ILNumerics - Technical Application Development
Assembly: ILNumerics.Toolboxes.Interpolation (in ILNumerics.Toolboxes.Interpolation.dll) Version: 5.5.0.0 (5.5.7503.3146)
Interpolated values for each point (column) provided in Xn
Kriging interpolation learns a hidden function from the given data based on statistical properties of the data. Kriging is well suited for scattered data interpolation.
Kriging interpolation from scattered data
[ILNumerics Interpolation Toolbox]
Namespace: ILNumerics.Toolboxes
Assembly: ILNumerics.Toolboxes.Interpolation (in ILNumerics.Toolboxes.Interpolation.dll) Version: 5.5.0.0 (5.5.7503.3146)
Syntax
public static RetArray<complex> kriging( InArray<complex> V, InArray<double> X, InArray<double> Xn, Func<InArray<double>, RetArray<double>> variogram = null, OutArray<double> error = null )
Parameters
- V
- Type: ILNumericsInArraycomplex
Data values, matrix with measured values at the n data points provided by X. Size [k x n]. - X
- Type: ILNumericsInArrayDouble
Data points, matrix with sample locations of dimension m in n columns. At least 2 samples must be provided. - Xn
- Type: ILNumericsInArrayDouble
New points to compute interpolated values for. The format corresponds to the X parameter. Size [k x l]. - variogram (Optional)
- Type: SystemFuncInArrayDouble, RetArrayDouble
[Optional] Variogram function of the euclidian distances. Default: PowerLawVariogram(InArrayDouble) - error (Optional)
- Type: ILNumericsOutArrayDouble
[Optional] if not null on input error information will be returned.
Return Value
Type: RetArraycomplexInterpolated values for each point (column) provided in Xn
Exceptions
Exception | Condition |
---|---|
ArgumentException | is thrown if either of X or V are null or do not have matching sizes. |
ArgumentException | if too few points are provided or all provided points X are too close to each other so that no reliable interpolation can be performed. |
Remarks
The interpolation is based on the geometrical relation of the points provided in X. The algorithm will remove any points being too close to each in order to increase stability of the algorithm.
While the default variogram function is fine in most situations one can provide a custom variogram function to the interpolation.
More details are found in the online documentation.
[ILNumerics Interpolation Toolbox]
See Also