As for gstat: I think you can't with krigeST, but you may succeed with
krige when you take time as the third dimension -- of course this
constrains the variogram models you can choose from to the metric model.
On 08/11/16 23:35, Santiago Beguería Portugués wrote:
> Dear R-sig-geo list members,
>
Dear R-sig-geo list members,
I am working on a spatio-temporal kriging model (using gstat::krigeST) of two
closely related variables. I’m getting good results on one of them, and not so
good on the other. Since both dependent variables are inter-related, I expect
that co-kringing would be a