Re: [ai-geostats] a questions of using GSTAT to do Gaussian Conditional Simulation!
Feng Liu wrote:
Single path; run the process with nsim=1; 100 times to get 100 different pathsHi, Dear List:I am trying to use Gstat to do Gaussian Conditional Simulation on my soil C content data. I got 3 questions as following:1. If I use "set nsim=100" to do 100 times simulation, does the simulations follow a single random path or they will follow 100 different random paths? What should I do if I want to let them follow different random paths.
(and rename the output each time).
Not with maps (maps are univariate), you can when using ascii column files with2. Is it possible for me to write all the results of 100 simulations to one single file? How?
Install gnuplot, and make sure that a binary called gnuplot is present in3. Gstat needs gnuplot to do the plot, but I could not get gnuplot compiled and start in windows, could you please tell me how to do it if you have experience on this.
the search path; the gnuplot folks tend to call it gnupltw32.exe or something
like that; see also the set gnuplot = 'xxx'; command in gstat files.
Also, I couldn't agree more with Ernesto: I find myself using gstat inside
R or S-Plus almost 100% of the time I spend using gstat.