Dakota Reference Manual  Version 6.4
Large-Scale Engineering Optimization and Uncertainty Analysis
 All Pages
analytic_covariance


Use an analytic covariance function for the purposes of generating a random field model. THIS IS AN EXPERIMENTAL CAPABILITY.

Specification

Alias: none

Argument(s): none

Required/Optional Description of Group Dakota Keyword Dakota Keyword Description
Required
(Choose One)
Group 1 squared_exponential

Specify a squared exponential covariance in the case where the random field is built from an analytic covariance functio. THIS IS AN EXPERIMENTAL CAPABILITY.

exponential

Specify an exponential covariance in the case where the random field is built from an analytic covariance functio. THIS IS AN EXPERIMENTAL CAPABILITY.

Description

As part of the capability to generate a random field representation, the user needs to specify the data used to generate the random field representation. If analytic_covariance is specified, an analytic covariance function will be used to generate instantiations of a random field over a mesh. The form of the covariance function must be specified (e.g. exponential or squared_exponential. THIS IS AN EXPERIMENTAL CAPABILITY UNDER ACTIVE DEVELOPMENT.

Default Behavior Currently, the build_source that is fully working is the dace_method_pointer. The others are not fully operational.