Transport for London
Transport for London (TfL) is a local government body responsible for the transport system in Greater London, England.TfL has responsibility for London's network of principal road routes, for various rail networks including the London Underground, London Overground, Docklands Light Railway and TfL Rail. It does not control National Rail services in London, however, but does for London's trams, buses and taxis, for cycling provision, and for river services. The underlying services are provided by a mixture of wholly owned subsidiary companies (principally London Underground), by private sector franchisees (the remaining rail services, trams and most buses) and by licensees (some buses, taxis and river services). TfL is also responsible, jointly with the national Department for Transport (DfT), for commissioning the construction of the new Crossrail line, and will be responsible for franchising its operation once completed.
The MIT Transit Lab has partnered with TfL since 2005, spearheading research on the use of data from the Oyster fare payment system to improve TfL’s understanding of how London’s public transport system is being used, how well it is performing, and how it may be improved. A continuing focus of this research has been the inference of public transport origin to destination travel patterns from Oyster data, which has led to the development of ODX, a tool for estimating aggregate travel on public transport, which is now widely used within TfL, as well as by other transit agencies in the US, including the MBTA, CTA and WMATA. Other MIT research also was instrumental in the expansion of the Oyster system to incorporate bank card and mobile phone fare payments along with Oyster card payments, significantly reducing barriers to use of public transport in London for many customers. Over the fifteen years of this research partnership, the research agenda has continually evolved to support the priorities of TfL, and has increasingly focused on the potential for new services such as demand responsive service, shared-ride and autonomous vehicles to improve the performance of the integrated London urban transport system.
Transit Assignment Under Unplanned Network Disruptions
This research project created a dynamic passenger assignment model designed to accurately and efficiently model the impact on the Underground network of passenger behavior during unplanned disruptions. Taking into account the limited knowledge of system conditions that passengers have during disruptions allows the model to identify disruption impacts that existing models may omit.
Simulation and Analysis of New Mobility
At a strategic level, JTL is developing simulation and analysis platforms to understand and communicate the impact of new infrastructure and transformative technologies such as autonomous vehicles. Some of these methodologies and tools have been featured at the UK Science Museum’s Our Lives in Data exhibit. The strong record and commitment of JTL and TfL make this an ideal research partnership for understanding and shaping the future of urban transport.
Discovering Latent Activity Patterns from Transit Smart Card Data: A Spatiotemporal Topic Model
Zhan Zhao, Haris N. Koutsopoulos and Jinhua Zhao
Transportation Research Part C
Although automatically collected human travel records can accurately capture the time and location of humanmovements, they do not directly explain the hidden semantic structures behind the data, e.g., activity types. This work proposes a probabilistic topic model, adapted from Latent Dirichlet Allocation (LDA), to discover representative and interpretable activity categorization from individual-level spatiotemporal data in an unsupervised manner. Specifically, the activity-travel episodes of an individual user are treated as words in a document, and each topic is a distribution
over space and time that corresponds to certain type of activity. The model accounts for a mixture of discrete and continuous attributes---the location, start time of day, start day of week, and duration of each activity episode. The proposed methodology is demonstrated using pseudonymized transit smart card data from London, U.K. The results show that the model can successfully distinguish the three most basic types of activities---home, work, and other. As the specified number of activity categories increases, more specific subpatterns for home and work emerge, and both the goodness of fit and predictive performance for travel behavior improve. This work makes it possible to enrich human mobility data with representative and interpretable activity patterns without relying on predefined activity categories or heuristic rules.
Schedule-free High-Frequency Transit Operations
Gabriel E. Sanchez-Martinez, Nigel H.M. Wilson and Haris N. Koutsopoulos
High-frequency transit systems are essential for the socioeconomic and environmental well-being of large and dense cities. The planning and control of their operations are important determinants of service quality. Although headway and optimization-based control strategies generally outperform schedule-adherence strategies, high-frequency operations are mostly planned with schedules, in part because operators must observe resource constraints (neglected by most control strategies) while planning and delivering service. This research develops a schedule-free paradigm for high-frequency transit operations, in which trip sequences and departure times are optimized in real-time, employing stop-skipping strategies and utilizing real-time information to maximize service quality while satisfying operator resource constraints. Following a discussion of possible methodological approaches, a simple methodology is applied to operate a simulated transit service without schedules. Results demonstrate the feasibility of the new paradigm.
Incorporating Mobile Activity Tracking Data in a Transit Agency: Collecting, Comparing, and Trip Mode Inference
Tim Scully, John P. Attanucci and Jinhua Zhao
Transportation Research Board 96th Annual Meeting
The near ubiquity of smartphones has the potential to transform how researchers, companies, and public transit agencies understand travel behavior. This research analyzes how an emerging class of automatically-collected data based on smartphone GPS and sensor information - referred to here as mobile activity-tracking data - can be used in a transit agency to better understand travel behavior. Through a collaboration with Transport for London, multiple weeks of mobile activity-tracking data of London residents was collected between 2015 and 2016 using an application called Moves. Using this case study, this paper discusses the benefits of this new data and how it compares with other data at TfL and elsewhere and examines the process of collecting the data. Using the resulting data, this paper then compares the resulting trip records from the mobile activity tracking data with those from the automatic fare card data collected during the same period and same individuals. By comparing mobile activity tracking with an established, well-researched data source like AFC, the authors observe that while the trip match rate between the two data sources is high (68%) but not perfect. Next, the paper proposes a probabilistic framework to identify between motorized trip modes using mobile activity tracking data and and the public transit network. Specifically, the model uses both spatial characteristics, such as distance to public transit network, and trip characteristics such as speed in order to identify the trip mode as bus, rail, subway, or motorized non-public transit. Using logistic regression, classification tree, and random forest, this model achieves an accuracy of 90%, 91%, and 92% respectively.
Mark is a second year student in the Masters of Science in Transportation program. He has a bachelor's degree in civil engineering from Cooper Union in New York, as well as internship experience at the New York MTA and several consulting firms. His research interests include operations optimization, reliability analysis, and congestion reduction. He is working on a project with Transport for London that uses predictive maintenance to improve rolling stock reliability, based on an aggregation of wide-ranging data sources. Outside of MIT, Mark enjoys playing chess and biking around Boston.
Kerem is a PhD candidate at Northeastern University Industrial Engineering Department. He received his MS and BS degrees within Turkey from Bogazici University and Bilkent University respectively.
His previous research activities were focused on data mining/machine learning and more specifically time-series modeling. His main research interests are machine learning and its applications on real life problems. He is currently working on denied boarding estimation and prediction project for Mass Transit Railway (MTR) in Hong Kong.
Seyedmostafa, a PhD student at Northeastern University, has been a member of the MIT Transit Lab since Fall 2017. He holds a Master of Science degree in Traffic Engineering and Transportation Planning from Sharif University of Technology. His research interests lie at the intersection of the new on-demand mobility services and conventional transit systems, where he aims to address the weaknesses of one through the strengths of the other. He is currently studying the dynamic sharing of resources in bus operation using real-time data, as well as ways to consolidate ride-sharing to increase opportunities for shared mobility. Outside of school, he enjoys literature, learning new languages and going to the gym.