InterpNd ND interpolation from raw data
=InterpNd(Method, Scaling, xValues, fValues, xStar, SubKriging)
Parameters
Method: Interpolation method
- −3 = Natural-neighbors (available in 2D)
- −2 = Akima (available in 1D)
- −1 = Linear (available in 1D)
- 0 = Nearest-neighbor
- 1 to 1.99 = Kriging (1.5 is a good choice)
Scaling: Scaling of parameters
- 0 = If parameters are homogeneous (no scaling)
- 1 = If parameters are NOT homogeneous (e.g. for black box model)
xValues: Function parameters values
fValues: Function values
xStar: Parameters value(s) to interpolate
SubKriging: [Optional for Kriging i.e. if 1 ≤ Method ≤ 1.99]
- If positive = Number of nearest points to select (1+nDim ≤ SubKriging ≤ 1024, SubKriging = 256 is a good choice)
- If negative = −Distance for selection of nearest points (SubKriging < 0)
If the SubKriging parameter is missing, all points will be used for Kriging interpolation.
If Scaling = 1, the distance for selection of nearest points is calculated in the normalised space (see main page for details).