GEOSTATS: variogram modelling
- My original request for help;
>I am interested in obtaining programs that may be used toSummary of responses
>automatically fit a model variogram. My application requires
>large numbers of variograms to be fitted to small datasets therefore
>speed and consistency are important. However, the code need not
>attempt to resolve any complex structure as it is likely that
>there will be insufficient information available for this to be
>Does anyone know of any software suitable for the above application ?
>Any method is fine e.g. fitting by least squares but I would prefer,
>although any language is probably ok, source code in FORTRAN so that
>I can easily fit it together with other tools.
>I will post a summary of any responses sent directly.
Many thanks to everyone who took the time to reply to my request.
Programs which were suggested to be of use were;
1) SAGE95; a powerful software package that calculates and
automatically models sample variograms (2 or 3D) (1 or 2
nested structures). You can download the program at the web site
2) A least-squares method that works using the GSLIB package. The code c=
be downloaded from the ftp site (ftp.iamg.org). The paper describing
the method can be found in Computers and Geoscience (Vol
3) The unix version of Geoeas (see the softfaq of AI-GEOSTATS).
(uncertain whether the dos version has an automatic fitting).
4) The S+ spatial module, bearing in mind the need to learn the
programming. There is a good book to lead you though, "Statistical models
in S+" Chambers and Hastie 1993. See Isaaks and Srivastava 1989 to avoid
violating any assumptions.
5) 250 variograms have been computed semi-automatically for the Kola
Ecochemistry Project, from which an Atlas has just been released:
Environmental Geochemical Atlas of the Central Barents Region (1998):
NGU, Trondheim, Norway. (See also
-- and their the report --or http://www.ngu.no .)
All the geostatistical computations (e.g. variograms) were made
using the program GEOSAN, which was developed at the department and
is also commercially available from it.
6) VARIOWIN and GSLIB were also suggested, although these require user
7) GSTAT http://www.frw.ruu.nl/gstat/
*To post a message to the list, send it to ai-geostats@....
*As a general service to list users, please remember to post a summary
of any useful responses to your questions.
*To unsubscribe, send email to majordomo@... with no subject and
"unsubscribe ai-geostats" in the message body.
DO NOT SEND Subscribe/Unsubscribe requests to the list!