![]() |
Dakota Reference Manual
Version 6.16
Explore and Predict with Confidence
|
Specification of an unordered ensemble of low-fidelity approximations
Alias: approximation_models
Argument(s): STRINGLIST
A non_hierarchical surrogate model manages an unordered set of low-fidelity model approximations, each of which may include hyper-parameter resolution controls (in the case of a simulation model) or additional model recursions.
Any corresponding sequence specifications within methods (e.g., quadrature_order_sequence, sparse_grid_level_sequence, expansion_order_sequence, etc. within stochastic expansion methods) should be synchronized with the order in the model listing.
Internal to the non-hierarchical model, subsets of the model ensemble may be active for any given evaluation, as dictated by the iterative algorithm in use.
model,
id_model = 'NONHIERARCH'
surrogate non_hierarchical
unordered_model_fidelities = 'LF1' 'LF2'
truth_model_pointer = 'HF'
model,
id_model = 'LF1'
simulation
interface_pointer = 'LF1_DRIVER'
solution_level_cost = 1.
model,
id_model = 'LF2'
simulation
interface_pointer = 'LF2_DRIVER'
solution_level_cost = 2.4
model,
id_model = 'HF'
simulation
interface_pointer = 'HF_DRIVER'
solution_level_cost = 256.
These keywords may also be of interest: