An official website of the United States government
During emergencies, it is often necessary to evacuate vulnerable people to safer places to reduce loss of lives and cope with human suffering. Shelters are publically available places to evacuate, especially for people who do not have any other choices. This paper overviews emergency shelter planning in disaster mitigation and preparation and discusses the need for better responding to people who need to evacuate during emergencies. Recent evacuation studies pay attention to integrating social factors into evacuation modeling for better prediction of evacuation decisions. Our goal is to address the impact of social behavior on the sheltering choices of evacuees and to explore the potential contributions of including social network characteristics in the decision-making process of authorities. We present the shelter utilization problem in South Carolina during Hurricane Florence and discuss an agent-based modeling approach that considers social community structures in modeling the shelter choice behavior of socially connected individuals
more »
« less
This content will become publicly available on March 1, 2026
Spatiotemporal Modeling of Connected Vehicle Data: An Application to Non-Congregate Shelter Planning During Hurricane-Pandemics
The growing complexity of natural disasters, intensified by climate change, has amplified the challenges of managing emergency shelter demand. Accurate shelter demand forecasting is crucial to optimize resource allocation, prevent overcrowding, and ensure evacuee safety, particularly during concurrent disasters like hurricanes and pandemics. Real-time decision-making during evacuations remains a significant challenge due to dynamic evacuation behaviors and evolving disaster conditions. This study introduces a spatiotemporal modeling framework that leverages connected vehicle data to predict shelter demand using data collected during Hurricane Sally (September 2020) across Santa Rosa, Escambia, and Okaloosa counties in Florida, USA. Using Generalized Additive Models (GAMs) with spatial and temporal smoothing, integrated with GIS tools, the framework captures non-linear evacuation patterns and predicts shelter demand. The GAM outperformed the baseline Generalized Linear Model (GLM), achieving a Root Mean Square Error (RMSE) of 6.7791 and a correlation coefficient (CORR) of 0.8593 for shelters on training data, compared to the GLM’s RMSE of 12.9735 and CORR of 0.1760. For lodging facilities, the GAM achieved an RMSE of 4.0368 and CORR of 0.5485, improving upon the GLM’s RMSE of 4.6103 and CORR of 0.2897. While test data showed moderate declines in performance, the GAM consistently offered more accurate and interpretable results across both facility types. This integration of connected vehicle data with spatiotemporal modeling enables real-time insights into evacuation dynamics. Visualization outputs, like spatial heat maps, provide actionable data for emergency planners to allocate resources efficiently, enhancing disaster resilience and public safety during complex emergencies.
more »
« less
- Award ID(s):
- 2101091
- PAR ID:
- 10614751
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Applied Sciences
- Volume:
- 15
- Issue:
- 6
- ISSN:
- 2076-3417
- Page Range / eLocation ID:
- 3185
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Understanding human movements in the face of natural disasters is critical for disaster evacuation planning, management, and relief. Despite the clear need for such work, these studies are rare in the literature due to the lack of available data measuring spatiotemporal mobility patterns during actual disasters. This study explores the spatiotemporal patterns of evacuation travels by leveraging users’ location information from millions of tweets posted in the hours prior and concurrent to Hurricane Matthew. Our analysis yields several practical insights, including the following: (1) We identified trajectories of Twitter users moving out of evacuation zones once the evacuation was ordered and then returning home after the hurricane passed. (2) Evacuation zone residents produced an unusually large number of tweets outside evacuation zones during the evacuation order period. (3) It took several days for the evacuees in both South Carolina and Georgia to leave their residential areas after the mandatory evacuation was ordered, but Georgia residents typically took more time to return home. (4) Evacuees are more likely to choose larger cities farther away as their destinations for safety instead of nearby small cities. (5) Human movements during the evacuation follow a log-normal distribution.more » « less
-
null (Ed.)The total cost for weather-related disasters in the US increases over time, and hurricanes usually create the most damage. One of the challenges, which is present in almost every major hurricane event, is the patient evacuation mission. We propose a comprehensive modeling and methodological framework for a large-scale patient evacuation problem when an area is faced with a forecasted disaster such as a hurricane. In this work, we integrate a hurricane scenario generation scheme using publicly available surge level forecasting software and a scenario-based stochastic integer program to make decisions on patient movements, staging area locations and positioning of emergency medical vehicles with an objective of minimizing the total expected cost of evacuation and the setup cost of staging areas. The hurricane scenario generation scheme incorporates the uncertainties in the hurricane intensity, direction, forward speed and tide level. To demonstrate the modeling approach, we apply real-world data from the Southeast Texas region in our experiments. We highlight the importance of operation time limits, the number of available resources and an accurate forecast on forthcoming hurricanes in determining the locations of staging areas and patient evacuation decisions.more » « less
-
Unplanned disaster events can greatly disrupt access to essential resources, with calamitous outcomes for already vulnerable households. This is particularly challenging when concurrent extreme events affect both the ability of households to travel and the functioning of traditional transportation networks that supply resources. This paper examines the use of volunteer-based crowdsourced food delivery as a community resilience tactic to improve food accessibility during overlapping disruptions with lasting effects, such as the COVID-19 pandemic and climate disasters. The study uses large-scale spatio-temporal data (n = 28,512) on crowdsourced food deliveries in Houston, TX, spanning from 2020 through 2022, merged with data on community demographics and significant disruptive events occurring in the two-year timespan. Three research lenses are applied to understand the effectiveness of crowdsourced food delivery programs for food access recovery: 1) geographic analysis illustrates hot spots of demand and impacts of disasters on requests for food assistance within the study area; 2) linear spatio-temporal modeling identifies a distinction between shelter-in-place emergencies and evacuation emergencies regarding demand for food assistance; 3) structural equation modeling identifies socially vulnerable identity clusters that impact requests for food assistance. The findings from the study suggest that volunteerbased crowdsourced food delivery adds to the resilience of food insecure communities, supporting its effectiveness in serving its intended populations. The paper contributes to the literature by illustrating how resilience is a function of time and space, and that similarly, there is value in a dynamic representation of community vulnerability. The results point to a new approach to resource recovery following disaster events by shifting the burden of transportation from resource-seekers and traditional transportation systems to home delivery by a crowdsourced volunteer network.more » « less
-
With the increase of natural disasters all over the world, we are in crucial need of innovative solutions with inexpensive implementations to assist the emergency response systems. Information collected through conventional sources (e.g., incident reports, 911 calls, physical volunteers, etc.) are proving to be insufficient [1]. Responsible organizations are now leaning towards research grounds that explore digital human connectivity and freely available sources of information. U.S. Geological Survey and Federal Emergency Management Agency (FEMA) introduced Critical Lifeline (CLL) s which identifies the most significant areas that require immediate attention in case of natural disasters. These organizations applied crowdsourcing by connecting digital volunteer networks to collect data on the critical lifelines from data sources including social media [3], [4], [5]. In the past couple of years, during some of the deadly hurricanes (e.g., Harvey, IRMA, Maria, Michael, Florence, etc.), people took on different social media platforms like never seen before, in search of help for rescue, shelter, and relief. Their posts reflect crisis updates and their real-time observations on the devastation that they witness. In this paper, we propose a methodology to build and analyze time-frequency features of words on social media to assist the volunteer networks in identifying the context before, during and after a natural disaster and distinguishing contexts connected to the critical lifelines. We employ Continuous Wavelet Transform to help create word features and propose two ways to reduce the dimensions which we use to create word clusters to identify themes of conversations associated with stages of a disaster and these lifelines. We compare two different methodologies of wavelet features and word clusters both qualitatively and quantitatively, to show that wavelet features can identify and separate context without using semantic information as inputs.more » « less
