increases, establishing robustness will become as important as demonstrating accuracy.},
doi = {},
url = {https://www.osti.gov/biblio/1048366},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2012},
month = {8}
}