JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 404
Type: Contributed
Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics and the Environment
Abstract #311360 View Presentation
Title: Hierarchical Modeling of Spatial-Temporal Tropical Cyclone Occurrences with Application to Seasonal Cyclone Forecasting
Author(s): Marcela Alfaro-Córdoba*+ and Montserrat Fuentes and Joe Guinness and Lian Xie
Companies: North Carolina State University and North Carolina State University and North Carolina State University and North Carolina State University
Keywords: Spatial-Temporal ; Tropical Cyclones ; Predictive point process ; Bayesian ; Multivariate ; Multiple probit
Abstract:

A tropical cyclone is a rotating system characterized by a low pressure center, strong winds and heavy rain, that can cause damages both out at sea or inland. Tropical cyclones can be classified as tropical storms, mild hurricanes, and strong hurricanes. We introduce a statistical framework to forecast the probability of occurrence and the category of a tropical cyclone at any spatial location in the Atlantic Basin. The different categories of tropical cyclones are modeled simultaneously across space and time as a function of sea surface temperatures and latent heat fluxes. We work with massive remote sensing data and computer model output to characterize sea surface temperatures and heat fluxes. A Bayesian spatial multiple probit model was used to model dependence between the proportion of tropical cyclones for each response, time and location and the covariates for the same time and location. Rank reductions techniques, using a multivariate space-time extension of a predictive point process were used to estimate the covariance matrices, integrating this approach in a hierarchical model to estimate both the total number of storms per year and the probability of occurrence.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2014 program




2014 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Professional Development program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.