This is unfortunately one of the shortcomings of Kriging. Ali and Lall
have developed series of nonparametric techniques that address many of
these shortcomings such as 1) data clustering, 2) stationarity
assumption, and 3) Variogram identification.
We specifically address the problem you are inquiring in one of our
Ali, A. I., and Lall, U., "A Kernel Estimator for Stochastic subsurface
characterization from drill log data", Ground Water, 34, 4, 647, 1996.
If you have any question, please feel free to contact me; or professor
Alaa I. Ali, Ph.D., P.E.
New Mexico State Engineer Office
; or aali@...
Phone: 505-827-6125 Fax: 505-827-6188
> Dear geostatisticians and the like,
> Have any of you encountered the problem that can sometimes arise when
> th strings of data (eg contiguous composites along drill holes) where
you get lu
> dicrously large weights assigned to the samples at the ends of the
> This problem is documented beautifully by Robert F. Shurtz in his
> 'Propagation of Error and Paradox in Geostatistics'
> 'The geostatistics machine and the drill core paradox'
> I would like to hear your thoughts on this and suggested solutions.
> fixes' have been proposed to deal with this paradox, but they most
> not solve the problem. It's the kriging system itself which is at
> Richard Gaze
> MRT Perth WA
> *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
> "unsubscribe ai-geostats" in the message body.
> DO NOT SEND Subscribe/Unsubscribe requests to the list!
*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!