A Bayesian Probabilistic Model for Estimating Building Damage Distribution from Forecasts

Estimating the distribution of building damage from forecasted hazards can enable more effective urban search and rescue (USAR) planning and operations. Our work uses Bayesian probabilistic modeling to estimate the distribution of building damage levels from forecasted hazard scores. We leverage data on building damage collected from FEMA USAR teams during wide area search operations. Our results validate the performance of the FEMA hazard forecasts predictions for Hurricane Ian in 2022, and also quantitatively characterizes the distribution of building damage for each forecasted hazard level.