|
Activity Number:
|
49
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 3, 2003 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Statistics & the Environment
|
| Abstract - #300536 |
|
Title:
|
Bayesian Hierarchical Spatio-Temporal Models for Wind Prediction
|
|
Author(s):
|
Li Chen*+ and Montserrat Fuentes and Jerry M. Davis
|
|
Companies:
|
North Carolina State University and North Carolina State University and North Carolina State University
|
|
Address:
|
Campus Box 8203, Raleigh, NC, 27695-0001,
|
|
Keywords:
|
Bayesian ; hierarchical ; separable ; stationary ; spatio-temporal
|
|
Abstract:
|
Wind fields along a coastline are composed of many features that are spatio-temporally complex in nature, and they are well recognized as nonstationary spatio-temporal processes. We represent the nonstationary spatio-temporal process as a mixture of local orthogonal separable stationary spatio-temporal processes. A test for separability is proposed. Our main objective is to develop a statistical model which is capable of providing reliable forecasts of wind fields. The model is designed in such a way that it is capable of combining observed wind data and output from mesoscale meteorological models to improve the forecasts. We model the data in terms of an underlying but unobservable true wind process, which is a nonstationary spatio-temporal process. We estimate the model in a Bayesian way. This provides improved wind field via the posterior distribution of the ture wind, and allows us to validate the meteorological model via the posterior predictive distribution of the observations. It also enables us to remove the bias in the meteorological model output by estimating additive and multiplicative bias parameters. We applied our methods to wind data on the Chesapeake Bay.
|
