skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, May 23 until 2:00 AM ET on Friday, May 24 due to maintenance. We apologize for the inconvenience.


Title: A machine learning approach for predicting hurricane evacuee destination location using smartphone location data
Abstract

Evacuation destination choice modeling is an integral aspect of evacuation planning. Outputs from such models are required to estimate the clearance times on which evacuation orders are based. The number of evacuees arriving at each destination also informs allocation of resources and shelter planning. Despite its importance, evacuee destination modeling has not received as much attention as identifying who evacuates and when. In this study, we present a new approach to identify evacuees and determine where they go and when using privacy-enhanced smartphone location data. We demonstrate the method using data from four recent U.S. hurricanes affecting multiple geographies (Florence 2018, Michael 2018, Dorian 2019, and Ida 2021). We then build on those results to develop a new machine learning model that predicts the number of evacuees that move between pairs of metropolitan statistical areas. The machine learning model incorporates hurricane characteristics, which have not been thoroughly exploited by existing methods. The model’s predictive power is comprehensively evaluated through a tenfold cross validation, holdout validation using Hurricane Ida (2021), and comparison with the traditional gravity model. Results suggest that the new model substantially outperforms the traditional gravity model across all performance indicators. Analysis of feature importance in the machine learning model indicates that in addition to distance and population, hurricane characteristics are important in evacuee destination choices.

 
more » « less
Award ID(s):
2002589
NSF-PAR ID:
10462846
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Springer Science + Business Media
Date Published:
Journal Name:
Computational Urban Science
Volume:
3
Issue:
1
ISSN:
2730-6852
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    The 2020 Atlantic hurricane season was extremely active and included, as of early November, six hurricanes that made landfall in the United States during the global coronavirus disease 2019 (COVID‐19) pandemic. Such an event would necessitate a large‐scale evacuation, with implications for the trajectory of the pandemic. Here we model how a hypothetical hurricane evacuation from four counties in southeast Florida would affect COVID‐19 case levels. We find that hurricane evacuation increases the total number of COVID‐19 cases in both origin and destination locations; however, if transmission rates in destination counties can be kept from rising during evacuation, excess evacuation‐induced case numbers can be minimized by directing evacuees to counties experiencing lower COVID‐19 transmission rates. Ultimately, the number of excess COVID‐19 cases produced by the evacuation depends on the ability of destination counties to meet evacuee needs while minimizing virus exposure through public health directives. These results are relevant to disease transmission during evacuations stemming from additional climate‐related hazards such as wildfires and floods.

     
    more » « less
  2. Abstract

    How evacuations are managed can substantially impact the risks faced by affected communities. Having a better understanding of the mobility patterns of evacuees can improve the planning and management of these evacuations. Although mobility patterns during evacuations have traditionally been studied through surveys, mobile phone location data can be used to capture these movements for a greater number of evacuees over a larger geographic area. Several approaches have been used to identify hurricane evacuation patterns from location data; however, each approach relies on researcher judgment to first determine the areas from which evacuations occurred and then identify evacuations by determining when an individual spends a specified number of nights away from home. This approach runs the risk of detecting non‐evacuation behaviors (e.g., work trips, vacations, etc.) and incorrectly labeling them as evacuations where none occurred. In this article, we developed a data‐driven method to determine which areas experienced evacuations. With this approach, we inferred home locations of mobile phone users, calculated their departure times, and determined if an evacuation may have occurred by comparing the number of departures around the time of the hurricane against historical trends. As a case study, we applied this method to location data from Hurricanes Matthew and Irma to identify areas that experienced evacuations and illustrate how this method can be used to detect changes in departure behavior leading up to and following a hurricane. We validated and examined the inferred homes for representativeness and validated observed evacuation trends against past studies.

     
    more » « less
  3. This paper presents the use of tsunami evacuation drills within a coastal community in the Cascadia Subduction Zone (CSZ) to better understand evacuation behaviors and thus to improve tsunami evacuation preparedness and resilience. Evacuees’ spatial trajectory data were collected by Global Navigation Satellite System (GNSS) embedded in mobile devices. Based on the empirical trajectory data, probability functions were employed to model people’s walking speed during the evacuation drills. An Evacuation Hiking Function (EHF) was established to depict the speed–slope relationship and to inform evacuation modeling and planning. The regression analysis showed that evacuees’ speed was significantly negatively associated with slope, time spent during evacuation, rough terrain surface, walking at night, and distance to destination. We also demonstrated the impacts of milling time on mortality rate based on participants’ empirical evacuation behaviors and a state-of-the-art CSZ tsunami inundation model. Post-drill surveys revealed the importance of the drill as an educational and assessment tool. The results of this study can be used for public education, evacuation plan assessment, and evacuation simulation models. The drill procedures, designs, and the use of technology in data collection provide evidence-driven solutions to tsunami preparedness and inspire the use of drills in other types of natural disasters such as wildfires, hurricanes, volcanoes, and flooding. 
    more » « less
  4. Abstract

    Hurricanes Isaac (2012), Harvey (2017), and Irma (2017) were storms with different geophysical characteristics and track forecast consistencies. Despite the differences, common themes emerged from the perception of track forecasts from evacuees for each storm. Surveys with a mixture of closed and open-ended responses were conducted during the evacuations of each storm while the storm characteristics and decision-making were fresh in the minds of evacuees. Track perception accuracy for each evacuee was quantified by taking the difference between three metrics: perceived track and official track (PT − OT), perceived track and forecast track (PT − FT), and home location and perceived track (HL − PT). Evacuees from Hurricanes Isaac and Harvey displayed a tendency to perceive hurricane tracks as being closer to their home locations than what was forecast to occur and what actually occurred. The large sample collected for Hurricane Irma provided a chance to statistically verify some of the hypotheses generated from Isaac and Harvey. Results from Hurricane Irma confirmed that evacuees expected a storm to be closer to their home locations after controlling for regional influences. Furthermore, participants with greater previous hurricane experience perceived a track as being closer to their home locations, and participants residing in zip codes corresponding with nonmandatory evacuation zones also perceived tracks as being closer to their home locations. These findings suggest that most evacuees from hurricanes in the United States appear to perceive storms as being closer to their home locations than they are and overestimate wind speeds at their homes, thus overestimating the true danger from landfalling hurricanes in many storms.

     
    more » « less
  5. Abstract Major disasters such as extreme weather events can magnify and exacerbate pre-existing social disparities, with disadvantaged populations bearing disproportionate costs. Despite the implications for equity and emergency planning, we lack a quantitative understanding of how these social fault lines translate to different behaviours in large-scale emergency contexts. Here we investigate this problem in the context of Hurricane Harvey, using over 30 million anonymized GPS records from over 150,000 opted-in users in the Greater Houston Area to quantify patterns of disaster-inflicted relocation activities before, during, and after the shock. We show that evacuation distance is highly homogenous across individuals from different types of neighbourhoods classified by race and wealth, obeying a truncated power-law distribution. Yet here the similarities end: we find that both race and wealth strongly impact evacuation patterns, with disadvantaged minority populations less likely to evacuate than wealthier white residents. Finally, there are considerable discrepancies in terms of departure and return times by race and wealth, with strong social cohesion among evacuees from advantaged neighbourhoods in their destination choices. These empirical findings bring new insights into mobility and evacuations, providing policy recommendations for residents, decision-makers, and disaster managers alike. 
    more » « less