Sebastiano,
OI and geostatistics are essentially the same thing.
In geostatistics more emphasis is placed on modelling the spatial
correlation structure, typically via the variogram, often from a single
realisation of the data.
In OI the form of the covariance functions is often dictated from
physical considerations (e.g. to impose geostrophic balance) and the
parameters of the covariance function estimated on the basis of
historical forecasts / observations (i.e. many realisations assuming
again stationarity in time). Often in OI the increments are predicted -
that is a forecast is used as the mean, and the residuals are treated as
a Gaussian random process.
The real difference is in emphasis; both assume a Gaussian process
(Gaussian random field model) at some level. Beware the subtleties
however; they will make different assumptions and these ought to be
carefully examined, but this depends on the actual version of the
methods being used and their implementation - little useful can be said
generically.
For my money, working in a dynamic setting (I assume 4D means space +
time) I'd look at the ensemble Kalman filter - a reduced rank method
that deals nicely with dynamics, and is computationally and
implementationally efficient!
cheers
Dan
sebastiano trevisani wrote:
Dear List Members
I'm trying to find some paper explaining relationship and differences
between classical geostatistical methodologies
and objective analysis.
I'm working with oceanographic data set (really complex: the data are
4D) ....it seem that in the oceanography world objective analysis is
more popular!
Thank you in advance for your help.
S. Trevisani
+
+ To post a message to the list, send it to [email protected]
+ To unsubscribe, send email to majordomo@ jrc.it with no subject and
"unsubscribe ai-geostats" in the message body. DO NOT SEND
Subscribe/Unsubscribe requests to the list
+ As a general service to list users, please remember to post a summary
of any useful responses to your questions.
+ Support to the forum can be found at http://www.ai-geostats.org/
--
--------------------------------------------------------------------
Dr Dan Cornford | tel: +44 (0)121 204 3451
Senior Lecturer, | fax: +44 (0)121 204 3681
Computer Science & NCRG | email: [EMAIL PROTECTED]
NCRG, Aston University |
Birmingham B4 7ET, UK | http://www.ncrg.aston.ac.uk/~cornfosd/
--------------------------------------------------------------------
+
+ To post a message to the list, send it to [email protected]
+ To unsubscribe, send email to majordomo@ jrc.it with no subject and "unsubscribe
ai-geostats" in the message body. DO NOT SEND Subscribe/Unsubscribe requests to the
list
+ As a general service to list users, please remember to post a summary of any
useful responses to your questions.
+ Support to the forum can be found at http://www.ai-geostats.org/
