Evacuation Risk Research Articles

Emergency evacuation risk assessment for toxic gas attacks in airport terminals: Model, algorithm, and application

Transportation infrastructure has often been the target of terrorist attacks, and mitigation of the risk of toxic gas attacks is a challenging task in the design of indoor emergency evacuation systems. Considering multiple emergency response modes, we propose an agent-based risk assessment model and its algorithm to integrate gas diffusion and pedestrian movement data for emergency response, quickly assessing average individual exposure risk. We assessed the exposure status of individuals with respect to their emergency response actions following a toxic gas attack in an airport terminal. The results indicate that in the event of a general gas attack on an airport terminal, ventilation must be immediately ceased along with early evacuation. In areas with a shelter-in-place environment, the ventilation mode and shelter-in-place time should be determined based on the concentration of indoor and outdoor gases. In areas with nerve gas exposure and high population density, a new exit must be established at evacuation bottlenecks, and pedestrians must be guided to evacuate while promptly closing ventilation. These results offer suggestions and strategies for emergency response and decision-making in airport terminals during such incidents.

Assessing evacuation risks in prominent historical mosques: An integrated quantitative and qualitative approach via the HM-ERI framework

Historical mosques, with their unique architectural features and high occupant densities, pose distinct challenges for safe and efficient evacuation. This study introduces the Historical Mosque Evacuation Risk Index (HM-ERI), a novel and comprehensive framework specifically designed to assess evacuation risks in these culturally significant structures. The HM-ERI model integrates three quantitative criteria derived from agent-based simulations and seventeen qualitative criteria assessed through on-site evaluations, generating two dimensionless risk scores: HM-ERIQN (quantitative risk) and HM-ERIQL (qualitative risk).Analysis of 12 prominent 15th and 16th century mosques in Turkey revealed a spectrum of evacuation risk levels. The mosques' HM-ERIQN values ranged from 0.27 (low risk) to 0.80 (high risk) in the range of 0–1, indicating variations in potential congestion and evacuation efficiency based on simulated total evacuation times ranging from 2 min 46.3 s to 8 min 18.5 s. HM-ERIQL values, reflecting the severity of qualitative factors on a 0–1 scale such as the lack of alternative exits, improper placement of shoe racks, complex building layouts, and limited emergency preparedness, fell between 0.46 and 0.73, indicating moderate to high risks.By integrating expert judgment and utilizing data from both simulations and on-site observations, the HM-ERI framework provides a practical tool for identifying high-risk historical mosques and informing targeted interventions to enhance evacuation safety. This research contributes to developing enhanced evacuation standards for these culturally significant structures, enabling improved safety evaluations and guiding effective preservation strategies that prioritize human life and cultural heritage.

Risk-based shelter network design in flood-prone areas: An application to Haiti

Evacuations occur when human safety is compromised by disasters, such as floods. Shelters play a crucial role in providing protection for individuals who have been displaced or have lost their housing, emphasizing the requirement for secure accessibility. This paper introduces an systematic optimization tool, utilizing mathematical programming, to assist decision-makers in designing an effective shelter network. It is effective preparedness decision as it minimizes the total risk of the network considering its flooding condition during the response phase while maximizing coverage for those most exposed and vulnerable to hazard. We propose a risk-based approach, wherein the inherent risks of the shelter network (i.e., population, shelter, and evacuation risks) have been thoroughly assessed and measured to consider the impacts of floods based on empirical research outputs. To formulate a well-parameterized and valid problem, extensive data collection and processing, incorporating the use of geographic information system (GIS) for data management, have been conducted. In collaboration with the World Bank and Government of Haiti, this project contributes to a development initiative focused on strengthening disaster response capacity and infrastructure for Haiti, experiencing recurrent devastating floods and in need of enhancing its existing shelter network. Detailed computational results highlight the value of our risk-based methodology compared to more common approaches, emphasizing contributions to addressing real humanitarian problems.

Quantifying the risk of medical evacuation in spaceflight

IntroductionTraditionally, NASA mission planners have used a heuristic and qualitative approach to design medical systems based on prior experience; however, this approach may result in implicit bias in design. The risk of needing to return to definitive care (RTDC) or medevac, has been particularly difficult to quantify due to the complexity of exploration spaceflight. The Informing Mission Planning through Analysis of Complex Tradespaces (IMPACT) tool is a probabilistic risk assessment approach designed by NASA to model medical risk in long duration spaceflight. This paper discusses how this tool can inform RTDC risk and improve the health and safety of astronaut crews. MethodsIMPACT was developed by subject matter experts using an evidence-based approach and can be used to quantify the risk of exceeding the onboard medical capabilities. Within the model, RTDC occurs when a condition meets a specific threshold that exceeds the on-board capabilities and requires a higher level of care. A notional lunar surface design reference mission (DRM) was modeled using IMPACT, and the RTDC rate was analyzed. ResultsOf the 119 medical conditions evaluated, thirty-four were preassigned to have zero probability of RTDC based on lack of acuity. Thirty-one conditions used the need for inpatient hospitalization or admission to intensive care as the RTDC surrogate. Twenty-six conditions used the probability of needing surgery, and ten conditions used treatment failure rates as the RTDC surrogate. The remaining 18 conditions had unique surrogates that did not fall into the above categories or were assigned a 100 % probability of RTDC due to their definition. In the sample DRM, the overall risk for RTDC was 0.32 events per mission. DiscussionQuantifying medical risk for human spaceflight is challenging but important in designing medical systems that support the health and performance of our astronaut crews. IMPACT can use the best available evidence to quantify the risk of an RTDC event based on mission parameters and help mission planners make informed design decisions. More work is underway to further refine the model and evidence that drives the RTDC calculation to improve model fidelity and utility for missions to the Moon, Mars, and beyond.

An extended model for evacuation considering pedestrian behavior of emergency avoidance in the earthquake situation

In earthquake situations, emergency avoidance is an important way to ensure the life safety of pedestrians. To study the behavior of emergency avoidance of pedestrians in a disaster situation, an extended cellular automata model for pedestrian evacuation is established according to the real video records. The concepts of “avoidance rate” and “avoidance time” are introduced to describe emergency avoidance behavior. The trampling behavior of pedestrians is also considered in the model, which draws on the concept of repulsive force in the social force model. Taking into account both evacuation time and stampede probability, the total risk index is used to describe the overall evacuation risk. The single-story teaching building was used as an evacuation scene. Parameters affecting the whole evacuation process and overall evacuation risk such as avoidance rate and avoidance time were analyzed. What’s more, seven evacuation strategies were discussed in detail. The study shows that reasonable arrangement of pedestrian evacuation with avoidance rate and avoidance time in a certain range can reduce congestion and improve the safety of evacuation and the evacuation time will not increase obviously. This work can provide theoretical references for evaluating the overall risk of evacuation and also provide technical support for formulating evacuation strategies under earthquakes.

How does evacuation risk change over time? Influences on evacuation strategies during accidental toxic gas releases

Evacuation may be the most necessary and effective method of saving human lives in an emergency where toxic gases are released. Therefore, there is a need for a rational assessment of the risk of evacuees from the affected area at different times. In this paper, a modeling framework is developed to assess and control the risk of the emergency evacuation process under toxic gas release. Data from geographic information systems, big data on the spatial aggregation of population activities, and multi-agent-based modeling are combined to formulate and simulate evacuation event scenarios under toxic gas release. The characteristics of evacuation message dissemination at different times were explored, while the risk of people evacuating at different times was assessed in terms of two dimensions: health and fear emotion. In this case study, the proposed modeling framework was used to assess the potential risks faced by people when following the original evacuation plan in the event of an accidental release of toxic gas. The results of the assessment show that the factors affecting the risk of the evacuation process include the geometric parameters of the sub-evacuation area (SEA; location of the SEA, delineation pattern of SEA, degree of crowding, complexity of the SEA environment, population density, and age structure of the population) and the rate of information communication. Therefore, a control strategy is proposed based on geometric optimization and emergency communication optimization. The results of evacuation risk control show that the latter has a wider range of applicability, while the former has a weaker impact on evacuation risk in densely populated areas. The study results can provide information for public emergency authorities to develop effective emergency evacuation plans.

Evaluation of Tsunami Evacuation Plans for an Underground Mall Using an Agent-Based Model

Tsunamis resulting from earthquakes can cause extensive damage, including infrastructure destruction, injuries, and fatalities. To address these risks, numerous tsunami evacuation simulations have been conducted to assess evacuation strategies and identify issues, particularly in Japan, where the Nankai Trough earthquake is anticipated, affecting underground malls in urban areas. Our previous research primarily focused on evacuating from underground to the surface, neglecting surface evacuation. Therefore, this study extended the previous study to include horizontal evacuation following the exit from the underground mall to ground level. It also considered the impact of pedestrian road crossings as interactions with vehicular traffic within the simulation to enhance realism and verify the evacuation risk. The study also explores scenarios where evacuation guide stairs are unavailable, comparing the effectiveness of alternative staircases in the evacuation plan. Results indicate that while using alternative staircases temporarily increases the number of evacuees reaching the surface, road crossings on evacuation routes become significant bottlenecks, leading to surface congestion and delayed evacuations. This raises doubts about the effectiveness of alternative staircases and highlights the need to consider alternative evacuation routes as a secondary plan. Additionally, the study reveals that reduced pedestrian flow at road crossings can significantly impact on evacuation times. Ultimately, this study demonstrated that achieving a short evacuation time from underground malls to the ground level might not always yield the best evacuation plan. It underscored the importance of considering aboveground factors in evacuation planning to ensure safety in the event of a tsunami caused by an earthquake.

Pedestrian evacuation planning under dam-break flood disaster considering road risk and road pedestrian demand

When facing disasters, a well-planned evacuation of people can significantly reduce casualties and disaster losses. Hurricane Katrina struck New Orleans in 2005, causing multiple dam failures and resulting in Lake Pontchartrain flooding back into the city. Taking this disaster as an example, this paper evaluates the risk of pedestrian evacuation on roads during dam-break flood disasters. The evaluation considers three aspects: road evacuation difficulty, disaster risk and road pedestrian demand. The fuzzy VIKOR model was used to evaluate 8 indicators for 50 candidate shelters. A dual-objective planning model was proposed to consider the time-varying and diverse emergency needs of disaster victims. By assessing the risk of pedestrian evacuation on the road and delineating restricted areas, the optimal path distance is calculated. Pareto optimality is then employed to achieve a trade-off between the convenience, cost, and applicability of the evacuation plan. In a complex post-disaster environment, the model can adapt flexibly to emergency rescue situations at various stages by adjusting the parameters in the objective and constraint equation. The Pareto optimal frontier can assist in determining the most suitable solution for the current scenario. In the case of New Orleans, 22 and 18 shelters were respectively selected from 34 candidate shelters for evacuation based on the simulated scenarios.

A BIM-FDS Based Evacuation Assessment of Complex Rail Transit Stations under Post-Earthquake Fires for Sustainable Buildings

Post-earthquake fire is considered as a catastrophic secondary disaster to personal and property safety, especially in complex rail transit station. This is primarily attributed to intricate infrastructure, densely populated floors, and the unrestricted layout of these areas. The aim of this study is to evaluate the evacuation capacity of complex railway stations under post-earthquake fires, and provide sustainable recommendations for building design. In this article, an evacuation assessment of a complex rail transit station under the post-earthquake fire for sustainable buildings was conducted from the internal environment and external rescue based on Building Information Modeling (BIM) and Fire Dynamic Simulation (FDS). The internal environment evacuation assessment simulation experiments were conducted in six hypothetical high-risk scenarios. In addition, the external rescue assessment was based on investigation of the route and the required rescue time during different periods of holidays and workdays. The results show that (1) The influence caused by different sizes of fire area in the power distribution room is smaller than those in the train at the platform floor. (2) In fire scenarios with the same fire area but different fire locations, the temperature is more affected than the CO concentration in the power distribution room. (3) It shows slight differences between single-floor fire and double-floor fire on evacuation of small area fire in power distribution room. Meanwhile, optimized design recommendations are proposed to reduce the risk of emergency evacuation in both internal and external environments of rail transit stations for sustainable future buildings, which include strategically locating the power distribution room away from public areas, installing fire-resistant doors around the room, increasing the quantity of smoke detectors and alarms with regular maintenance, minimizing the size of the power distribution room, developing specific emergency plans for train fires, and incorporating small fire stations in urban planning near complex public buildings to mitigate post-earthquake road obstruction challenges.

Study on Elevated Interval Evacuation of Metro Train considering the Influence of Fire, Railings, and Track Bed

Elevated metro is a typical type of urban rail transit that operates on viaducts. Due to its fast construction speed and low cost, it plays an important role in transportation systems with dense concentrations of people. Once a fire accident occurs in rush hour, it will cause high casualty and enormous injuries. In this regard, studying the characteristics of fire smoke spread and passengers’ evacuation is of profound significance. In this paper, Pyrosim and Pathfinder software was utilized to simulate metro fire and evacuation process. The variation of temperature, CO concentration, and visibility inside carriage and outside walkaway were studied to explore the characteristic of fire and smoke. Evacuation time, speed, density, and path were analyzed for six cases considering the influence of railing settings on evacuation walkaway and the use of track bed. The impact of smoke on movement speed reduction and temperature on the available door numbers were taken into consideration. Results revealed that the temperature of accident carriage rose to tenability limit after 50 s and the visibility decreased to 5 m within 150 s. CO concentration was below safety criteria due to sufficient oxygen. Temperature was the most important factor that leads to the risk of evacuation, especially inside the accident carriage. The length of evacuation walkaway could highly reduce evacuation time and density. Railings had a negative impact on evacuation while the usage of track bed had a positive effect. Besides, the impact of railings was not as significant as the usage of the track bed. Research results can provide decision‐making reference for fire protection and evacuation design to alleviate congestion and improve safety management.

Simulation of emergency evacuation with crowd-gathering risk and evaluation methods: a case study of the mass rapid transit system in Taipei

ABSTRACT Mass rapid transit (MRT) systems are the backbone of transportation infrastructure in many cities. During emergencies, indoor subway stations become particularly susceptible to panic and overcrowding, making evacuation difficult. Therefore, simulating the evacuation and sheltering processes of a large number of individuals during emergencies is key in urban disaster response. In this study, a spatial evacuation risk model was used to enhance the safety of evacuation strategies in an MRT system. Data were collected on spatial architectural floor plans, and a database for communication and pedestrian flow was established. The behavioral patterns and distribution of individuals within stations and the characteristics of refuge spaces were also investigated. To simulate the processes of evacuation and sheltering, the Pathfinder evacuation simulation tool was used to construct a three-dimensional spatial model of a subway station. Specific scenarios were then constructed to simulate the procedures of evacuation and sheltering. Subsequently, the factors contributing to overcrowding-related hazards were analyzed to examine the spatial risks associated with crowd aggregation and evacuation and provide recommendations for improvement. Given its numerous advantages, this approach can serve as a valuable reference for conducting risk assessments in other large-scale crowd aggregation spaces.

A Qualitative Investigation of Space Exploration Medical Evacuation Risks.

INTRODUCTION: Exploration beyond low Earth orbit requires innovative solutions to support the crew medically, especially as the opportunity for timely evacuation to Earth diminishes. This includes assessing the risks and benefits that a complicated medical evacuation (MEDEVAC) poses to the injured crewmember, the crew, and the mission. This qualitative study identifies common MEDEVAC risk assessment principles used in spaceflight and other extreme environments to better inform future risk assessment tools and exploration mission concepts.METHODS: Semistructured interviews were conducted with subject matter experts in spaceflight and analog domains, including polar operations, undersea operations, combat medicine, and mountaineering. Transcripts were analyzed using the qualitative method of Thematic Analysis with the technique of consensus, co-occurrence, and comparison.RESULTS: Subject matter experts described 18 themes divided into two main categories: Primary Risk Considerations (e.g., crew, mission, resources, time) and Contributing Factors (e.g., psychological considerations, medical preparation, politics).DISCUSSION: Primary Risk Considerations can assess MEDEVAC risk across mission phases, with Contributing Factors acting as premission tools to adjust those risks. Inter- and intracategory connections identified medical support considerations, MEDEVAC support considerations, and philosophy as the most impactful Contributing Factors. Medical support considerations, psychological considerations, and political considerations were found to have unique aspects given the distances and societal impact of exploration vs. low Earth orbit spaceflight. The Contributing Factor theme of decision making was determined to be unique due to its impacts across both categories. These findings expand current considerations and are important inputs for exploration mission MEDEVAC Concepts of Operations.Almand A, Ko SY, Anderson A, Keller RJ, Zero M, Anderson AP, Laws JM, Lehnhardt K, Easter BD. A qualitative investigation of space exploration medical evacuation risks. Aerosp Med Hum Perform. 2023; 94(12):875-886.

Predicting hurricane evacuation for local neighborhoods across a metropolitan region

To mitigate the devastating impacts of hurricanes on people's lives, communities, and societal infrastructures, disaster management would benefit considerably from a detailed understanding of evacuation, including the socio-demographics of the populations that evacuate, or remain, down to disaggregated geographic levels such as local neighborhoods. A detailed household evacuation prediction model for local neighborhoods requires both a robust household evacuation decision model and individual household data for small geographic units. This paper utilizes a recently published statistical meta-analysis for the first requirement and then conducts a rigorous population synthesis procedure for the second. Our model produces predicted non-evacuation rates for all US Census block groups for the Tampa-St. Petersburg-Clearwater Metropolitan Statistical Area for a Hurricane Irma-like storm along with their socio-demographic and hurricane impact risk profiles. Our model predictions indicate that non-evacuation rates are likely to vary considerably, even across neighboring block groups, driven by the variability in evacuation risk profiles. Our results also demonstrate how different predictors may come to the fore in influencing non-evacuation in different block groups, and that predictors which may have an outsize impact on individual household evacuation decisions, such as Race, are not necessarily associated with the greatest differentials in non-evacuation rates when we aggregate households to block group level and above. Our research is intended to provide a framework for the design of hurricane evacuation prediction tools that could be used in disaster management.

Quantitative assessment of flooding risk based on predicted evacuation time: A case study in Joso city, Japan

Flooding is a frequent natural hazard, threatening people's lives and properties worldwide. Even though completely preventing damage from flooding is impossible, an appropriate evacuation can help minimize its impact and mitigate human casualties. However, analyzing various flooding information to make quick evacuation judgments is challenging for decision-makers. Therefore, a quantitative flooding risk assessment is needed to support appropriate evacuation decisions. This study introduces the travel time under ideal evacuation conditions to quantify evacuation vulnerability, with Dijkstra's algorithm finding the evacuation route and the Random Forest algorithm predicting the evacuation time. The evacuation vulnerability is then integrated with time-varying flooding hazards and estimated congestion levels to assess evacuation risk. Herein, a case study in Joso, Japan is used as an example to demonstrate the practicality and applicability of the proposed approach. As a result, the prediction model achieved high accuracy with an RMSE of 0.88min and a MAPE of 5.88 %. The proposed approach clearly illustrated the vulnerable areas and times that may hinder an efficient evacuation process. Also, this approach identified and visualized the individual evacuation risk distribution during a given flooding scenario: 49.38 % of buildings were assessed as having the highest-risk: no evacuation ability, while a maximum of 11.86 % and 3.83 % of the buildings were assessed as middle-risk and high-risk. Furthermore, the regional evacuation deadline and priorities were specified to ensure timely and effective evacuation. Overall, this study develops an approach for assessing evacuation vulnerability and risk that could facilitate awareness among the public and provide judgmental bases for evacuation preparedness and decision-making.

Simulation Study on Fire Product Movement Law and Evacuation in a University High-Rise Teaching Building

High-rise teaching buildings are complex public buildings that combine the evacuation risks of school buildings and high-rise buildings. In this regard, studying fire product transport patterns and personnel evacuation characteristics of high-rise school buildings is crucial for safe and rapid evacuation. In this paper, we applied Pyrosim2018 software to build a model of a teaching building and performed numerical fire simulation to analyze temperature, CO gas, and visibility to determine the available evacuation time ASET; meanwhile, we performed evacuation simulation by Pathfinder 2019 to determine the required evacuation time and analyze the congestion problem during evacuation. By improving the evacuation route, secondary simulations were conducted and compared with the previous results. The results show that visibility is the main factor affecting evacuation in of the event of a fire in this school building. Based on the visibility analysis, it is recommended that personnel evacuate from floors four and above within 709.2 S when the fire location is at a specific position on the third floor. While the original safety exits of the school building can avoid a large number of casualties, they cannot guarantee the safe evacuation of all people, and planning a reasonable evacuation route can obviously relieve the evacuation pressure in the high-rise corridor.

Simulation analysis of evacuation processes in a subway station based on multi-disaster coupling scenarios

ObjectiveThis study aimed to improve knowledge on ways to effectively solve problems associated with subway station emergencies and provide methodological guidance for safety management. Process and methodA real case was considered—the Nanning Chaoyang Square subway station—and the AnyLogic simulation modeling software was used to build a simulation model of the evacuation process in the station in different disaster and disaster coupling scenarios. In particular, the characteristics of various disaster scenarios and the coupling effect between multiple disasters were analyzed, the social force model was improved during the analysis of pedestrian movement, and the key factors affecting the evacuation process in fire outbreak, flooding, and fire and flood coupling scenarios were analyzed. The number of evacuated pedestrians and evacuation times in each scenario were compared for analysis, to propose targeted suggestions. ResultsThe impact of fire products on pedestrians increased rapidly during the fire growth stage. When a fire or flood occurred on Side A of the station hall floor, the impact on the evacuation capacity was the greatest. The results support the claim that different multi-disaster coupling scenarios have different effects on evacuation risk owing to the influence of pedestrian evacuation strategies.

Relative Risk ofAll-Cause Medical Evacuation forBehavioral Health Conditions inU.S. Central Command.

Behavioral health disorders are the leading category of evacuations from the U.S. Central Command (USCENTCOM) area of responsibility. Understanding the relative risk of behavioral health conditions associated with all-cause evacuation is important for the allocation of resources to reduce the evacuation burden. Data from the USTRANSCOM Regulating and Command & Control Evacuation System and Theater Medical Data Store covering personnel deployed to the USCENTCOM area of responsibility between January 1, 2017 and December 31, 2021 were collected and analyzed. All individuals who were diagnosed with a behavioral health-specific ICD-9 (290-316) or ICD-10 (F00-F99) code during the period were included. Using the earliest medical encounter, the number of individuals diagnosed with a particular code and the frequency individuals were evacuated being diagnosed with any code were calculated. The mean monthly USCENTCOM population during this period was 62,535. A total of 22,870 individuals were diagnosed with a behavioral health-related disorder during the study period. Of this population, 1,414 individuals required an evacuation. The relative risk of the top 30 diagnosis codes used during the initial visit of individuals during the study period was calculated. Within this group of initial diagnoses, F32.9 'Major depressive disorder, single episode, unspecified' had the highest proportion evacuated at 15.9%. There is a broad array of behavioral health-specific diagnoses used initially in the care of behavioral health disorders with a great variation in their association with evacuation risk. Variations of diagnoses associated with anxiety, depressive, and adjustment disorders are most associated with eventual evacuation.

Design for safety in metro station evacuation: a study of fire emergency evacuation behavior and simulation

PurposeMetro stations have become a crucial aspect of urban rail transportation, integrating facilities, equipment and pedestrians. Impractical physical layout designs and pedestrian psychology impact the effectiveness of an evacuation during a metro fire. Prior research on emergency evacuation has overlooked the complexity of metro stations and failed to adequately consider the physical heterogeneity of stations and pedestrian psychology. Therefore, this study aims to develop a comprehensive evacuation optimization strategy for metro stations by applying the concept of design for safety (DFS) to an emergency evacuation. This approach offers novel insights into the management of complex systems in metro stations during emergencies.Design/methodology/approachPhysical and social factors affecting evacuations are identified. Moreover, the social force model (SFM) is modified by combining the fire dynamics model (FDM) and considering pedestrians' impatience and panic psychology. Based on the Nanjing South Metro Station, a multiagent-based simulation (MABS) model is developed. Finally, based on DFS, optimization strategies for metro stations are suggested.FindingsThe most effective evacuation occurs when the width of the stairs is 3 meters and the transfer corridor is 14 meters. Additionally, a luggage disposal area should be set up. The exit strategy of the fewest evacuees is better than the nearest-exit strategy, and the staff in the metro station should guide pedestrians correctly.Originality/valuePrevious studies rarely consider metro stations as sociotechnical systems or apply DFS to proactively reduce evacuation risks. This study provides a new perspective on the evacuation framework of metro stations, which can guide the designers and managers of metro stations.

Emergency evacuation risk assessment method for educational buildings based on improved extreme learning machine

In educational facility interiors, the risk of congestion and trampling among occupants during the evacuation process presents a significant safety concern. Therefore, assessing the risk of the evacuation process is of great practical and academic importance. To meet the requirements of rapid and timely risk assessment, this article proposes an emergency evacuation risk assessment model based on the Improved Extreme Learning Machine (ELM). The ELM with fast learning speed and good generalization performance is improved to form the Deep Extreme Learning Machine (DELM) and Kernel Based Extreme Learning Machine (KELM) models, and the Improved Seagull Optimization Algorithm (ISOA) was used to constitute the ISOA-DELM and ISOA-KELM models for training. Taking a university library as an example, the evaluation process of model data acquisition, training, and testing is analyzed and compared. The prediction accuracy of the ISOA-DELM and ISOA-KELM models proposed in this paper reached more than 92%. The results show that improved extreme learning machine models can enable an efficient and fast risk assessment.

An Integrated Data-Driven Predictive Resilience Framework for Disaster Evacuation Traffic Management

Maintaining smooth traffic during disaster evacuation is a lifesaving step. Traffic resilience is often used to define the ability of a roadway during disaster evacuation to withstand and recover its functionality from disturbances in terms of traffic flow caused by a disaster. However, a high level of variances due to system complexity and inherent uncertainty associated with disaster and evacuation risks poses great challenges in predicting traffic resilience during evacuation. To fill this gap, this study aimed to propose a new integrated data-driven predictive resilience framework that enables incorporating traffic uncertainty factors in determining road traffic conditions and predicting traffic performance using machine learning approaches and various space and time (spatiotemporal) data sources. This study employed an augmented Long Short-Term Memory (LSTM)-based approach with correlated spatiotemporal traffic data to predict traffic conditions, then to map those conditions to traffic resilience levels: daily traffic, segment traffic, and overall route traffic. A case study of Hurricane Irma’s evacuation traffic was used to demonstrate the effectiveness of the proposed framework. The results indicated that the proposed method could effectively predict traffic conditions and thus help to determine traffic resilience. The data also confirmed that the traffic infrastructures along the US I-75 route remained resilient despite the disturbances during the disaster evacuation activities. The findings of this study suggest that the proposed framework is applicable to other disaster management scenarios to obtain more robust decisions for the emergency response during disaster evacuation.