Dear Paulo, thank you very much. It is working and it is much faster (about half time for the same amount of cells to simulate).
laura On 17 May 2011 19:27, Paulo Justiniano Ribeiro Jr <[email protected]>wrote: > Laura > > args(grf) > im=grf(n=611*634,grid="reg", nx=611, ny=634, xlims=c(1, 611), ylims=c(1, > 634), nugget=nug, cov.par=c(sill,range), mean=mean) > image(im) > > > will work for this > > PLease update both, geoR and RandomFields > > I'm also preparing a fix such that your original call will work as well > > best > P.J. > > > Paulo Justiniano Ribeiro Jr > LEG (Laboratorio de Estatistica e Geoinformacao) > Universidade Federal do Parana > Caixa Postal 19.081 > CEP 81.531-990 > Curitiba, PR - Brasil > Tel: (+55) 41 3361 3573 > VOIP: (+55) (41) (3361 3600) 1053 1066 > Fax: (+55) 41 3361 3141 > e-mail: paulojus AT ufpr br > http://www.leg.ufpr.br/~paulojus > > > On Fri, 13 May 2011, Laura Poggio wrote: > > Dear all, >> I am trying to run gaussian unconditional simulation with spatial >> structure >> using the grf function of geoR, with the following code: >> >> library(geoR) >> a=c(1:611) >> b=c(1:634) >> gr=expand.grid(a,b) >> im=grf(661*634, grid=gr, nugget=nug, cov.par=c(sill,range), mean=mean) >> >> When using geoR version 1.6.32 (or older) with version 1.3.45 (or older) >> of >> RandomFields the results present an evident spatial structure. While using >> the same code with version 1.6.33 or 1.6.34 of GeoR and version 2.0.4x of >> RandomFields the resulting pattern is like pure random noise. >> I tried with different values for sill, range, nugget and mean, but the >> results are always without spatial structure. If needed, I can provide >> more >> information and figures for more visual examples. >> >> Any hints would be greatly appreciated. >> >> Thank you very much in advance >> >> Laura >> >> [[alternative HTML version deleted]] >> >> _______________________________________________ >> R-sig-Geo mailing list >> [email protected] >> https://stat.ethz.ch/mailman/listinfo/r-sig-geo >> >> [[alternative HTML version deleted]] _______________________________________________ R-sig-Geo mailing list [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-geo
