A Bayesian multivariate functional model with spatially varying coefficient approach for modeling hurricane track data

Abstract Hurricanes are massive storm systems with enormous destructive capabilities. Understanding the trends across space and time of a hurricane track and intensity leads to improved forecasts and minimizes their damage. Viewing the hurricane’s latitude, longitude, and wind speed as functions of time, we propose a novel spatiotemporal multivariate functional model to simultaneously allow for multivariate, longitudinal, and spatially observed data with noisy functional covariates. The proposed procedure is fully Bayesian and inference is performed using MCMC. This new approach is illustrated through simulation studies and analyzing the hurricane track data from 2004 to 2013 in the Atlantic basin. Simulation results indicate that our proposed model offers a significant reduction in the mean square error and averaged interval and increases the coverage probability. In addition, our method offers a 10% reduction in location and wind speed prediction error.