Real‐Time Recommendations for Traffic Control in an Intelligent Transportation System (ITS) During an Emergency Evacuation: Phase I Studies
-
2020-12-01
-
Details:
-
Creators:
-
Corporate Creators:
-
Corporate Contributors:
-
Subject/TRT Terms:
-
Publication/ Report Number:
-
Resource Type:
-
Geographical Coverage:
-
Edition:Final Report: May 2019 – December 2020
-
Corporate Publisher:
-
Abstract:Recent hurricanes such as Irma (2017) and Florence (2018) caused mass evacuations and the issues occurring during the evacuations have been brought to the public attention. To address these issues, the project team has investigated significant cues for evacuation planners’ decisions using a Linear Lens Model and machine learning algorithms, and has analyzed traffic data during hurricane evacuations in North Carolina to discover spatial-temporal evacuation traffic patterns and create predictive models of hurricane evacuation traffic volumes. The results show that only one of the seven cues tested (wind speed) contributes to evacuation planners’ decisions and the sensor locations at the same county and adjacent counties form the cluster for evacuation traffic prediction. These models and findings can support the deployment of an effective evacuation and improve the mobility of the people and evacuation resources during a hurricane. The authors have also proposed and tested the quantitative methods to quantify a hurricane disruption to the U.S. airport network and identify feasible airports to reroute disrupted flights. Our results show that the proposed methods can identify the airports to be disrupted by an approaching hurricane and feasible airports for flight rerouting, which can support airlines administrators to divert flights from the affected airports.
-
Format:
-
Funding:
-
Collection(s):
-
Main Document Checksum:
-
Download URL:
-
File Type: