Speaker: Danny Modlin, North Carolina State University, Dept. of Statistics
Date: 2 November 2010
Title: Circular CAR Modeling of Vector Fields
As hurricanes approach landfall, there are several hazards for which coastal popu- lations must be prepared. Damaging winds, torrential rains, and tornadoes play havoc with both the coast and inland areas; but, the biggest seaside menace to life and prop- erty is the storm surge. Wind fields are used as the primary forcing for the numerical forecasts of the coastal ocean response to hurricane force winds such as the height of the storm surge and the degree of coastal flooding. Unfortunately, developments in deterministic modeling of these forcings have been hindered by extreme computational expenses.
In this paper, we present a multivariate spatial model for vector fields, that we apply to hurricane forcing winds. More specifically, a circular conditional autoregressive (CCAR) representation of the vector direction, and a spatial conditional model for the vector length given the direction is presented, while a Bayesian framework is being used for inference from this model. We apply our framework for vector fields model hurricane surface wind fields. A case study of Hurricane Floyd of 1999 compares our CCAR model to prior methods that decompose wind speed and direction into its N-S and W-E cardinal components.