Point Kriging

kriging(observations, theoretical_model, points, how='ok', neighbors_range=None, no_neighbors=4, use_all_neighbors_in_range=False, sk_mean=None, allow_approx_solutions=False, number_of_workers=1, show_progress_bar=True)

Function manages Ordinary Kriging and Simple Kriging predictions.

Parameters:

observationsnumpy array

Known points and their values.

theoretical_modelTheoreticalVariogram

Fitted variogram model.

pointsnumpy array

Coordinates with missing values (to estimate results).

howstr, default=’ok’

Select what kind of kriging you want to perform:

• ‘ok’: ordinary kriging,

• ‘sk’: simple kriging - if it is set then sk_mean parameter must be provided.

neighbors_rangefloat, default=None

The maximum distance where we search for neighbors. If None is given then range is selected from the theoretical_model rang attribute.

no_neighborsint, default = 4

The number of the n-closest neighbors used for interpolation.

use_all_neighbors_in_rangebool, default = False

True: if the real number of neighbors within the neighbors_range is greater than the number_of_neighbors parameter then take all of them anyway.

sk_meanfloat, default=None

The mean value of a process over a study area. Should be know before processing. That’s why Simple Kriging has a limited number of applications. You must have multiple samples and well-known area to know this parameter.

allow_approx_solutionsbool, default=False

Allows the approximation of kriging weights based on the OLS algorithm. We don’t recommend set it to True if you don’t know what are you doing. This parameter can be useful when you have clusters in your dataset, that can lead to singular or near-singular matrix creation.

number_of_workersint, default=1

How many processing units can be used for predictions. Increase it only for a very large number of interpolated points (~10k+).

show_progress_barbool, default=True

Show progress bar of predictions.

Returns:

: numpy array

Predictions [predicted value, variance error, longitude (x), latitude (y)]

---

ordinary_kriging(theoretical_model, known_locations, unknown_location, neighbors_range=None, no_neighbors=4, use_all_neighbors_in_range=False, allow_approximate_solutions=False)

Function predicts value at unknown location with Ordinary Kriging technique.

Parameters:

theoretical_modelTheoreticalVariogram

A trained theoretical variogram model.

known_locationsnumpy array

The known locations.

unknown_locationUnion[List, Tuple, numpy array]

Point where you want to estimate value (x, y) <-> (lon, lat).

neighbors_rangefloat, default=None

The maximum distance where we search for neighbors. If None is given then range is selected from the theoretical_model rang attribute.

no_neighborsint, default = 4

The number of the n-closest neighbors used for interpolation.

use_all_neighbors_in_rangebool, default = False

True: if the real number of neighbors within the neighbors_range is greater than the number_of_neighbors parameter then take all of them anyway.

allow_approximate_solutionsbool, default=False

Allows the approximation of kriging weights based on the OLS algorithm. We don’t recommend set it to True if you don’t know what are you doing. This parameter can be useful when you have clusters in your dataset, that can lead to singular or near-singular matrix creation.

Returns:

: numpy array

[predicted value, variance error, longitude (x), latitude (y)]

Raises:

RunetimeError

Singularity matrix in a Kriging system.

---

simple_kriging(theoretical_model, known_locations, unknown_location, process_mean, neighbors_range=None, no_neighbors=1, use_all_neighbors_in_range=False, allow_approximate_solutions=False)

Function predicts value at unknown location with Ordinary Kriging technique.

Parameters:

theoretical_modelTheoreticalVariogram

A trained theoretical variogram model.

known_locationsnumpy array

The known locations.

unknown_locationUnion[List, Tuple, numpy array]

Point where you want to estimate value (x, y) <-> (lon, lat).

process_meanfloat

The mean value of a process over a study area. Should be know before processing. That’s why Simple Kriging has a limited number of applications. You must have multiple samples and well-known area to know this parameter.

neighbors_rangefloat, default=None

The maximum distance where we search for neighbors. If None is given then range is selected from the theoretical_model rang attribute.

no_neighborsint, default = 4

The number of the n-closest neighbors used for interpolation.

use_all_neighbors_in_rangebool, default = False

True: if the real number of neighbors within the neighbors_range is greater than the number_of_neighbors parameter then take all of them anyway.

allow_approximate_solutionsbool, default=False

Allows the approximation of kriging weights based on the OLS algorithm. We don’t recommend set it to True if you don’t know what are you doing. This parameter can be useful when you have clusters in your dataset, that can lead to singular or near-singular matrix creation.

Returns:

: numpy array

[predicted value, variance error, longitude (x), latitude (y)]

Raises:

RunetimeError

Singularity matrix in a Kriging system.