skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models

Abstract

For many real systems, several computer models may exist with different physics and predictive abilities. To achieve more accurate simulations/predictions, it is desirable for these models to be properly combined and calibrated. We propose the Bayesian calibration of computer model mixture method which relies on the idea of representing the real system output as a mixture of the available computer model outputs with unknown input dependent weight functions. The method builds a fully Bayesian predictive model as an emulator for the real system output by combining, weighting, and calibrating the available models in the Bayesian framework. Moreover, it fits a mixture of calibrated computer models that can be used by the domain scientist as a mean to combine the available computer models, in a flexible and principled manner, and perform reliable simulations. It can address realistic cases where one model may be more accurate than the others at different input values because the mixture weights, indicating the contribution of each model, are functions of the input. Inference on the calibration parameters can consider multiple computer models associated with different physics. The method does not require knowledge of the fidelity order of the models. We provide a technique able to mitigatemore » the computational overhead due to the consideration of multiple computer models that is suitable to the mixture model framework. We implement the proposed method in a real-world application involving the Weather Research and Forecasting large-scale climate model.« less

Authors:
 [1]; ORCiD logo [2]
  1. Durham University, Durham (United Kingdom). Department of Mathematical Sciences
  2. Purdue University, West Lafayette, IN (United States). Department of Mathematics, School of Mechanical Engineering
Publication Date:
Research Org.:
Lawrence Berkeley National Laboratory, Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC).
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
OSTI Identifier:
1463648
Resource Type:
Journal Article
Resource Relation:
Journal Name: Journal of Computational Physics; Journal Volume: 342; Journal Issue: C
Country of Publication:
United States
Language:
English

Citation Formats

Karagiannis, Georgios, and Lin, Guang. On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models. United States: N. p., 2017. Web. doi:10.1016/j.jcp.2017.04.003.
Karagiannis, Georgios, & Lin, Guang. On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models. United States. doi:10.1016/j.jcp.2017.04.003.
Karagiannis, Georgios, and Lin, Guang. Tue . "On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models". United States. doi:10.1016/j.jcp.2017.04.003.
@article{osti_1463648,
title = {On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models},
author = {Karagiannis, Georgios and Lin, Guang},
abstractNote = {For many real systems, several computer models may exist with different physics and predictive abilities. To achieve more accurate simulations/predictions, it is desirable for these models to be properly combined and calibrated. We propose the Bayesian calibration of computer model mixture method which relies on the idea of representing the real system output as a mixture of the available computer model outputs with unknown input dependent weight functions. The method builds a fully Bayesian predictive model as an emulator for the real system output by combining, weighting, and calibrating the available models in the Bayesian framework. Moreover, it fits a mixture of calibrated computer models that can be used by the domain scientist as a mean to combine the available computer models, in a flexible and principled manner, and perform reliable simulations. It can address realistic cases where one model may be more accurate than the others at different input values because the mixture weights, indicating the contribution of each model, are functions of the input. Inference on the calibration parameters can consider multiple computer models associated with different physics. The method does not require knowledge of the fidelity order of the models. We provide a technique able to mitigate the computational overhead due to the consideration of multiple computer models that is suitable to the mixture model framework. We implement the proposed method in a real-world application involving the Weather Research and Forecasting large-scale climate model.},
doi = {10.1016/j.jcp.2017.04.003},
journal = {Journal of Computational Physics},
number = C,
volume = 342,
place = {United States},
year = {Tue Aug 01 00:00:00 EDT 2017},
month = {Tue Aug 01 00:00:00 EDT 2017}
}