emulator

Use an emulator or surrogate model to evaluate the likelihood function

Specification

• Alias: None

• Arguments: None

Child Keywords:

Required/Optional	Description of Group	Dakota Keyword	Dakota Keyword Description
Required (Choose One)	Emulator Type	gaussian_process	Gaussian Process surrogate model
		pce	Polynomial Chaos Expansion surrogate model
		ml_pce	Multilevel Polynomial Chaos Expansion as an emulator model.
		mf_pce	Multifidelity Polynomial Chaos Expansion as an emulator model.
		sc	Stochastic Collocation as an emulator model.
		mf_sc	Multifidelity Stochastic Collocation as an emulator model.

Description

This keyword describes the type of emulator used when calculating the likelihood function for the Bayesian calibration. The emulator can be a Gaussian process, polynomial chaos expansion, or stochastic collocation.