Re: About Gstat!

[Derk Jan Karssenberg <D.Karssenberg@geog.uu.nl>]

Yao Changqing wrote:

> Hi,   I am a user of Gstat. I appreciate this software and use it to
> do some research. But there is a question that I concern, can Gstat
> predict the data in 3D? If can,would you like to give me a sample.
> Thank you very much! Sincerely, Changqing Yao

Yes, this is possible, interpolation of 3D data at non-gridded
locations. Add an extra column with the z coordinates in your input file
and specify it in the data commands in your command file, for instance:

Example 4. Ordinary block kriging
#
# Local ordinary block kriging at non-gridded locations
#
data(zinc): 'zinc.eas', x=1, y=2, z=3, v=4,
min=20, max=40, radius=1000; # local neighbourhood
variogram(zinc): 2.42e+04 Nug(0) + 1.34e+05 Sph(800);
data(): 'locs.eas', x=1, y=2, z=3; # prediction locations
blocksize: dx=40, dy=40; # 40  40 block averages
set output = 'zinc_ok.out'; # ascii output file

Regards, DJ



--

Derek Karssenberg
PCRaster
Faculty of Geographical Sciences
Utrecht University
PO Box 80.115
3508 TC Utrecht
the Netherlands
Phone:  (+31) 30 2532768
Fax:    (+31) 30 2531145
E-mail: d.karssenberg@geog.uu.nl
http://www.geog.uu.nl/pcraster