Re: universal kriging switch

[Konstantin Malakhanov <kosta@iwwnt.iwwl.rwth-aachen.de>]

>>>>> "Peter Schlesinger" == Peter Schlesinger <pschles@whrc.org> writes:

    Peter Schlesinger> Edzer, What is the parameter we must use to get
    Peter Schlesinger> GSTAT to invoke universal kriging? We have the
    Peter Schlesinger> ordinary kriging working "well" now, but now we
    Peter Schlesinger> want to try universal kriging. What do we
    Peter Schlesinger> change/add in our .CMD file to get GSTAT to do
    Peter Schlesinger> universal kriging? There's a note in the online
    Peter Schlesinger> manual about a "d=1" to use on the data
    Peter Schlesinger> line. Is that what we want to do?

To get universal kriging, you can either:
1) use d=? switch to get trend of that order, or
2) use X=?? to model a trend as some combination of x,y-coordinates and
possibly user-defined function.

Chapter 4.2 'data' explains that. Look also at Examples 13,14,17.

Greetings,
-- 
Konstantin Malakhanov
---
Institut for Hydraulic Engineering & Groundwater Mgmt., 
RWTH Aachen, Germany
E-Mail: malakhanov@iww.rwth-aachen.de          Tel. +49/(0)241/807343
-- 
I will invent "TIDY BOWL"...