Hello,
As a learning experience I have made a kriger in R and have been exploring
different variogram models. I really like the speed and simplicity of
entering data to the gstat package which solves much faster than my toy
kriger. I have taken a brief look at the gstat C source code where the
variogram functions are defined and would like to dig into this deeper.
Does anyone have experience or advice on how to implement your own
variogram models in gstat? In Multivariable geostatistics in S: the gstat
package (Edzer J. Pebesma, 2004) it states that it is straightforward but I
haven't been able to get too far yet.
Alternatively, is it possible to directly specify the covariance matrices
directly (mine tend to be sparse) to gstat for solving.
Thank you for any help you may have!
Cheers,
Jonathan
[[alternative HTML version deleted]]
_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo
