.. _method-bayes_calibration-dream:

"""""
dream
"""""


DREAM (DiffeRential Evolution Adaptive Metropolis)



**Topics**


bayesian_calibration


.. toctree::
   :hidden:
   :maxdepth: 1

   method-bayes_calibration-dream-chain_samples
   method-bayes_calibration-dream-seed
   method-bayes_calibration-dream-chains
   method-bayes_calibration-dream-num_cr
   method-bayes_calibration-dream-crossover_chain_pairs
   method-bayes_calibration-dream-gr_threshold
   method-bayes_calibration-dream-jump_step
   method-bayes_calibration-dream-emulator
   method-bayes_calibration-dream-standardized_space
   method-bayes_calibration-dream-export_chain_points_file


**Specification**

- *Alias:* None

- *Arguments:* None


**Child Keywords:**

+-------------------------+--------------------+------------------------------+-----------------------------------------------+
| Required/Optional       | Description of     | Dakota Keyword               | Dakota Keyword Description                    |
|                         | Group              |                              |                                               |
+=========================+====================+==============================+===============================================+
| Required                                     | `chain_samples`__            | Number of Markov Chain Monte Carlo posterior  |
|                                              |                              | samples                                       |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `seed`__                     | Seed of the random number generator           |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `chains`__                   | Number of chains in DREAM                     |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `num_cr`__                   | Number of candidate points for each           |
|                                              |                              | crossover.                                    |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `crossover_chain_pairs`__    | Number of chains used in crossover.           |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `gr_threshold`__             | Convergence tolerance for the Gelman-Rubin    |
|                                              |                              | statistic                                     |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `jump_step`__                | Number of generations a long jump step is     |
|                                              |                              | taken                                         |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `emulator`__                 | Use an emulator or surrogate model to         |
|                                              |                              | evaluate the likelihood function              |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `standardized_space`__       | Perform Bayesian inference in standardized    |
|                                              |                              | probability space                             |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `export_chain_points_file`__ | Export the MCMC chain to the specified        |
|                                              |                              | filename                                      |
+----------------------------------------------+------------------------------+-----------------------------------------------+

.. __: method-bayes_calibration-dream-chain_samples.html
__ method-bayes_calibration-dream-seed.html
__ method-bayes_calibration-dream-chains.html
__ method-bayes_calibration-dream-num_cr.html
__ method-bayes_calibration-dream-crossover_chain_pairs.html
__ method-bayes_calibration-dream-gr_threshold.html
__ method-bayes_calibration-dream-jump_step.html
__ method-bayes_calibration-dream-emulator.html
__ method-bayes_calibration-dream-standardized_space.html
__ method-bayes_calibration-dream-export_chain_points_file.html



**Description**


The DiffeRential Evolution Adaptive Metropolis algorithm is described
in :cite:p:`Vrugt`.  For the DREAM method, one can define the number of
chains used with ``chains`` (minimum 3). The total number of
generations per chain in DREAM is the number of samples ( ``samples``)
divided by the number of chains ( ``chains``).  The number of chains
randomly selected to be used in the crossover each time a crossover
occurs is ``crossover_chain_pairs``.  There is an extra adaptation
during burn-in, in which DREAM estimates a distribution of crossover
probabilities that favors large jumps over smaller ones in each of the
chains.  Normalization is required to ensure that all of the input
dimensions contribute equally. In this process, a discrete number of
candidate points for each crossover value is generated. This parameter
is ``num_cr``.  The ``gr_threshold`` is the convergence tolerance for
the Gelman-Rubin statistic which will govern the convergence of the
multiple chain process. The integer ``jump_step`` forces a long jump
every ``jump_step`` generations.  For more details about these
parameters, see :cite:p:`Vrugt`.

*Attention:* While the ``emulator`` specification for DREAM
includes the keyword posterior_adaptive, it is not yet operational.