Evacuation Traffic Management Research Articles

Predicting hurricane evacuation behavior synthesizing data from travel surveys and social media

Evacuation behavior models estimated using post-disaster surveys are not adequate to predict real-time dynamic population response as a hurricane unfolds. With the emergence of ubiquitous technology and devices in recent times, social media data with its higher spatio-temporal coverage has become a potential alternative for understanding evacuation behaviour during hurricanes. However, these data are often associated with selection bias and population representativeness issues. To that extent, the current study proposes a novel data fusion algorithm to combine heterogeneous data sources from transportation systems and social media, in a unified framework to understand and predict real-time population response during hurricanes. Specifically, Twitter data of 2300 users are collected for evacuation response during Hurricane Irma and augmented behaviourally (probabilistically) with a representative National Household Travel Survey (NHTS) data, thus creating a hybrid dataset to improve the representativeness as well as provide a rich set of explanatory variables for understanding the evacuation behavior. The fusion process is conducted using a probabilistic matching method based on a set of common attributes across NHTS and Twitter. The fused dataset is employed to estimate the evacuation model and a comparison exercise is conducted to evaluate the performance of the model via fusion. The model fitness measures clearly demonstrate the improvement in data fit for the evacuation model through the proposed fusion algorithm. Further, we conduct a prediction assessment to illustrate the applicability of the proposed fusion technique and the results clearly highlight the improvement in the evacuation prediction rate achieved through the fused models. The proposed data-driven methods will enhance our ability to predict time-dependent evacuation demand for better hurricane response operations such as targeted warning dissemination and improved evacuation traffic management, allowing emergency plans to be more adaptive.

Bimodal Traffic Evacuation Management for Road Tunnels Considering Social Fairness: CTM-Based Model

Bimodal Traffic Evacuation Management for Road Tunnels Considering Social Fairness: CTM-Based Model

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.

A deep learning approach for network-wide dynamic traffic prediction during hurricane evacuation

Proactive evacuation traffic management largely depends on real-time monitoring and prediction of traffic flow at a high spatiotemporal resolution. However, evacuation traffic prediction is challenging due to the uncertainties caused by sudden changes in projected hurricane paths and consequently populations’ evacuation behavior. Moreover, modeling spatiotemporal traffic flow patterns requires extensive data over a longer time period, whereas evacuations typically last for two to five days. In this paper, we present a novel data-driven approach for predicting evacuation traffic at a network scale. We develop a dynamic graph convolutional long short-term memory neural network (DGCN-LSTM) model to learn the network dynamics during hurricane evacuation. We first train the model for non-evacuation period traffic data and found that the model outperforms existing deep learning models for predicting non-evacuation period traffic with an RMSE value of 226.84. However, when the model is applied for predicting evacuation traffic, the RMSE value increased to 1440.99. We overcome this issue by adopting a transfer learning approach with additional features related to evacuation traffic demand such as distance from the evacuation zone, time to landfall, and other zonal level features to control the transfer of information (network dynamics) from non-evacuation periods to evacuation periods. The final transfer learned DGCN-LSTM model performs well to predict evacuation traffic flow (RMSE = 399.69). The implemented model can be applied to predict evacuation traffic over a longer forecasting horizon (up to 6-hour). It will assist transportation agencies to activate appropriate traffic management strategies to reduce delays for evacuating traffic.

Modeling the impact of traffic management strategies on households' stated evacuation decisions

Evacuation traffic management has been implemented in large-scale disaster evacuations (such as hurricanes) to facilitate traffic flow and reduce travel delay. The outcomes of these strategies were quantified via traffic simulation but were assumed to have no/limited impacts on households' evacuation-related decisions. This study analyzed and modeled the impact of these strategies on five evacuation related household choices (evacuate/stay, departure time, route, vehicle, and destination) separately based on 415 responses collected from a stated preference survey. The survey was conducted in 2017 in coastal areas near Hampton Roads. Traffic management is likely to motivate some (32%) households to evacuate instead of sheltering in place. In addition, not all households take the interstates with traffic management even though route choice is the most likely to be affected by traffic management. Households need more information for their departure time and destination choices in response to traffic management since they are more likely to feel uncertain of the impact of the strategies on these decisions. Such uncertainty in departure time and destination choice is especially true for those who evacuate late and for those who choose accommodations other than the home of friends/relatives. Emergency management agencies should also be aware that some households may intentionally depart before traffic management starts. Among the five choices, vehicle use is the choice that is least likely to be affected. All the above-mentioned findings potentially affect parameter specifications in evacuation traffic simulation studies. This study then used multinomial logit models to estimate the impacts of traffic management on each of the five evacuation related choices. The model estimation results can help improve evacuation demand predictions and guide evacuation information dissemination.

Lane-based multi-class vehicle collaborative evacuation management

Mixed traffic evacuation management is recognized as a critical and challenging task. This paper develops a bi-level model to address the multi-class vehicle collaborative evacuation problem. The upper-level program is a mixed-integer nonlinear programming (MINLP) model to determine the optimal lane allocation scheme according to the fleet size. The lower-level program is formulated as multiple independent system optimal dynamic traffic assignment (SO-DTA) problems to load mixed traffic flow. A two-layer solution method integrating branch-and-bound algorithm is developed to solve the model. Finally, the optimization model is applied in a small network and a real-world network. Results demonstrate that (1) the evacuation performance of multi-class vehicle collaboration is better than that of single-class vehicles under the medium demand levels; (2) the proposed model realizes the coupling among evacuation demand, fleet size, and road network capacity; (3) the shortest path should first be allocated to the bus during a mass evacuation.

Predicting traffic demand during hurricane evacuation using Real-time data from transportation systems and social media

In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of people across multiple states in the United States. Under hurricane evacuation, efficient traffic operations can maximize the use of transportation infrastructure, reducing evacuation time and stress due to massive congestion. Evacuation traffic prediction is critical to plan for effective traffic management strategies. However, due to the complex and dynamic nature of evacuation participation, predicting evacuation traffic demand long ahead of the actual evacuation is a very challenging task. Real-time information from various sources can significantly help us reliably predict evacuation demand. In this study, we use traffic sensor and Twitter data during hurricanes Matthew and Irma to predict traffic demand during evacuation for a longer forecasting horizon (greater than 1 h). We present a machine learning approach using Long-Short Term Memory Neural Networks (LSTM-NN), trained over real-world traffic data during hurricane evacuation (hurricanes Irma and Matthew) using different combinations of input features and forecast horizons. We compare our prediction results against a baseline prediction and existing machine learning models. Results show that the proposed model can predict traffic demand during evacuation well up to 24 h ahead. The proposed LSTM-NN model can significantly benefit future evacuation traffic management.

Evacuation Traffic Management under Low Visibility and Toxic-Gas Leakage Disasters

The majority of existing evacuation models neglect the fact that leaking toxic gas usually degrades atmospheric visibility under chemical disasters. This paper takes the impact of leaking toxic gas on atmospheric visibility into account in evacuation problems. The reduction of traffic speed and road capacity under conditions of low atmospheric visibility is introduced and has stochastic features. Further, a robust evacuation traffic management model for evacuation scenarios of low visibility and toxic-gas-leakage disasters is developed to obtain optimal evacuation plans. The proposed robust optimization model can guarantee the feasibility of optimal evacuation plans to the evacuation scenarios of low atmospheric visibility under corresponding robustness requirements. Numerical experiments show that neglecting the impact of low atmospheric visibility overestimates the performance of optimal evacuation plans and even assigns evacuation traffic to roads with bad driving conditions under chemical disasters.

Evacuation Traffic Management under Diffusion of Toxic Gas Based on an Improved Road Risk Level Assessment Method

Toxic gas leakage has diffusion characteristics and thus dynamically affects surrounding zones. Most of current evacuation traffic management models set the road risk level as a static value, which is related to the distance to the hazard source, or a dynamic value, which is determined by the toxic gas concentration. However, the toxic gas propagation direction is not considered, and this may lead some evacuees driving from less dangerous regions to higher dangerous regions. To address the shortcomings of traditional evacuation traffic management models, this paper proposes an improved road risk level assessment method based on the difference of the risk levels of upstream and downstream zones of road and develops a safer evacuation traffic management model under the diffusion of toxic gas. The Cell Transmission Model (CTM) is used to depict the evacuation traffic loading process. A numerical test is carried out on Nguyen and Dupuis Network. The test results show that the improved road risk level assessment method can avoid the evacuees driving into higher risk level regions from less dangerous regions.

Trade-off between signal and cross-elimination strategies during evacuation traffic management

It is well accepted in literature that the strategy of using crossing-elimination (or uninterrupted-flow) intersections has the advantage over signals in expanding network capacity during evacuation. This result holds well in a static evacuation network in which flow patterns are not explicitly modeled (e.g., queuing on network links and time-varying evacuation demand). This paper examines the problem of selecting and distributing signal control and uninterrupted flow strategies in evacuation traffic management. More specifically, the following critical issues are investigated: (1) Does an optimal distribution between signal and uninterrupted flow strategies exist in a dynamic evacuation network and what is it? and (2) How to best plan turning restriction and signal timings at those intersections with different control strategies? Results show that the best distribution of uninterrupted flow and signalized intersections exists to yield the minimum evacuation clearance time. Intersections located within the demand generating area (i.e., the impacted area) are more likely to be selected by the model as uninterrupted flow ones to facilitate fast access of evacuees to the evacuation routes; while signals tend to locate outside the impact area to reduce detours of evacuation traffic to destination. The proposed model outperforms other scenarios in terms of reducing evacuation clearance time, which demonstrates its effectiveness.

Managing Emergency Traffic Evacuation With a Partially Random Destination Allocation Strategy: A Computational-Experiment-Based Optimization Approach

Natural or man-made disasters can cause huge losses of human life and property. One of the effective and widely used response and mitigation strategies for these disasters is traffic evacuation. Evacuation destination choice is critical in evacuation traffic planning and management. In this paper, we propose a partially random destination allocation strategy for evacuation management. We present a metamodel-based simulation optimization method to design the strategy. The proposed method uses a quadratic polynomial as a metamodel, within which a degree-free trust region algorithm is developed to solve the proposed model. The performance of the proposed method is evaluated based on a subnetwork of Beijing with two different traffic demands. Computational experiments demonstrate that the proposed method can yield a well-performed strategy, leading to reduced network clearance times.

A multi-perspective dynamic network performance efficiency measurement of an evacuation: A dynamic network-DEA approach

In this paper, we consider evacuation planning as a multi-perspective, multi-system, and multi-process operation, and explore how a dynamic network performance measurement approach helps us to measure the efficiency performance of this system of systems. Two different perspectives are studied, i.e., that of the transportation agency and that of the household. These perspectives are linked through intermediate outputs and carry-overs generated by the underlying processes associated with each perspective. Within this context, we propose a theoretical representation of a slacks-based dynamic network DEA approach for measuring evacuation performance when a ramp closure evacuation traffic management strategy is considered. This representation requires a theoretical yet tractable conceptual framework that incorporates stakeholder perspectives, evacuation-related systems, processes and their interdependencies. This research combines the dynamic network DEA approach with traffic engineering and socio-behavioral theory of protective action. An initial exploration of the proposed approach allows for the discovery of efficiency interdependencies among perspectives, which in turn provides useful information and insights for the future design of holistic evacuation traffic management strategies.

Optimization of Evacuation Traffic Management With Intersection Control Constraints

Route guidance instructions are crucial in the implementation of an evacuation plan. Considering travelers' compliance with these instructions is controllable by adopting traffic management at intersections, a simulation-based framework for optimizing traffic management is presented with the objective function of maximizing evacuation efficiency with uncertain budget constraint. A comprehensive case study illustrates the sensitivity of traffic simulation model with traffic demand, duration of hazard, and traffic management. The specific analyses on network performances provide some practical insights. In reality, mandatory traffic management is unnecessary as the optimal instructions are unavailable. Well-staged departure and appropriate enforcement of traffic management at intersections are recommended, which contribute to extensive distribution of traffic flow and then high-efficiency evacuation.

Simulation Study of Evacuation Routes and Traffic Management Strategies in Short-Notice Emergency Evacuation

Emergency evacuation traffic is simulated in response to an assumed chlorine gas spill incident in downtown Jackson, Mississippi. The best evacuation corridors are identified, and possible effective traffic management strategies are compared to increase the cumulative number of vehicles evacuated out of the protective action zone and to decrease the average travel times for evacuees. To relieve the heavy traffic congestion around the spill location caused by the sudden increase in demand, traffic management strategies (law enforcement for traffic control, contraflow operations, and variable message signs) are tested on the three major arterial streets in the protective action zone to improve evacuation performance over a baseline traffic management strategy. A multiway analysis of variance was conducted for the simulation results to numerically assess the effect of each factor that might contribute to the performance of the short-notice evacuation. Results of a comparison of evacuation scenarios used to determine evacuation effectiveness and statistical analysis indicated that ( a) selection of a best contraflow operation route depends on interference from intersecting links and the cost of deploying traffic management and ( b) the use of both contraflow and variable message signs could improve evacuation performance over using neither or only one of the two strategies.

On Criticality Assessment Based Evacuation Modeling: Empirical Findings

In this paper, criticality assessment is introduced as an intermediate step in evacuation modeling, in order to identify the optimal allocation of measures for the development of evacuation traffic management strategies. The criticality assessment of network components is reviewed and analyzed concerning its sensitivity in demand and supply variations. It is proposed that when highlighting the most critical component(s) of a network under evacuation conditions, one could either intervene to the component(s) itself, assuring the preservation of its operation and enhancement of functionality or intervene to alternative component(s) of the network that could offer attractive alternatives to the critical one. The two intervention approaches are presented in detail and evaluated in terms of minimizing travel times of evacuees in the Sioux Falls test network. 

Simulation analysis for evacuation under congested traffic scenarios: a case study

In this paper a new simulation modeling approach to support evacuation traffic management is introduced and a case study is presented. Traditional traffic simulation models neglect some real-life factors that need to be considered in an evacuation, such as the effect of road information and active control measures to manage traffic flow while vehicles are competing to find the best or preferred route. A passive equilibrium-seeking modeling approach may not be suitable for evacuation trip analysis due to limited route capacity and likely severe congestion during an evacuation. This paper introduces a new updated cell transmission model using discrete-event simulation, which can review and analyze the preferred path of evacuation traffic from multiple starting locations (or originations) to multiple destinations. Using this approach, case studies are conducted based on the user equilibrium principle, since it represents a natural behavior in an evacuation process. This research also demonstrates that, with the help of the cell transmission simulation model, an active traffic control mechanism can be evaluated. This study found that active traffic control measures are capable of decreasing total travel time during an evacuation by thousands of vehicle hours. Incorporating behavior consideration into the evacuation planning can help form a more accurate and realistic analysis of an evacuation plan.

Evaluation of different contraflow strategies for hurricane evacuation in Charleston, South Carolina

Limited specific evidence is available on the effectiveness of using contraflow as an evacuation traffic management tool. This study was conducted to determine the best combination of strategy options for evacuating Charleston, SC, along route I-26 during the event of a hurricane or other events. PARAMICS microscopic traffic simulator was used to evaluate the impact of each combination of evacuee response timing and traffic control strategy, such as contraflow, with respect to average vehicular travel time and evacuation duration. Analysis revealed the combination of management strategies that created the lowest evacuation durations and travel times for several types of anticipated evacuee responses. Furthermore, a proposed reconfiguration of the I-526/I-26 interchange for contraflow operations produced additional savings in travel times and evacuation durations. These findings support the use of all lanes for contraflow during all evacuations and provide justification to examine a possible reconfiguration of the I-526/I-26 interchange for use during evacuations.

Dynamic Plan Generation and Real-Time Management Techniques for Traffic Evacuation

Surface transportation systems play a crucial role in responding to natural disasters and other catastrophic incidents that have devastating impacts on the lives of people all over the world. Intelligent transportation systems (ITS) can play an important role not only in improving the operational efficiency of a transportation system but also in enhancing its safety and security. In this paper, we propose new techniques for augmenting ITS to improve and support homeland security. In particular, we propose two evacuation algorithms, i.e., all-links and fastest-links, and perform simulation studies to compare their performance. These algorithms are part of a smart traffic evacuation management system (STEMS) developed to provide rapid and efficient response to human-caused threats and disasters by automatically generating dynamic evacuation plans based on incident location and scope and subsequently automatically controlling traffic lights to direct evacuation traffic in a safe manner.

Online Behavior-Robust Feedback Information Routing Strategy for Mass Evacuation

Disaster response to manmade and natural events involves the quick evacuation of the affected population to safer areas. Given the potential for large-scale loss of life and property, there is a need for effective emergency strategies to mitigate the adverse effects of these disasters. Most existing evacuation traffic management strategies focus on increasing network capacity along the evacuation direction such as contraflow lanes, but other information or routing strategies have not been fully explored. Optimal routing strategies can be presented to evacuees as recommended routes. Advising evacuees that take system-optimal routes help balance the distribution of evacuation flows among multiple evacuation routes. However, a critical aspect in evaluating the effectiveness of such strategies is to properly account for the possible evacuation route-choice behavior. This study analyzed the situation in which evacuees are given a set of system-optimal paths; evacuees choose their evacuation routes, following a certain route-choice behavior (rational, panic, etc.). Discussions focus on the extent to which the routing effectiveness can be properly estimated, subject to the route-choice behavior. This paper further proposes a behavior-robust feedback information routing (FIR) strategy to further improve system performance. The FIR is based on the concept of closed-loop control that reacts to the system state and updates the advised routes. The FIR that targets the system-optimal routing strategy has been shown to be effective and robust for real-time evacuation traffic management.

Model Reference Adaptive Control Framework for Real-Time Traffic Management under Emergency Evacuation

Recent natural or man-made disasters around the world have provided compelling evidence that transportation system plays a crucial role in the emergency evacuation and have stressed the need for effective evacuation traffic management to maximize the utilization of the transportation system and to minimize fatalities and losses. This paper presents a model reference adaptive control (MRAC) framework for real-time traffic management under emergency evacuation. Distinct from the well-studied evacuation planning, real-time traffic management for evacuation aims to dynamically guide (control) traffic flow under evacuation in such a way that certain system objective (e.g., minimization of fatalities or property losses) could be achieved. The proposed framework is based on both dynamic network modeling techniques and adaptive control theory, by considering the traffic network under evacuation as a dynamic system. First, a prescriptive dynamic traffic assignment model is applied to predict, in a short-term and rolling-horizon manner, the desired traffic states based on certain system optimal objectives. This model will serve as a reference point for the adaptive control. Then, the adaptive control system integrates these desired states and the current prevailing traffic conditions collected via the sensing system to produce real-time traffic control schemes. Finally, these traffic control schemes are implemented in the field to guide the real-world traffic flow to evolve towards the desired states. Simulation studies provided in this paper show that the proposed framework based on MRAC can significantly improve the performance of real-time evacuation traffic management.