Hi Moshood,
I think you can do this way
Ordinary kriging to create kriging prediction orkrig - krige(yield ~
1, canmod.sp, newdata = grid, model=exp.mod,nmax=20)
OrdKrigecv - Krige.cv(yield ~ 1, canmod.sp,
model=exp.mod,nmax=20)
RMSE.ok -
On Wed, May 21, 2014 at 5:14 PM, Remi Genevest rgenev...@free.fr wrote:
Thanks a lot Barry. Your post perfectly matches what I was looking for.
Well now if I want to do a coarser grid covering Europe, what I should do is
doing more or less the same thing, just to change the resolution, right?
Hi Michele,
I tried the script as advised but get the error message
ordkrigcv- krige.cv(yield ~ 1, canmod.sp, newdata = grid,
model=exp.mod,nmax=20)Error in gstat(g = NULL, id = var1, formula =
formula, data = locations, :
unused argument(s) (newdata = S4 object of class SpatialPixels)
Hi Moshood,
You did not follow what Michele sent to you:
ordkrigcv- krige.cv(yield ~ 1, canmod.sp,
model=exp.mod, nmax=20)
try:
?krige.cv from the gstat library to see what you need to supply for the
function.
I would also advise you try reading Bivand et al (2008). Some of these
Alright !
You pointed out my goal indeed... but 100meters by 100meters is still a bit
too high for a map over Europe.
So, this is what I have done :
### create a grid raster
ll = CRS(+init=epsg:4326)
origin = SpatialPoints(cbind(7,40),ll)
grid = raster()
## make resolution ie 0.008 min par
On Thu, May 22, 2014 at 7:44 PM, Remi Genevest rgenev...@free.fr wrote:
Alright !
You pointed out my goal indeed... but 100meters by 100meters is still a bit
too high for a map over Europe.
So, this is what I have done :
### create a grid raster
ll = CRS(+init=epsg:4326)
origin =
