Grant: Discovery Grants Program - Individual

The performance of major truck crossings is critical to Canada's economic performance and trade relationships with the U.S. To date, research to study traffic at major Canadian land border facilities and corridors has been limited due to the lack of appropriate data. However, there is a critical need for developing and using accurate short-term predictive models that can help carriers, land border operators and traffic engineers determine traffic conditions at land borders in real-time up to two hours in advance. There is also a need for developing detailed simulation models that can help decision-makers to understand the impacts that disruptive vehicle technology (i.e., connected and autonomous) will have on border traffic conditions. The specific short-term objectives of this research program are: 1) Advance the current state of knowledge on land border crossing movements and supply chain processes in Canada with the help of real-time border related data; 2) Develop, implement, and test a variety of machine learning and deep learning models using real-time data collected from traffic sensors deployed by the applicant for the Ambassador Bridge, Canada's Busiest land border, to perform short-term prediction of border crossing times and traffic volumes; 3) Calibrate micro-analytical models to simulate and analyze car-truck interaction in a complex and highly congested border corridor and to simulate the impacts that connected and autonomous vehicles in the traffic stream will have on border traffic conditions; and 4) devise a list of measures to characterize truck freight fluidity at Canada's busiest land border crossings. In the long run, the objective of the conducted work will be to develop integrated simulation and microsimulation predictive models for freight transportation, trade flow and supply chain movements, to examine policies that could improve the performance of traffic on major congested corridors and cross-border points. The novelty of the proposed research program is threefold: 1) the work is the first of its kind to utilize real-time data obtained from dedicated border related traffic sensors for the Ambassador Bridge to understand border traffic patterns and delays; 2) the work will apply a suite of new machine learning and deep learning models to develop operational models that can perform real-time predictions for the border; and 3) the work will develop a regional microsimulation model for cross-border traffic movements to support the future transportation planning process for major Canadian cross-border corridors and facilities. To our knowledge, this is the only research program in Canada that is focused on such important and applied border related problem. Overall, this research program builds on the research work that the applicant has been conducting for the past 10 years at the Cross-Border Institute. The program will also contribute to the training of a number of highly qualified personnel.