Hello, My previous post was far to broad to handle so I'm triming it to a format somehow easier to handle.
I have been using kriging to estimate oceanographic data from the NWW3 model. My aim is to densify the spatio-temporal resolution of the model without having to use another model to refine NWW3 data. Basically, I intend to interpolate NWW3 data in space and in time with a model capable of considering the spatio-temporal relationships present in this type of phenomena. The subjacent idea is the following: we may consider reasonable to accept that the waveset average height at a determined location depends not only on the heights of its neighboors but also on the height of the mentioned location (and its neighboors) in a previous/posterior instant in time. I would appreciate your comments on this reasoning. Nevertheless, this approach is not applicable when considering wavesets directions since the directional semivariograms will be erroneously influenced by the circular nature of these variables: averaging 5 degrees with 355 degrees will result in 180 degrees, while the correct result should be 0 degrees. I haven't been able to figure out how to interpolate directions in this spatio-temporal framework. Can someone lead me to software, references or techniques to perform this kind of interpolation? Thank you, Nelson + + To post a message to the list, send it to ai-geostats@jrc.it + 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/
