Deep Learning Approach for Predictive Analytics to Support Diversion during Freeway Incidents

Route diversion during incidents on freeways has been proven to be a useful tactic to mitigate non-recurrent congestion. However, the capacity constraints created by the signals on the alternative routes put limits on the diversion process since the typical time-of-day (TOD) signal control cannot handle the sudden increase in the traffic on the arterials because of diversion. Thus, there is a need for active transportation management strategies that support agencies in identifying the potential diversion routes for freeway incidents and the need for adjusting the traffic signal timing under different incident and traffic conditions. This paper investigates the use of a data analytic approach based on the long short-term memory (LSTM) deep neural network method to predict the alternative routes dynamically using incident attributes and traffic status on the freeway, and travel time on both the freeway and alternative routes during the incident. Additionally, a methodology is proposed for the development of special signal plans for the critical intersections on the alternative arterials based on the results from the LSTM neural network, combined with simulation modeling, and signal timing optimization. The methodology developed in the paper can be easily implemented by the transportation agencies, as it is based on data that are generally available to the agencies. The results from this paper indicate that the developed methodology can be used as part of a decision support system (DSS) to manage the traffic proactively during the incidents on the freeways.