mf_pce

Multifidelity Polynomial Chaos Expansion as an emulator model.

Specification

  • Alias: None

  • Arguments: None

  • JSON argument key: None

Child Keywords:

Required/Optional

Description of Group

JSON Group Key

Dakota Keyword

Dakota Keyword Description

Optional

p_refinement

Automatic polynomial order refinement

Optional

max_refinement_iterations

Maximum number of expansion refinement iterations

Optional

allocation_control

Sample allocation approach for multifidelity expansions

Optional

discrepancy_emulation

Formulation for emulation of model discrepancies.

Required (Choose One)

Coefficient Approach

coefficient_approach

quadrature_order_sequence

Sequence of quadrature orders used in a multi-stage expansion

sparse_grid_level_sequence

Sequence of sparse grid levels used in a multi-stage expansion

expansion_order_sequence

Sequence of expansion orders used in a multi-stage expansion

orthogonal_least_interpolation

Build a polynomial chaos expansion from simulation samples using orthogonal least interpolation.

Optional (Choose One)

Basis Family

basis_family

askey

Select the standardized random variables (and associated basis polynomials) from the Askey family that best match the user-specified random variables.

wiener

Use standard normal random variables (along with Hermite orthogonal basis polynomials) when transforming to a standardized probability space.

Optional

normalized

The normalized specification requests output of PCE coefficients that correspond to normalized orthogonal basis polynomials

Optional

export_expansion_file

Export the coefficients and multi-index of a Polynomial Chaos Expansion (PCE) to a file

Optional (Choose One)

Covariance Type

covariance_type

diagonal_covariance

Display only the diagonal terms of the covariance matrix

full_covariance

Display the full covariance matrix

Description

Selects a multifidelity polynomial chaos expansion (MF PCE) surrogate model to use in the Bayesian likelihood calculations. Most specification options are carried over for using MF PCE as a surrogate within the Bayesian framework.