Hi R community
I need to interpolate precipitation data for a natural park. I have
precipitation data from some climate stationts. (I know the table is not
complete but I only need to show you X,Y, Altitude and PrepJul)
X
Y
Altitude
PrepJan
PrepFeb
PrepMar
PrepAp
PrepMay
PrepJun
PrepJul
597706
4093438
41
0
9
77,8
63,1
17,5
0
2,6
597535
4088967
202
0
11,3
67,9
70,8
12,1
0
0,6
572307
4064892
41
1
9,5
22
40,5
2,5
0
0
571059
4074743
50
2,4
13,9
31,3
63,3
8,1
0
1,4
570795
4091537
356
0
15
79
86
19,5
1
0
554563
4077703
20
5,2
15,6
43,4
64,5
15
0,2
0
575091
4089921
183
1,2
13,2
64,6
70,6
16,2
0,2
3,4
The area where this data must be interpolated in the natural park with an
irregular shape inside of a grid of 2190 lines and 2282 columns with utm
coordinates. I have tried "Krig" from "fields" package. A created a matrix with
independant data (a) and a vector with dependant data (b).
a<-matrix(c(clima$X,clima$Y,clima$Altitud),,3)
b<-clima$PrepJul
Interpolation<-Krig(a,b)
mapa<-predict.surface(interpolacion, nx=2190, ny=2282)
str(mapa)
num [1:2190] 554563 554583 554602 554622 554642 ...
$ y: num [1:2282] 4064892 4064905 4064917 4064930 4064942 ...
$ z: num [1:2190, 1:2282] NA NA NA NA NA NA NA NA NA NA ...
NA values are due to the fact that outside of the natural park there isn't
precipitation registred. NA values are not a problem.
I write the result to ENVI with "write.ENVI" from "Catools" package. And the
result is an image but data interpolated don't follow the natural park limits,
the image of interpolated data don't macht the area of the natural park. And I
don't know how to solve this. If anyone know any possible reason or any
suggestion to do an interpolation, I would be really grateful.
Lucas
_________________________________________________________________
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
