.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "examples/05_kriging/10_simple_collocated_cokriging.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_examples_05_kriging_10_simple_collocated_cokriging.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_examples_05_kriging_10_simple_collocated_cokriging.py:


Simple Collocated Cokriging
----------------------------

Simple collocated cokriging uses secondary data at the estimation location
to improve the primary variable estimate.

This example demonstrates the correlogram-based API using MarkovModel1,
which encapsulates the Markov Model I (MM1) cross-covariance structure.

Example
^^^^^^^

Here we compare Simple Kriging with Simple Collocated Cokriging using the
MarkovModel1 correlogram.

.. GENERATED FROM PYTHON SOURCE LINES 17-31

.. code-block:: Python


    import matplotlib.pyplot as plt
    import numpy as np

    from gstools import Gaussian, MarkovModel1, krige
    from gstools.cokriging import SimpleCollocated

    # condtions
    np.random.seed(4)
    cond_pos = np.array([0.5, 2.1, 3.8, 6.2, 13.5])
    cond_val = np.array([0.8, 1.2, 1.8, 2.1, 1.4])
    gridx = np.linspace(0.0, 15.0, 151)
    model = Gaussian(dim=1, var=0.5, len_scale=2.0)








.. GENERATED FROM PYTHON SOURCE LINES 32-33

Generate correlated secondary data

.. GENERATED FROM PYTHON SOURCE LINES 33-43

.. code-block:: Python


    sec_pos = np.linspace(0, 15, 31)
    primary_trend = np.interp(sec_pos, cond_pos, cond_val)
    gap_feature = -1.6 * np.exp(-(((sec_pos - 10.0) / 2.0) ** 2))
    gap_feature2 = -0.95 * np.exp(-(((sec_pos - 4.0) / 2.0) ** 2))
    sec_val = 0.99 * primary_trend + gap_feature + gap_feature2

    sec_grid = np.interp(gridx, sec_pos, sec_val)
    sec_at_primary = np.interp(cond_pos, sec_pos, sec_val)








.. GENERATED FROM PYTHON SOURCE LINES 44-45

Simple Kriging and Simple Collocated Cokriging

.. GENERATED FROM PYTHON SOURCE LINES 45-65

.. code-block:: Python


    sk = krige.Simple(model, cond_pos=cond_pos, cond_val=cond_val, mean=1.0)
    sk_field, sk_var = sk(gridx, return_var=True)

    # Compute cross-correlation from data
    cross_corr = np.corrcoef(cond_val, sec_at_primary)[0, 1]

    # Create MarkovModel1 correlogram
    correlogram = MarkovModel1(
        primary_model=model,
        cross_corr=cross_corr,
        secondary_var=np.var(sec_val),
        primary_mean=1.0,
        secondary_mean=np.mean(sec_val),
    )

    # Simple Collocated Cokriging
    scck = SimpleCollocated(correlogram, cond_pos=cond_pos, cond_val=cond_val)
    scck_field, scck_var = scck(gridx, secondary_data=sec_grid, return_var=True)








.. GENERATED FROM PYTHON SOURCE LINES 66-87

.. code-block:: Python


    fig, ax = plt.subplots(1, 2, figsize=(10, 3.5))

    ax[0].scatter(cond_pos, cond_val, color="red", label="Primary data")
    ax[0].scatter(
        cond_pos,
        sec_at_primary,
        color="blue",
        marker="s",
        label="Secondary at primary",
    )
    ax[0].plot(sec_pos, sec_val, "b-", alpha=0.6, label="Secondary data")
    ax[0].legend()

    ax[1].plot(gridx, sk_field, label="Simple Kriging")
    ax[1].plot(gridx, scck_field, label="Simple Collocated Cokriging")
    ax[1].scatter(cond_pos, cond_val, color="k", zorder=10, label="Conditions")
    ax[1].legend()

    plt.tight_layout()
    plt.show()



.. image-sg:: /examples/05_kriging/images/sphx_glr_10_simple_collocated_cokriging_001.png
   :alt: 10 simple collocated cokriging
   :srcset: /examples/05_kriging/images/sphx_glr_10_simple_collocated_cokriging_001.png
   :class: sphx-glr-single-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 0.189 seconds)


.. _sphx_glr_download_examples_05_kriging_10_simple_collocated_cokriging.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: 10_simple_collocated_cokriging.ipynb <10_simple_collocated_cokriging.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: 10_simple_collocated_cokriging.py <10_simple_collocated_cokriging.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: 10_simple_collocated_cokriging.zip <10_simple_collocated_cokriging.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_