.. _method-global_reliability-experimental:

""""""""""""
experimental
""""""""""""


Use the experimental Gaussian Process surrogate


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

   method-global_reliability-experimental-export_model
   method-global_reliability-experimental-options_file


**Specification**

- *Alias:* None

- *Arguments:* None


**Child Keywords:**

+-------------------------+--------------------+--------------------+---------------------------------------------+
| Required/Optional       | Description of     | Dakota Keyword     | Dakota Keyword Description                  |
|                         | Group              |                    |                                             |
+=========================+====================+====================+=============================================+
| Optional                                     | `export_model`__   | Exports surrogate model in user-specified   |
|                                              |                    | format(s)                                   |
+----------------------------------------------+--------------------+---------------------------------------------+
| Optional                                     | `options_file`__   | Filename for a YAML file that specifies     |
|                                              |                    | Gaussian process options                    |
+----------------------------------------------+--------------------+---------------------------------------------+

.. __: method-global_reliability-experimental-export_model.html
__ method-global_reliability-experimental-options_file.html



**Description**


The experimental GP surrogate is an emerging capability intended to
supersede the ``dakota`` and ``surfpack`` GP implementations by unifying
the best features of both. It also includes additional features such
as the ability to export the model and then use it from Python.