[R-sig-Geo] Spatio Temporal kriging in Gstat

[Dan Turenne]

I would be happy to provide a data set and script but I'm not sure what you mean by making the data available "off-list".  Is there a particular forum where R-Sig-Geo users can post data and scripts?  Thanks again for your help.


Daniel Turenne

University of Manitoba


________________________________
From: R-sig-Geo <r-sig-geo-bounces at r-project.org> on behalf of Edzer Pebesma <edzer.pebesma at uni-muenster.de>
Sent: June 21, 2016 1:52 AM
To: r-sig-geo at r-project.org
Subject: Re: [R-sig-Geo] Spatio Temporal kriging in Gstat

This might be due to a bug (or feature) in the software caused by the
sparseness in your data, which might be different from that used to test
the software. Please make the data available (off-list), along with an R
script, so we can try to reproduce the error message and look into it.

On 21/06/16 04:11, Dan Turenne wrote:
> My apologies, I accidentally sent an unfinished email, here is the complete version of my question
>
>
> Hello R-Sig-Geo,
>
>
> As part of my masters thesis I am attempting to use spatio-temporal regression kriging to make predictions with temperature data, and I was hoping that someone might be able to give some insight as to how the algorithms work in gstat.  My data consists of daily temperature observations from April 1 to July 31, 2000.  There are observations from 164 stations across these 122 days, however not all stations have observations on all days, making for a total of 19282 records.
>
>
> I have tried to use an STSDF object but I have not had any success.  I created an sp object of length 164 with the station locations:
>
>
>     sp = data.frame(long = stations$long, lat = stations$lat)
>
>     coordinates(sp) = ~ long+lat
>
>
> Then I created a vector of length 122 with the times the observations were recorded and a data vector of length 19282:
>
>
>     beginDate = as.Date(2000/04/01)
>
>     endDate = as.Date(2000/07/31)
>
>     times = as.POSIXct(seq(beginDate,endDate,by="days"))
>
>
>     data=data.frame(temps$residual)
>
>
> And I also made an index detailing where observations are available, it looks like this with the first column representing spatial index and the second representing the time index
>
>
>     1   1
>
>     2   1
>
>     3   1
>
>     4   1
>
>
>     st=STSDF(sp,time,data,index,endTime=delta(time))
>
>
> however when I try to calculate the sample variogram I get the following error:
>
>
>     sample.stVariogram=variogramST(residual~1,data=st, tunit="days", tlags=1:7, progress=TRUE)
>
>
>
>    Error in apply(do.call(cbind, lapply(ret, function(x) x$np)), 1, sum,  :
>    dim(X) must have a positive length
>    In addition: There were 50 or more warnings (use warnings() to see the first 50)
>
>
> All 50 of the errors are :
>
>
>   In is.na(data[[as.character(as.list(formula)[[2]])]]) :
>    is.na() applied to non-(list or vector) of type 'NULL'
>
>
> Can anyone see what I am doing wrong or give me any pointers?  This error  is rather cryptic and I'm not quite sure what I'm doing wrong.  Any help would be appreciated.
>
>
> Many Thanks,
>
> Daniel Turenne
>
> University of Manitoba
>
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at r-project.org
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
R-sig-Geo - R Special Interest Group on using Geographical ...<https://stat.ethz.ch/mailman/listinfo/r-sig-geo>
stat.ethz.ch
R-sig-Geo -- R Special Interest Group on using Geographical data and Mapping About R-sig-Geo



>

--
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


	[[alternative HTML version deleted]]