Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Generic sequential sampling for metamodel approximations

Conference ·
Metamodels approximate complex multivariate data sets from simulations and experiments. These data sets often are not based on an explicitly defined function. The resulting metamodel represents a complex system's behavior for subsequent analysis or optimization. Often an exhaustive data search to obtain the data for the metalnodel is impossible, so an intelligent sampling strategy is necessary. While inultiple approaches have been advocated, the majority of these approaches were developed in support of a particular class of metamodel, known as a Kriging. A more generic, cotninonsense approach to this problem allows sequential sampling techniques to be applied to other types of metamodeis. This research compares recent search techniques for Kriging inetamodels with a generic, inulti-criteria approach combined with a new type of B-spline metamodel. This B-spline metamodel is competitive with prior results obtained with a Kriging metamodel. Furthermore, the results of this research highlight several important features necessary for these techniques to be extended to more complex domains.
Research Organization:
Los Alamos National Laboratory
Sponsoring Organization:
DOE
OSTI ID:
976613
Report Number(s):
LA-UR-03-2708; DETC2003/CIE-91
Country of Publication:
United States
Language:
English