Leveraging Machine Learning and Simulation to Advance Disaster Preparedness Assessments through FEMA National Household Survey Data

Effective household and individual disaster preparedness can minimize physical harm property damage during catastrophic events. To assess the risk vulnerability of affected areas, it is crucial for relief agencies to understand level public preparedness. Traditionally, government have employed nationwide random telephone surveys gauge public’s attitudes actions towards However, these may lack generalizability in certain locations due low response rates or areas not covered by survey. address this issue enhance comprehensiveness assessments, we develop a framework that seamlessly integrates machine learning simulation. Our approach leverages algorithms establish relationships between demographic characteristics. Using Monte Carlo simulation, generate datasets incorporate information location based on government-provided distribution data. The generated dataset then input into model predict population. We demonstrate effectiveness our applying Miami-Dade County, where accurately predicts With innovative approach, clearer more comprehensive understanding