An integrated evacuation decision support system framework with social perception analysis and dynamic population estimation

Abstract

In designing evacuation plans, it is critical for the responsive agencies to consider the dynamic change of human population within impact areas and understand social perception from local residents. Although a large number of evacuation models has been reported in the literature, many used census survey data which represent only the nighttime population distribution. To fill this research gap, this paper introduces a novel data integration framework for developing an evacuation decision support system for wildfire, Integrated Wildfire Evacuation Decision Support System (IWEDSS). IWEDSS integrates multiple data sources including social media, census survey, geographic information systems (GIS) data layers, volunteer suggestions, and remote sensing data. The integration is based on multi-disciplinary theoretical and modeling approaches including Geographic Information Science, civil and transportation engineering, computer science, social media and communication. IWEDSS includes four core modules: dynamic population estimation, stage-based robust evacuation planning, social perception analysis, and web-based geomatical analytic platform. It offers tools for evacuation planers and resource managers to make better decisions that can reduce the evacuation time and potential number of injuries and deaths. This paper also presents a case study to demonstrate the suitability of incorporating social media data to estimate the dynamic change of human population.