Hi, The area of statistics you're looking for is called geostatistics. There are many R packages to conduct such analyses. See the Spatial task view for some good starting points:
http://cran.r-project.org/web/views/Spatial.html You'll need to do some homework to understand the various options and which are best for your data. You might start with Inverse Distance Weighting. Sarah On Mon, Jul 28, 2014 at 9:07 AM, Kulupp <kul...@online.de> wrote: > Dear R-experts, > > I have a regular grid dataframe (here: the first 50 rows) : > > # data frame (regular grid) with x, y (UTM-coordinates) and z (depth) > # x=UTM coordinates (easting, zone 32) > # y=UTM coordinates (northing, zone 32) > # z=river-depth (meters) > df <- data.frame(x=c(3454240, 3454240, 3454240, 3454240, 3454240, 3454250, > 3454250, 3454250, 3454250, 3454250, 3454250, 3454250, 3454250, 3454250, > 3454250, 3454250, > 3454250, 3454250, 3454260, 3454260, 3454260, 3454260, > 3454260, 3454260, 3454260, 3454260, 3454260, 3454260, 3454260, 3454260, > 3454260, 3454260, > 3454260, 3454260, 3454260, 3454260, 3454260, 3454260, > 3454260, 3454260, 3454270, 3454270, 3454270, 3454270, 3454270, 3454270, > 3454270, 3454270, > 3454270, 3454270), > y=c(5970610, 5970620, 5970630, 5970640, 5970650, 5970610, > 5970620, 5970630, 5970640, 5970650, 5970660, 5970670, 5970680, 5970690, > 5970700, 5970710, > 5970720, 5970730, 5970610, 5970620, 5970630, 5970640, > 5970650, 5970660, 5970670, 5970680, 5970690, 5970700, 5970710, 5970720, > 5970730, 5970740, > 5970750, 5970760, 5970770, 5970780, 5970790, 5970800, > 5970810, 5970820, 5970610, 5970620, 5970630, 5970640, 5970650, 5970660, > 5970670, 5970680, > 5970690, 5970700), > z= c(-1.5621, -1.5758, -1.5911, -1.6079, -1.6247, -1.5704, > -1.5840, -1.5976, -1.6113, -1.6249, -1.6385, -1.6521, -1.6658, -1.6794, > -1.6930, -1.7067, > -1.7216, -1.7384, -1.5786, -1.5922, -1.6059, -1.6195, > -1.6331, -1.6468, -1.6604, -1.6740, -1.6877, -1.7013, -1.7149, -1.7285, > -1.7422, -1.7558, > -1.7694, -1.7831, -1.7967, -1.8103, -1.8239, -1.8376, > -1.8522, -1.8690, -1.5869, -1.6005, -1.6141, -1.6278, -1.6414, -1.6550, > -1.6686, -1.6823, > -1.6959, -1.7095)) > head(df) > plot(df[,1:2], las=3) # to show that it's a regular grid > > My question: is there a function to calculate the depth of any coordinate > pair (e.g. x=3454263, y=5970687) within the grid, e.g. by bilinear > interpolation or any other meaningful method? > > Thanks a lot for your help in anticipation > > Best wishes > > Thomas > -- Sarah Goslee http://www.functionaldiversity.org ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
