[R-sig-Geo] kriging -- grass -- asciigrid

Sat Mar 1 01:21:33 CET 2008

Dear members,

I have tried to export a kriging map to arcgis as asciigrid or image.
I have used the functions write.asciigrid and writeRast6sp(grass), in
both cases any success; In the former when exporting it, I got the
following message " Asciigrid does not support grids with non-square
cells". I checked for the krige map topology characteristics using the
following code:
getGridTopology(lidekri)

Apparently cell size looks fine: see below

                         s1       s2
cellcentre.offset -363565.9 175563.0
cellsize               90.0     90.0
cells.dim             804.0   1236.0

For the writeRast6sp function from "spgrass6" library

writeRast6sp(lidekri,"lidekri",zcol="var1.pred",NODATA=-9999),

I got the following message error

 "Error in system(paste(paste("g.tempfile", .addexe(), sep = ""),
"pid=",  :  g.tempfilepid=421 not found"

I will greatly appreciate any suggestions to get around this technical problem.

Sincerely,

Jose Funes

On Fri, Feb 29, 2008 at 6:00 AM,  <r-sig-geo-request at stat.math.ethz.ch> wrote:
> Send R-sig-Geo mailing list submissions to
>         r-sig-geo at stat.math.ethz.ch
>
>  To subscribe or unsubscribe via the World Wide Web, visit
>         https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>  or, via email, send a message with subject or body 'help' to
>         r-sig-geo-request at stat.math.ethz.ch
>
>  You can reach the person managing the list at
>         r-sig-geo-owner at stat.math.ethz.ch
>
>  When replying, please edit your Subject line so it is more specific
>  than "Re: Contents of R-sig-Geo digest..."
>
>
>  Today's Topics:
>
>    1. estimates for paths of travel given two time series,      drawn
>       from two corresponding spatial densities (Galkowski, Jan)
>    2. makeGrid(PBSmapping) (Markus Loecher)
>    3. Choice of Spatial weights (stefan lhachimi)
>
>
>  ----------------------------------------------------------------------
>
>  Message: 1
>  Date: Thu, 28 Feb 2008 13:58:49 -0500
>  From: "Galkowski, Jan" <jgalkows at akamai.com>
>  Subject: [R-sig-Geo] estimates for paths of travel given two time
>         series, drawn from two corresponding spatial densities
>  To: <r-sig-geo at stat.math.ethz.ch>
>  Message-ID:
>         <76EB4827B2104D40AE7E43AA5D8582EA011A9D32 at MAVS1.kendall.corp.akamai.com>
>
>  Content-Type: text/plain
>
>  This is less an R question and more a request to the community for
>  literature references and the like.
>
>  I'm interested in the following inferential question.  What's the max
>  likelihood estimate for a path of travel of a point across a plane
>  having stable, smooth densities of two separate variables given two time
>  series of their values at the point as it moves?   Suppose all that's
>  available is the ratio of the variables?
>
>  This is motivated by problems of inferring movement of biological
>  specimens between nesting and migratory regions, or the problem of
>  recovery of travel given the technique described here:
>
>     http://www.pnas.org/cgi/content/abstract/105/8/2788
>
>  Despite that, are there R packages which might help this?  I ask because
>  I often find real gems buried within many R packages, gems which aren't
>  obviously related to their primary subject.
>
>  Thanks much.
>
>         [[alternative HTML version deleted]]
>
>
>
>  ------------------------------
>
>  Message: 2
>  Date: Thu, 28 Feb 2008 15:00:28 -0500
>  From: Markus Loecher <loecher at eden.rutgers.edu>
>  Subject: [R-sig-Geo] makeGrid(PBSmapping)
>  To: r-sig-geo at stat.math.ethz.ch
>  Message-ID: <20080228195805.F18A632408E at annwn13.rutgers.edu>
>  Content-Type: text/plain; charset="us-ascii"; format=flowed
>
>  Dear geo experts,
>  I am clearly misunderstanding the role of the projection argument in
>  the wonderful utility makeGrid(PBSmapping).
>  I had hoped that by setting projection ="LL" the resulting grid would
>  be equidistant in "real" space, and hence curvilinear in lat/lon space.
>  But the following code yields the identical, regular grid,
>  irrespective of the projection argument:
>
>         mypolys <- makeGrid(x= seq(-123,-122,length=10), y = seq(33, 34,
>  length=10), byrow = FALSE, addSID = TRUE, projection = "LL")
>         plotMap(mypolys)
>         mypolys <- makeGrid(x= seq(-123,-122,length=10), y = seq(33, 34,
>  length=10), byrow = FALSE, addSID = TRUE, projection = 1)
>         plotMap(mypolys)
>
>  Is there an easy way to create a rectangular grid in lat/lon space ?
>  Should I first translate the points to UTM coordinates ?
>
>  Thanks!
>
>  Markus
>
>
>
>  ------------------------------
>
>  Message: 3
>  Date: Fri, 29 Feb 2008 11:36:18 +0100
>  From: "stefan lhachimi" <stefan.duke at gmail.com>
>  Subject: [R-sig-Geo] Choice of Spatial weights
>  To: r-sig-geo at stat.math.ethz.ch
>  Message-ID:
>         <a211af3b0802290236m53a12cd1h806a3106f508fb54 at mail.gmail.com>
>  Content-Type: text/plain; charset=ISO-8859-1
>
>  Dear all,
>
>  as a matter of curiosity does anybody know literature which discusses
>  what spatial weight to choose (e.g. k-nn, single or double
>  contiguity)? Or has anybod a good rule of thumb?
>  I found an article which proposes to try several specification and
>  take either the one with the highest lambda  or the one with the best
>  overall model fit (in a regression). But I think that is statistically
>  speaking that is not very satisfactory, in particular if the
>  application does not give any indication what weight to use.
>
>  Any hints?
>  Best,
>  Stefan
>
>
>
>  ------------------------------
>
>  _______________________________________________
>  R-sig-Geo mailing list
>  R-sig-Geo at stat.math.ethz.ch
>  https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>
>
>  End of R-sig-Geo Digest, Vol 54, Issue 27
>  *****************************************
>