Public Transportation Modeling and design
In large cities with historically engrained transportation habits, it is difficult to predict the effects of introducing new modes of transportation. Major infrastructure projects end up being severely underused or lead to unexpected disruptive effects. Planners need to make use of all the data available to design transportation systems that truly meet the needs of their city’s residents. This includes tapping into existing human behavior by extracting patterns from diverse sources of data and understanding how that translates into transportation demand and projecting how people will use new modes of transportation. Additionally, government agencies need to understand how these results are used to inform plans for new developments and infrastructure. They are also interested in understanding how those plans alleviate current bottlenecks and manage transportation demand more effectively within cities suffering from urban sprawl.
What we did
Using a diverse range of data, from public infrastructure to telecom to social media activity, we provided our clients with richly detailed measures of mobility patterns, transportation usage, and demographic concentrations. In the process, we developed data-infused transportation models to identify the existing causes of traffic and study the interplay between congestion and new public transit options. Combined with bilingual surveys on walking habits and cultural preferences, we designed a simulation that was uniquely tailored to the city that we studied. Additionally, we conducted spatial analyses to detect areas of the city that influence overall mobility patterns and congestion the most. We also linked them to businesses and services to identify the relationship between amenities and mobility habits. We combined our work into an interactive web platform that let users visualize a broad selection of data, explore our results, and run further analyses on the city’s transportation system.
We provided our clients with detailed analyses of urban mobility patterns, including rich data sets that encoded when and where people travel. We also analyzed the resulting strain on the city’s transportation infrastructure and identified the sources of strain, highlighting areas that should be targeted to alleviate congestion most effectively. We used this work to study the effectiveness of a new infrastructure project to introduce a comprehensive public transit system in the city. Additionally, we designed innovative applications of machine learning to identify how neighborhoods affect the mobility patterns of residents across the city and revealed how specific types of businesses and services drive their behavior. To bring everything together, we designed an interactive web platform to showcase all the data we gathered, the results we generated, and the analyses we designed to interested users and urban planners.