Predictions of damages from Atlantic tropical cyclones: a hierarchical Bayesian study on extremes

TL;DR

This paper develops Bayesian hierarchical models to predict damages from Atlantic tropical cyclones, incorporating climate indices and cyclone characteristics for seasonal and individual event damage forecasts.

Contribution

It introduces a novel hierarchical Bayesian framework that models both seasonal cyclone activity and individual cyclone damage potential, improving damage prediction accuracy.

Findings

Robust prediction of cyclone damages demonstrated

Models outperform existing methods in accuracy

Effective incorporation of climate indices

Abstract

Bayesian hierarchical models are proposed for modeling tropical cyclone characteristics and their damage potential in the Atlantic basin. We model the joint probability distribution of tropical cyclone characteristics and their damage potential at two different temporal scales, while taking several climate indices into account. First, a predictive model for an entire season is developed that forecasts the number of cyclone events that will take place, the probability of each cyclone causing some amount of damage, and the monetized value of damages. Then, specific characteristics of individual cyclones are considered to predict the monetized value of the damage it will cause. Robustness studies are conducted and excellent prediction power is demonstrated across different data science models and evaluation techniques.