|
Activity Number:
|
476
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #310347 |
|
Title:
|
Modeling Wind Fields Using Process Convolutions
|
|
Author(s):
|
Margaret Short*+
|
|
Companies:
|
University of Alaska Fairbanks
|
|
Address:
|
P.O. Box 750125, Fairbanks, AK, 99775,
|
|
Keywords:
|
wind field ; spatial process ; process convolutions ; Markov chain Monte Carlo
|
|
Abstract:
|
We propose an approach to modeling wind field data using process convolutions. Our approach has several advantages over a standard Gaussian process approach for such data. In particular, it has the ability to handle both the periodicity of the wind direction and the non-negativity of the wind speed. Ours is a Bayesian model; we implement it via Markov chain Monte Carlo. We illustrate the approach with an application.
|
