[R-sig-Geo] I've a problem with krige and would appreciate any thoughts...

Edzer Pebesma edzer.pebesma at uni-muenster.de
Mon Apr 20 09:07:18 CEST 2009


The problem is that for universal kriging prediction, you need IDSaco
values at the prediction locations. So, you need to make the prediction
locations grid (newdata) a SpatialGridDataFrame that has these values on
each prediction location (grid node).
--
Edzer

Peter S. Hayes wrote:
> Hello list,
>
> I have some data I am attempting to krige as an example for my class
> to perform.
>
> Most of the work has been reading in, reprojecting, and formatting
> data... all fine.
>
> But, when I create the variogram, grid, and variogram model and pass
> these into fit.variogram, I receive an error that - on the surface -
> seems to make no sense.
>
> I considered that the singular variogram model might be the problem,
> but that made no difference when changed. I'm puzzled... any thoughts?
>
> Thank you all!
>
>
>
> Pete Hayes
>
>
> str(fishtr)
> Formal class 'SpatialPointsDataFrame' [package "sp"] with 5 slots
> ..@ data :'data.frame': 364 obs. of 8 variables:
> .. ..$ X : int [1:364] 1 2 3 4 5 6 8 9 10 11 ...
> .. ..$ Cruise_Tow: int [1:364] 199402 199402 199402 199402 199402
> 199402 199402 199402 199402 199402 ...
> .. ..$ YearNo : int [1:364] 0 0 0 0 0 0 0 0 0 0 ...
> .. ..$ NUMBER : int [1:364] 2 19 12 10 1 12 18 8 23 7 ...
> .. ..$ WEIGHT_KG : num [1:364] 0.9 2.2 2 2.4 0.5 0.8 1.7 1.2 3.6 1.9 ...
> .. ..$ DSaco : num [1:364] 164743 156002 152330 167741 179798 ...
> .. ..$ IDSaco : num [1:364] 6.07e-06 6.41e-06 6.56e-06 5.96e-06
> 5.56e-06 ...
> .. ..$ lwt : num [1:364] -0.105 0.788 0.693 0.875 -0.693 ...
> ..@ coords.nrs : num(0)
> ..@ coords : num [1:364, 1:2] 421360 415658 432270 462808 460247 ...
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : NULL
> .. .. ..$ : chr [1:2] "DECLON" "DECLAT"
> ..@ bbox : num [1:2, 1:2] 347047 4641166 595022 4902398
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : chr [1:2] "DECLON" "DECLAT"
> .. .. ..$ : chr [1:2] "min" "max"
> ..@ proj4string:Formal class 'CRS' [package "sp"] with 1 slots
> .. .. ..@ projargs: chr " +proj=utm +zone=19 +ellps=GRS80 +datum=NAD83
> +units=m +no_defs +towgs84=0,0,0"
> > str(vg)
> Classes ‘gstatVariogram’ and 'data.frame': 15 obs. of 6 variables:
> $ np : num 490 1120 1758 2125 2678 ...
> $ dist : num 5126 12320 20132 28176 36059 ...
> $ gamma : num 1.18 1.48 1.33 1.52 1.6 ...
> $ dir.hor: num 0 0 0 0 0 0 0 0 0 0 ...
> $ dir.ver: num 0 0 0 0 0 0 0 0 0 0 ...
> $ id : Factor w/ 1 level "var1": 1 1 1 1 1 1 1 1 1 1 ...
> - attr(*, "direct")='data.frame': 1 obs. of 2 variables:
> ..$ id : Factor w/ 1 level "var1": 1
> ..$ is.direct: logi TRUE
> > str(vg.fit)
> Classes ‘variogramModel’ and 'data.frame': 2 obs. of 9 variables:
> $ model: Factor w/ 19 levels "Nug","Exp","Sph",..: 1 3
> $ psill: num 0.698 0.761
> $ range: num 0 10342
> $ kappa: num 0 0.5
> $ ang1 : num 0 0
> $ ang2 : num 0 0
> $ ang3 : num 0 0
> $ anis1: num 1 1
> $ anis2: num 1 1
> - attr(*, "singular")= logi TRUE
> - attr(*, "SSErr")= num 2.16e-07
> > str(spgrid)
> Formal class 'SpatialGrid' [package "sp"] with 5 slots
> ..@ grid :Formal class 'GridTopology' [package "sp"] with 3 slots
> .. .. ..@ cellcentre.offset: num [1:2] 347046 4641165
> .. .. ..@ cellsize : num [1:2] 1000 1000
> .. .. ..@ cells.dim : int [1:2] 255 265
> ..@ grid.index : int(0)
> ..@ coords : num [1:2, 1:2] 347046 601046 4641165 4905165
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : NULL
> .. .. ..$ : chr [1:2] "coords.x1" "coords.x2"
> ..@ bbox : num [1:2, 1:2] 346546 4640665 601546 4905665
> .. ..- attr(*, "dimnames")=List of 2
> .. .. ..$ : chr [1:2] "coords.x1" "coords.x2"
> .. .. ..$ : chr [1:2] "min" "max"
> ..@ proj4string:Formal class 'CRS' [package "sp"] with 1 slots
> .. .. ..@ projargs: chr " +proj=utm +zone=19 +ellps=GRS80 +datum=NAD83
> +units=m +no_defs +towgs84=0,0,0"
> >
> > lwt.uk <- krige(lwt~IDSaco,fishtr,spgrid,vg.fit)
> Error in eval(expr, envir, enclos) : object "IDSaco" not found
> >
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo

-- 
Edzer Pebesma
Institute for Geoinformatics (ifgi), University of Münster
Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251
8333081, Fax: +49 251 8339763 http://ifgi.uni-muenster.de/
http://www.springer.com/978-0-387-78170-9 e.pebesma at wwu.de



More information about the R-sig-Geo mailing list