Applying Mobile Location Data to Improve Hurricane Evacuation Plans

Abstract

Can private location data be used for the public good? During an emergency, cities and municipalities must disperse limited resources to the areas of greatest need. The data which can best inform these decisions may be hidden within the mobile apps that city residents use on an everyday basis. Given the ethical concerns surrounding location tracking, we address this question using data from X-Mode Social, Inc., a start-up company with open and transparent data sharing policies. X-Mode’s high-quality location data are compliant with both regulations in the European Union (GDPR) and the United States (CCPA). We narrowed our focus to the City of Jacksonville, Florida, which issued mandatory evacuations prior to Hurricane Dorian’s approach in early September 2019. After validating that X-Mode’s data correlates with local population densities, we visualized locations pre- and post-hurricane in order to establish whether mobile app users were able to heed government warnings. Next, we used a combination of both spatial analysis and generalized linear modeling methods to characterize patterns of movement during the evacuation. Finally, we built an interactive web-based app to reveal areas where the evacuation process could potentially be improved. Our results work to fill current knowledge gaps and provide a process with which city and municipal managers might utilize to more effectively allocate resources during a crisis.