Activity Number:
|
378
|
Type:
|
Topic Contributed
|
Date/Time:
|
Thursday, August 15, 2002 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Section on Bayesian Stat. Sciences*
|
Abstract - #301916 |
Title:
|
Space-time Modelling of Sydney Harbour Winds
|
Author(s):
|
Edward Cripps*+ and David Nott and Christopher Wikle and William Dunsmuir
|
Affiliation(s):
|
University of New South Wales and University of New South Wales and University of Missouri and University of Minnesota
|
Address:
|
School of Mathematics, Sydney, International, 2052, Australia
|
Keywords:
|
Space-time ; Hierarchical models ; Bayesian Analysis ; Markov chain Monte Carlo ; Numercial weather prediction
|
Abstract:
|
In this paper, we develop a space-time statistical model for local forecasting of surface level wind fields in a coastal region with comnplex topography. Our statistical model makes use of output from deterministic numerical weather prediction models (NWP), which are able to produce forecasts of surface wind fields on a spatial grid. When predicting surface winds at observing stations errors can arise due to sub-grid scale processes not adequately captured by the NWP model, and our statistical model attempts for these influences. In particular we use information from observing stations within the study region as well as topographic information to account for local bias. We use Bayesian methods for inference in our model, with computations carried out using Markov chain Monte Carlo algorithms. The empircal performance of our model is studied.
|