Search

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. [ABSTRACT FROM AUTHOR]

Shelters are safe facilities that protect a population from possible damaging effects of a disaster. For that reason, shelter location and traffic assignment decisions should be considered simultaneously for an efficient evacuation plan. In addition, as it is very difficult to anticipate the exact place, time, and scale of a disaster, one needs to take into account the uncertainty in evacuation demand, the disruption/degradation of evacuation road network structure, and the disruption in shelters. In this study, we propose an exact algorithm based on Benders decomposition to solve a scenario-based two-stage stochastic evacuation planning model that optimally locates shelters and that assigns evacuees to shelters and routes in an efficient and fair way to minimize the expected total evacuation time. The second stage of the model is a second-order cone programming problem, and we use duality results for second-order cone programming in a Benders decomposition setting. We solve practical-size problems with up to 1,000 scenarios in moderate CPU times. We investigate methods such as employing a multicut strategy, deriving Pareto-optimal cuts, and using a preemptive priority multiobjective program to enhance the proposed algorithm. We also use a cutting plane algorithm to solve the dual subproblem since it contains a constraint for each possible path. Computational results confirm the efficiency of our algorithms. [ABSTRACT FROM AUTHOR]

• Demonstrates the use large-scale data for network-wide traffic prediction during evacuation. • Develops a dynamic graph convolutional neural network model to learn network dynamics. • Implements a transfer learning based approach to incorporate evacuation context. • Tests model performance using real-world traffic data from Hurricane Irma. 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. [ABSTRACT FROM AUTHOR]

Traffic management during an evacuation and the decision of where to locate the shelters are of critical importance to the performance of an evacuation plan. From the evacuation management authority’s point of view, the desirable goal is to minimize the total evacuation time by computing a system optimum (SO). However, evacuees may not be willing to take long routes enforced on them by a SO solution; but they may consent to taking routes with lengths not longer than the shortest path to the nearest shelter site by more than a tolerable factor. We develop a model that optimally locates shelters and assigns evacuees to the nearest shelter sites by assigning them to shortest paths, shortest and nearest with a given degree of tolerance, so that the total evacuation time is minimized. As the travel time on a road segment is often modeled as a nonlinear function of the flow on the segment, the resulting model is a nonlinear mixed integer programming model. We develop a solution method that can handle practical size problems using second order cone programming techniques. Using our model, we investigate the importance of the number and locations of shelter sites and the trade-off between efficiency and fairness. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM PUBLISHER]