Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Toronto

$69,000.00

Keeping Transit Moving: Advanced AI and Optimization Methods for Systems Operational Management

EF 2024-25

Résumé
High quality public transit is the linchpin of liveable and sustainable cities worldwide. Although transit has always faced financial and operational challenges in our cities, it now faces an environment that is increasingly uncertain and turbulent. More than ever, transit riders complain about their buses showing up late, sometimes more than one arriving together, and often little space (if any) is left to get on board! In cities with both rail and bus services, disruptions to rail services are also occurring more frequently which often unleash a mayhem across the entire transit network, buses included. As if these problems are not enough for transit agencies to contend with, but they are confronted daily with the big challenge of drivers reporting absent on a short notice, a problem which more than tripled after the pandemic. In many cases, planned bus services are cancelled due to unplanned driver absences. These problems combine to exacerbate an already poor user experience and deal a heavy financial blow to transit agencies. A recent study estimated the economic cost of user delays due to subway incidents in New York to be 389 million USD annually. Not to mention the disproportionate social impact of these problems, affecting marginalized communities more than others. All these problems, which are often intertwined, have a variety of causes, some internal to the transit ecosystem and some external. Transit agencies respond to these problems with actions that are typically based on professional judgment and experience, with very little use of the increasingly abundant and diverse data at their disposal and the growing power of AI. This project aims to tackle these problems by developing decision support tools based on emerging AI methods and available transit data. The first project will develop analytics for predicting service anomalies (mainly bus bunching and overcrowding) and a real-time decision recommendation system that mixes the power of predictive analytics with human experience in a coherent framework. In the second project, another decision support system will be developed to help transit agencies decide, upon any rail disruption incident, how many buses are required to serve as replacement shuttle buses and from which routes those buses should be pulled and when to arrive, while minimizing delays to affected bus users particularly those belonging to marginalized communities. The third project will develop tools to aid transit agencies predict unplanned driver absences and schedule stand-by drivers accordingly, again using leading edge AI and optimization methods. This research is important not only for transit personnel responsible for managing delays and unexpected events but primarily the riders who will enjoy a higher quality service. The benefits to Canada are substantial, reducing the cost of transit delays across the country and reaping financial gains from commercializing of the novel solutions of the proposed research.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-05499
Name nom
Shalaby, Amer
Department département
Civil Engineering - Civil Engineering
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
69000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
700
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Transportation systems and services
Area of application fr
Services et systèmes de transport
Research subject code
1003
Research subject group en
Civil engineering
Research subject group fr
Génie civil
Research subject en
Transportation engineering
Research subject fr
Génie du transport
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Keeping Transit Moving: Advanced AI and Optimization Methods for Systems Operational Management
Keywords
public transit; transit management; machine learning; prediction; optimization; data science; spareboard drivers; bus bridging; recommendation systems
Application summary
High quality public transit is the linchpin of liveable and sustainable cities worldwide. Although transit has always faced financial and operational challenges in our cities, it now faces an environment that is increasingly uncertain and turbulent. More than ever, transit riders complain about their buses showing up late, sometimes more than one arriving together, and often little space (if any) is left to get on board! In cities with both rail and bus services, disruptions to rail services are also occurring more frequently which often unleash a mayhem across the entire transit network, buses included. As if these problems are not enough for transit agencies to contend with, but they are confronted daily with the big challenge of drivers reporting absent on a short notice, a problem which more than tripled after the pandemic. In many cases, planned bus services are cancelled due to unplanned driver absences. These problems combine to exacerbate an already poor user experience and deal a heavy financial blow to transit agencies. A recent study estimated the economic cost of user delays due to subway incidents in New York to be 389 million USD annually. Not to mention the disproportionate social impact of these problems, affecting marginalized communities more than others. All these problems, which are often intertwined, have a variety of causes, some internal to the transit ecosystem and some external. Transit agencies respond to these problems with actions that are typically based on professional judgment and experience, with very little use of the increasingly abundant and diverse data at their disposal and the growing power of AI. This project aims to tackle these problems by developing decision support tools based on emerging AI methods and available transit data. The first project will develop analytics for predicting service anomalies (mainly bus bunching and overcrowding) and a real-time decision recommendation system that mixes the power of predictive analytics with human experience in a coherent framework. In the second project, another decision support system will be developed to help transit agencies decide, upon any rail disruption incident, how many buses are required to serve as replacement shuttle buses and from which routes those buses should be pulled and when to arrive, while minimizing delays to affected bus users particularly those belonging to marginalized communities. The third project will develop tools to aid transit agencies predict unplanned driver absences and schedule stand-by drivers accordingly, again using leading edge AI and optimization methods. This research is important not only for transit personnel responsible for managing delays and unexpected events but primarily the riders who will enjoy a higher quality service. The benefits to Canada are substantial, reducing the cost of transit delays across the country and reaping financial gains from commercializing of the novel solutions of the proposed research.