Dakota Reference Manual
Version 6.16
Explore and Predict with Confidence

A Dakota input file is a collection of fields from the dakota.input.summary file that describe the problem to be solved by Dakota. Several brief examples follow below.
Dakota 6.14 and newer include a refreshed Examples Library, ranging from examples of Dakota input files and basic studies through complete case studies. These can be found in binary distributions in dakota/share/dakota/examples/official
(dakota/dakotaexamples
in source distributions). Legacy examples, including many from the Dakota software manuals appear in other directories in dakota/share/dakota/examples
(dakota/examples
for source).
Sample 1: Optimization
The following sample input file shows singlemethod optimization of the Textbook Example (see Textbook) using DOT's modified method of feasible directions. A similar file is available as dakota/share/dakota/examples/users/textbook_opt_conmin.in
.
# Dakota Input File: textbook_opt_conmin.in environment tabular_data tabular_data_file = 'textbook_opt_conmin.dat' method # dot_mmfd #DOT performs better but may not be available conmin_mfd max_iterations = 50 convergence_tolerance = 1e4 variables continuous_design = 2 initial_point 0.9 1.1 upper_bounds 5.8 2.9 lower_bounds 0.5 2.9 descriptors 'x1' 'x2' interface direct analysis_driver = 'text_book' responses objective_functions = 1 nonlinear_inequality_constraints = 2 numerical_gradients method_source dakota interval_type central fd_gradient_step_size = 1.e4 no_hessians
Sample 2: Least Squares (Calibration)
The following sample input file shows a nonlinear least squares (calibration) solution of the Rosenbrock Example (see Rosenbrock) using the NL2SOL method. A similar file is available as dakota/share/dakota/examples/users/rosen_opt_nls.in
# Dakota Input File: rosen_opt_nls.in environment tabular_data tabular_data_file = 'rosen_opt_nls.dat' method max_iterations = 100 convergence_tolerance = 1e4 nl2sol model single variables continuous_design = 2 initial_point 1.2 1.0 lower_bounds 2.0 2.0 upper_bounds 2.0 2.0 descriptors 'x1' "x2" interface analysis_driver = 'rosenbrock' direct responses calibration_terms = 2 analytic_gradients no_hessians
Sample 3: Nondeterministic Analysis
The following sample input file shows Latin Hypercube Monte Carlo sampling using the Textbook Example (see Textbook). A similar file is available as dakota/share/dakota/test/dakota_uq_textbook_lhs.in
.
method, sampling, samples = 100 seed = 1 complementary distribution response_levels = 3.6e+11 4.0e+11 4.4e+11 6.0e+04 6.5e+04 7.0e+04 3.5e+05 4.0e+05 4.5e+05 sample_type lhs variables, normal_uncertain = 2 means = 248.89, 593.33 std_deviations = 12.4, 29.7 descriptors = 'TF1n' 'TF2n' uniform_uncertain = 2 lower_bounds = 199.3, 474.63 upper_bounds = 298.5, 712. descriptors = 'TF1u' 'TF2u' weibull_uncertain = 2 alphas = 12., 30. betas = 250., 590. descriptors = 'TF1w' 'TF2w' histogram_bin_uncertain = 2 num_pairs = 3 4 abscissas = 5 8 10 .1 .2 .3 .4 counts = 17 21 0 12 24 12 0 descriptors = 'TF1h' 'TF2h' histogram_point_uncertain = 1 num_pairs = 2 abscissas = 3 4 counts = 1 1 descriptors = 'TF3h' interface, fork asynch evaluation_concurrency = 5 analysis_driver = 'text_book' responses, response_functions = 3 no_gradients no_hessians
Sample 4: Parameter Study
The following sample input file shows a 1D vector parameter study using the Textbook Example (see Textbook). It makes use of the default environment and model specifications, so they can be omitted. A similar file is available in the test directory as dakota/share/dakota/examples/users/rosen_ps_vector.in
.
# Dakota Input File: rosen_ps_vector.in environment tabular_data tabular_data_file = 'rosen_ps_vector.dat' method vector_parameter_study final_point = 1.1 1.3 num_steps = 10 variables continuous_design = 2 initial_point 0.3 0.2 descriptors 'x1' "x2" interface analysis_driver = 'rosenbrock' direct responses objective_functions = 1 no_gradients no_hessians
Sample 5: Hybrid Strategy
The following sample input file shows a hybrid environment using three methods. It employs a genetic algorithm, pattern search, and full Newton gradientbased optimization in succession to solve the Textbook Example (see Textbook). A similar file is available as dakota/share/dakota/examples/users/textbook_hybrid_strat.in
.
environment hybrid sequential method_list = 'PS' 'PS2' 'NLP' method id_method = 'PS' model_pointer = 'M1' coliny_pattern_search stochastic seed = 1234 initial_delta = 0.1 variable_tolerance = 1.e4 solution_accuracy = 1.e10 exploratory_moves basic_pattern #verbose output method id_method = 'PS2' model_pointer = 'M1' max_function_evaluations = 10 coliny_pattern_search stochastic seed = 1234 initial_delta = 0.1 variable_tolerance = 1.e4 solution_accuracy = 1.e10 exploratory_moves basic_pattern #verbose output method id_method = 'NLP' model_pointer = 'M2' optpp_newton gradient_tolerance = 1.e12 convergence_tolerance = 1.e15 #verbose output model id_model = 'M1' single variables_pointer = 'V1' interface_pointer = 'I1' responses_pointer = 'R1' model id_model = 'M2' single variables_pointer = 'V1' interface_pointer = 'I1' responses_pointer = 'R2' variables id_variables = 'V1' continuous_design = 2 initial_point 0.6 0.7 upper_bounds 5.8 2.9 lower_bounds 0.5 2.9 descriptors 'x1' 'x2' interface id_interface = 'I1' direct analysis_driver= 'text_book' responses id_responses = 'R1' objective_functions = 1 no_gradients no_hessians responses id_responses = 'R2' objective_functions = 1 analytic_gradients analytic_hessians
Additional example input files, as well as the corresponding output, are provided in the Tutorial chapter of the Users Manual [4].