Browse Groups

• ## Re: AI-GEOSTATS: Modelling anisotropy with GSTAT

(1)
• NextPrevious
• Pei-Chun, Question 1, You may be interested in some of these points on lognormal kriging, as I have been involved with lognormal kriging of datasets, but not
Message 1 of 1 , Dec 2 5:18 AM
View Source
Pei-Chun,

Question 1,
You may be interested in some of these points on lognormal
kriging, as I have been involved with lognormal kriging of datasets,
but not in use for unconditional simulation.

- Lognormal kriging can be very sensitive. If you plot experimental
are well formed you are in luck, however if your variograms are very
erratic, note that your grades will be in error in proportion of the error
in your estimation of the sill.
- Yes prior to lognormal kriging you log transform the data so it has
zero skewness and is normally distributed. Note that if your data
belongs to a "three" parameter lognormal population you must also
make an estimte of the third parameter alpha, and add this to your
values before taking their logarithms.
If you plot a log probability plot of your data and it is a straight line
then you have a two parameter lognormal distribution and you can
take logarithms of the data to acheive zero skewness.
If the line drops of towards the origin you may have a three parameter
lognormal population with which you can estimate alpha from the
graph or alternatively iterativley trial different values to your population
until it has a skewness of zero i.e.
z=ln(x+alpha)
where z is the transformed distribution which has skewness=0;

- Also note that the anti-logarithm of a number is not equal to the
logarithm of a number, so after your modelling, you cannot back
transform your data, by simply taking the antilogarithm of the values.
You will have to check a geostatistical text to see the procedure for
back transformation of data.

Question 2,
I have just read Margaret Armstrongs "Basic Linear Geostatistics" and
in the chapter on Structural Analysis provides three case studies, and in
all case studies uses the same nugget effect for all directions, even though
in two of the case studies there is variation of the nugget effect in different
I would be inclined to use the omidirectional nugget effect in your case, the
values are reasonably similar as in the case studies. It is possible the nugget
effect varies in the different directions due to the different spacing of the data
in the different directions, and the data is samples also, so may not perfectly
follow the real underlying values of the actual continuous data.

Regards Digby Millikan B.Eng

Geolite Mining Systems
U4/16 First Ave.,
Payneham South SA 5070
Australia.
Ph: +61 8 84312974

digbym@...
http://www.users.on.net/digbym

[Non-text portions of this message have been removed]
Your message has been successfully submitted and would be delivered to recipients shortly.
To: