[prev in list] [next in list] [prev in thread] [next in thread] 

List:       r-sig-geo
Subject:    [R-sig-Geo] Warning message in fit.variogram for regression kriging
From:       Seyed Jalil Alavi via R-sig-Geo <r-sig-geo () r-project ! org>
Date:       2017-09-23 6:10:49
Message-ID: 651784711.688721.1506147049927 () mail ! yahoo ! com
[Download RAW message or body]

Dear all


I want to perform regression kriging in R using GSIF package or gstat manually. I \
want to use linear regression model fitted with quadratic term and interaction \
between variables as the base model for regression kriging.


Here is my final LM model:


LM1 <-  lm(Site_Form ~ DEM + Profile_Curvature + TPI + TRASP + Valley_Depth +     \
Vertical_Distance + I(Plan_Curvature^2) + I(Profile_Curvature^2) +     I(TWI^2) + \
I(Valley_Depth^2) + I(Vertical_Distance^2) + TRASP:Vertical_Distance +     DEM:TRASP \
+ DEM:Vertical_Distance, data=Data)


When I want to run fit.variogram I encounter with this Warning message:

In fit.variogram(vr, model = vgm(4, "Sph", 400, 1)) :

  No convergence after 200 iterations: try different initial values?


I do not where the problem is. I changed the nugget, range and sill values. But it \
still remains.


I would be very grateful if somebody helps me.


Thank you very much


Regards


Jalil


 

	[[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo


[prev in list] [next in list] [prev in thread] [next in thread]