--- Begin Message ---
Hi,
Kanishka Perera wrote:
> Dear Netters,
> My research is based on gas migration in soil using kriging
> interpolation techniques. Right now I am at a stage of developing a
> primary model. My data measurement (sampling) points are not point
> measurements but is averaged to a area considered. The reason why I
> cannot approximate area measurements to point measurements is my kriging
> grid size is same as the sampling area size. Therefore the only kriging
> method applicable to my problem is block to block covariances. Through
> the gstat user's manual I came to know that gstat is capable of
> estimating block to block covariances. My problem is how to use the
> gstat software determine block to block estimates. If some one has any
> example that has been used before is highly appreciated. Also let me
> know whether the example of command file given in Ex 8 in user's manual
> is for point to block or block to block covariances.
>
Ex 8 is for 'point' to block kriging. It is assumed your data points are
point estimates and the predictions made will be predictions for blocks of
40 by 40 in size. But I think if you have measurements with a considerable
support (sampling size) you can do ordinary point kriging (without defining
a block size). Your predictions will have the same support as the support
of your (measurement) data - point kriging does not change the support.
Derk
>
> Thanks!
> Kanishka Perera
--
Derk Jan 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 (new)
or d.karssenberg@frw.ruu.nl (old)
http://www.frw.ruu.nl/pcraster.html
--- End Message ---