New paper: Lin Y, Li J, Porr A, Logan G, Xiao N, Miller HJ (2023) “Creating building-level, three-dimensional digital models of historic urban neighborhoods from Sanborn Fire Insurance maps using machine learning.” PLoS ONE 18(6): e0286340. https://doi.org/10.1371/journal.pone.0286340.
Abstract. Sanborn Fire Insurance maps contain a wealth of building-level information about U.S. cities dating back to the late 19th century. They are a valuable resource for studying changes in urban environments, such as the legacy of urban highway construction and urban renewal in the 20th century. However, it is a challenge to automatically extract the building-level information effectively and efficiently from Sanborn maps because of the large number of map entities and the lack of appropriate computational methods to detect these entities. This paper contributes to a scalable workflow that utilizes machine learning to identify building footprints and associated properties on Sanborn maps. This information can be effectively applied to create 3D visualization of historic urban neighborhoods and inform urban changes. We demonstrate our methods using Sanborn maps for two neighborhoods in Columbus, Ohio, USA that were bisected by highway construction in the 1960s. Quantitative and visual analysis of the results suggest high accuracy of the extracted building-level information, with an F-1 score of 0.9 for building footprints and construction materials, and over 0.7 for building utilizations and numbers of stories. We also illustrate how to visualize pre-highway neighborhoods.
New publication: Liu, L., Kar, A., Tokey, A. Le, H.T.K. and Miller, H.J. (2023) “Disparities in public transit accessibility and usage by people with mobility disabilities: An evaluation using high-resolution transit data,” Journal of Transport Geography, 109, 103589.
Abstract: Many people with mobility disabilities (PwMD) rely on public transit to access crucial resources and maintain social interactions. However, they face higher barriers to accessing and using public transit, leading to disparities between people with and without mobility disabilities. In this paper, we use high-resolution public transit real-time vehicle data, passenger count data, and paratransit usage data from 2018 to 2021 to estimate and compare transit accessibility and usage of people with and without mobility disabilities. We find large disparities in powered and manual wheelchair users’ accessibility relative to people without disabilities. The city center has the highest accessibility and ridership, as well as the highest disparities in accessibility. Our scenario analysis illustrates the impacts of sidewalks on accessibility disparities among the different groups. We also find that PwMD using fixed-route service are more sensitive to weather conditions and tend to ride transit in the middle of the day rather than during peak hours. Further, the spatial pattern of bus stop usage by PwMD is different than people without disabilities, suggesting their destination choices can be driven by access concerns. During the COVID-19 pandemic, accessibility disparities increased in 2020, and PwMD disproportionately avoided public transit during 2020 but used it disproportionately more during 2021 compared to riders without disabilities. This paper is the first to examine PwMD’s transit experience with large high-resolution datasets and holistic analysis incorporating both accessibility and usage. The results fill in these imperative scientific gaps and provide valuable insights for future transit planning.
On April 14, I had the opportunity to give a lecture in the Mobility and Planning for Human-scale Cities lecture series organized by the Mobility Lab at the University of Tartu in Estonia, sponsored by the US Speaker Program of the US Department of State.
Mobility is central to urbanity, and urbanity is central to our common future as the world’s population crowds into urban areas. This is creating a global mobility crisis due to the unsustainability of our 20th century transportation systems for a crowded and connected 21st century world. We need to move beyond inflexible, unsustainable and brittle car-dominated mobility monocultures to flexible, sustainable and resilient mobility polycultures with a wide spectrum of integrated mobility options. This transition is hard because mobility is complex, a wicked problem and a fundamental social dilemma.
In this lecture, I address the transition towards sustainable mobility. I discuss how we can leverage the urban data revolution to resolve these challenges. In particular, I focus on the role of next generation urban observatory science that respects complexity, embraces uncertainty and conflicting values, facilitates urban experimentation and creates environments for collaboration and knowledge co-production. I identified the major scientific challenges, merits and broader impacts of the observatory approach to transportation and urban science.
A recording of the lecture is available via the link below:
Why is sustainable mobility so hard? Some observations on the paths forward – 14 April 2023