Parameterdependent modelblending with multiexpert based machine learning and proxy sites
Abstract
A parameterbased multimodel blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameterbased blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a subrange for each of the critical parameters.
 Inventors:
 Issue Date:
 Research Org.:
 International Business Machines Corp., Armonk, NY (United States)
 Sponsoring Org.:
 USDOE
 OSTI Identifier:
 1637838
 Patent Number(s):
 10592817
 Application Number:
 14/797,777
 Assignee:
 International Business Machines Corporation (Armonk, NY)
 Patent Classifications (CPCs):

G  PHYSICS G06  COMPUTING G06N  COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G  PHYSICS G06  COMPUTING G06F  ELECTRIC DIGITAL DATA PROCESSING
 DOE Contract Number:
 EE0006017
 Resource Type:
 Patent
 Resource Relation:
 Patent File Date: 07/13/2015
 Country of Publication:
 United States
 Language:
 English
 Subject:
 97 MATHEMATICS AND COMPUTING
Citation Formats
Hamann, Hendrik F., Hwang, Youngdeok, Klein, Levente, Lenchner, Jonathan, Lu, Siyuan, Marianno, Fernando J., Tesauro, Gerald J., and van Kessel, Theodore G. Parameterdependent modelblending with multiexpert based machine learning and proxy sites. United States: N. p., 2020.
Web.
Hamann, Hendrik F., Hwang, Youngdeok, Klein, Levente, Lenchner, Jonathan, Lu, Siyuan, Marianno, Fernando J., Tesauro, Gerald J., & van Kessel, Theodore G. Parameterdependent modelblending with multiexpert based machine learning and proxy sites. United States.
Hamann, Hendrik F., Hwang, Youngdeok, Klein, Levente, Lenchner, Jonathan, Lu, Siyuan, Marianno, Fernando J., Tesauro, Gerald J., and van Kessel, Theodore G. Tue .
"Parameterdependent modelblending with multiexpert based machine learning and proxy sites". United States. https://www.osti.gov/servlets/purl/1637838.
@article{osti_1637838,
title = {Parameterdependent modelblending with multiexpert based machine learning and proxy sites},
author = {Hamann, Hendrik F. and Hwang, Youngdeok and Klein, Levente and Lenchner, Jonathan and Lu, Siyuan and Marianno, Fernando J. and Tesauro, Gerald J. and van Kessel, Theodore G.},
abstractNote = {A parameterbased multimodel blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameterbased blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a subrange for each of the critical parameters.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2020},
month = {3}
}