- Award ID(s):
- 2045744
- NSF-PAR ID:
- 10428837
- Editor(s):
- Babski-Reeves, K.; Eksioglu, B.; Hampton, D.
- Date Published:
- Journal Name:
- Proceedings of the IISE Annual Conference & Expo 2023
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Individual evacuation decision making has been studied for multiple decades mainly using theory-based approaches, such as random utility theory. This study aims to bridge the research gap that no studies have adopted data-driven approaches in modeling the compliance of hurricane evacuees with government-issued evacuation orders using survey data. To achieve this, we conducted a survey in two coastal metropolitan regions of Florida (Jacksonville and Tampa) during the 2020 Atlantic hurricane season. After preprocessing survey data, we employed three supervised learning algorithms with different complexities, namely, multinomial logistic regression, random forest, and support vector classifier, to predict evacuation decisions under various hypothetical hurricane threats. We found that the evacuation decision is mainly determined by people’s perception of hurricane risk regardless of whether the government issued an order; COVID-19 risk is not a major factor in evacuation decisions but influences the destination type choice if an evacuation decision is made. Additionally, past and future evacuation destination types were found to be highly correlated. After comparing the algorithms for predicting evacuation decisions, we found that random forest can achieve satisfactory classification performance, especially for certain categories or when some categories are merged. Finally, we presented a conceptual optimization model to incorporate the data-driven modeling approach for evacuation behavior into a government-led evacuation planning framework to improve the compliance rate.more » « less
-
Hurricane evacuation has become an increasingly complicated activity in the U.S. as it involves moving many people who live along the Atlantic coast and Gulf coast within a very limited time. A good deal of research has been conducted on hurricane evacuation, but only a limited number of studies have looked into the timing aspect of evacuation. This paper intends to contribute to the literature on evacuation timing decisions by investigating what factors influence the time preference at the household level. Two hurricane survey data sets were used to analyze household evacuation behaviors across the Gulf coast as well as the Northeast and Mid-Atlantic coast in a comparative perspective. Using the Heckman selection model, we examined various factors identified in the literature on the two possible outcomes (evacuation and early evacuation). We found that the most important determinants of evacuation were prior evacuation experience, evacuation orders, and risk perceptions, while the most important determinants of early evacuation were prior evacuation experiences, days spent at the evacuation destination, and the cost of evacuation. Socioeconomic factors also influenced the two decisions but differently. These results provide implications for future hurricane evacuation planning and for improving emergency management practices.more » « less
-
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.
-
Hurricane evacuation has become an increasingly complicated activity in the U.S. as it involves moving many people who live along the Atlantic coast and Gulf coast within a very limited time. A good deal of research has been conducted on hurricane evacuation, but only a limited number of studies have looked into the timing aspect of evacuation. This paper intends to contribute to the literature on evacuation timing decisions by investigating what factors influence the time preference at the household level. Two hurricane survey data sets were used to analyze household evacuation behaviors across the Gulf coast as well as the Northeast and Mid-Atlantic coast in a comparative perspective. Using the Heckman selection model, we examined various factors identified in the literature on the two possible outcomes (evacuation and early evacuation). We found that the most important determinants of evacuation were prior evacuation experience, evacuation orders, and risk perceptions, while the most important determinants of early evacuation were prior evacuation experiences, days spent at the evacuation destination, and the cost of evacuation. Socioeconomic factors also influenced the two decisions but differently. These results provide implications for future hurricane evacuation planning and for improving emergency management practices.
-
A stochastic optimization model for patient evacuation from health care facilities during hurricanesWe propose a rigorous modeling and methodological effort that integrates statistical implementation of hydrology models in predicting inland and coastal flood scenarios due to hurricanes and a scenario-based stochastic integer programming model which suggests resource and staging area decisions in the first stage and the evacuation decisions in the second stage. This novel study combines physics-based flood prediction models and stochastic optimization for large- scale multi-facility coordination of hospital and nursing home evacuations before impending hurricanes. The optimization model considers scenario-dependent evacuation demand, transport vehicles with varying capacities, and both critical and non-critical patients. Utilizing Hurricane Harvey of 2017 as a case study and actual healthcare facility locations in southeast Texas, we explore various evacuation policies, demonstrating the impact of routing strategies, staging area decisions, flood thresholds, and receiving facility capacities on evacuation outcomes. One of the findings is that choosing staging area(s) and deploying evacuation vehicles optimally considering the uncertainty of the hurricane’s path at the time of decision making could have significant effect on the total cost of the operation and evacuation time experienced by the evacuees. We also show the non-negligible value of the scenario-based staging and routing solution conservatively calculated in relation to a single scenario solution using the concept of value of stochastic solution.more » « less