[R-sig-Geo] gstat: BLAS/LAPACK routine 'DPOTRF' gave error code -4

Edzer Pebesma edzer.pebesma at uni-muenster.de
Fri Feb 19 08:17:02 CET 2016


Yeboah,

It looks like this problem has been solved in the development version of
gstat, on https://github.com/edzer/gstat

Let me know if you have trouble installing from source/github, in which
case I will do a CRAN submission.

Best regards,

On 19/02/16 06:14, Yeboah Gyasi-Agyei wrote:
> Dear Edzer,
> 
>  
> 
> I’ve been using gstat for sometime now and my code has been running
> well. I today downloaded R version 3.2.2 and 3.2.3 and this code line on
> conditional simulation is generating the error message below.
> 
>  
> 
>  OK <- krige(z ~ 1, ConDat, Gridat,model = Model2D,nsim=1,nmax = 50,
> nmin = 5, maxdist = 100)
> 
>   drawing 1 GLS realisation of beta...
> 
>   [using conditional Gaussian simulation]
> 
>  
> 
> Error in predict.gstat(g, newdata = newdata, block = block, nsim = nsim,  :
> 
>   BLAS/LAPACK routine 'DPOTRF' gave error code -4
> 
>  
> 
> However there is no problem with ordinary kriging when nsim=0. The
> attached file contains ConDat, Gridat and Model2D.
> 
>  
> 
> From a search on the web  I noticed that other "programs / code" got
> similar errors and the cause was generally due to some arrays being
> incomplete, or the size of the array is not big enough.
> 
>  
> 
> Please advise and thanks for your help.
> 
>  
> 
> Yeboah
> 

-- 
Edzer Pebesma
Institute for Geoinformatics  (ifgi),  University of Münster
Heisenbergstraße 2, 48149 Münster, Germany; +49 251 83 33081
Journal of Statistical Software:   http://www.jstatsoft.org/
Computers & Geosciences:   http://elsevier.com/locate/cageo/
Spatial Statistics Society http://www.spatialstatistics.info

-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 490 bytes
Desc: OpenPGP digital signature
URL: <https://stat.ethz.ch/pipermail/r-sig-geo/attachments/20160219/5248f94d/attachment.bin>


More information about the R-sig-Geo mailing list