[SOLVED] Standardised (by data variance) semivariogram?

If you have problems using RGeostats package or if you simply need some help on an unlisted subject.

[SOLVED] Standardised (by data variance) semivariogram?

Postby markm0705 » Mon Apr 15, 2019 4:34 am

In other software systems I have used, I typically prepare standardised semivariograms for modelling and display purposes. I've found I have to first divide each datum by data variance if I want to do this using vario.grid() or vario.calc(). Is this best way to do this in RGeostats or is there another option?
Last edited by markm0705 on Tue May 28, 2019 9:50 am, edited 1 time in total.
markm0705
 
Posts: 22
Joined: Sun Mar 17, 2019 9:39 am

Re: Standardised (by data variance) semivariogram?

Postby Didier Renard » Tue Apr 16, 2019 8:52 am

Hello

For sure, normalizing the data beforehand is a solution. However, a more general method can be imagined which normalizes the simple variograms and the cross-variograms simultaneously.

We have developed a post-mortem function which ensures the simultaneous and consistent normalization of a set of simple and cross variograms: vario.transfo.
Let me illustrate this message by a simple exercise:

Code: Select all
db = db.create(x1=runif(100),x2=runif(100),z1=rnorm(100),z2=rnorm(100))   # This creates a bivariate 2D data base
vario = vario.calc(db)                                                    # This calculates the bivariate variogram
plot(vario)                                                               # Display the initial variogram
vnorm = vario.transfo("v1",vario1=vario,oper="norm")                      # Create the normalized variogram
plot(vnorm)


Hope this will help
Didier Renard
 
Posts: 337
Joined: Thu Sep 20, 2012 4:22 pm

Re: Standardised (by data variance) semivariogram?

Postby markm0705 » Tue Apr 16, 2019 9:38 am

Didier

Thanks for this the process looks to be straightforward - I will get back to this post if not successful - appreciate the rapid replies to my questions

Regards
markm0705
 
Posts: 22
Joined: Sun Mar 17, 2019 9:39 am

Re: Standardised (by data variance) semivariogram?

Postby Didier Renard » Tue Apr 16, 2019 10:19 am

Thanks

Let me recall that it would be satisfactory for us if you could modify the name of the TOPIC by adding the world "[SOLVED]" in front of it, when you consider that an answer has been reached ... in order to allow a quick sort of the remaining posts..
Thanks in advance
Didier Renard
 
Posts: 337
Joined: Thu Sep 20, 2012 4:22 pm


Return to Other Troubleshooting

Who is online

Users browsing this forum: No registered users and 7 guests

cron