rotateAnisotropicData {intamap} | R Documentation |
This function applies an isotropic transformation of
the coordinates specified in object
.
rotateAnisotropicData(object,anisPar)
object |
(i) An Intamap type object (see intamap-package )
containing one SpatialPointsDataFrame
data frame named observations which includes the observed values (ii) or a
SpatialPointsDataFrame
which includes both coordinates and observations or (iii) SpatialPoints which includes only
coordinates to be rotated. |
anisPar |
An array containing the anisotropy parameters (anisotropy ratio and axes orientation)
(see estimateAnisotropy ) for the rotation.
If object is the output of estimateAnisotropy function, these parameters are part of object .
In cases (ii) and (iii) anisPar defines the two anisotropy
parameters. For the definition of the anisotropy parameters see estimateAnisotropy . |
This function performs a rotation and rescaling of the
coordinate axes in order to obtain a new coordinate system, in which
the observations become statistically isotropic. This assumes that
the estimates of the anisotropy ratio and the orientation angle
provided in anisPar
are accurate.
(i) A modified object with transformed coordinates if
rotateAnisotropicData is called with an Intamap object as input (see
intamap-package
) or (ii) the transformed coordinates if a
SpatialPointsDataFrame
is used as input or (iii)
the transformed coordinates if a SpatialPoints
object is the input.
Hristopulos Dionisis, Spiliopoulos Giannis
[1] http://www.intamap.org
[2] A. Chorti and D. T. Hristopulos (2008). Non-parametric Identification of Anisotropic (Elliptic) Correlations in Spatially Distributed Data Sets, IEEE Transactions on Signal Processing, 56(10), 4738-4751 (2008).
estimateAnisotropy
library(gstat) data(sic2004) coordinates(sic.val)=~x+y sic.val$value=sic.val$dayx anisPar <- estimateAnisotropy(sic.val) print(anisPar) rotatedObs <- rotateAnisotropicData(sic.val,anisPar) newAnisPar <- estimateAnisotropy(rotatedObs) print(newAnisPar)