Planning, Meet Technology

By Reid Ewing

In the 13 years I've been writing for Planning magazine, I have been slow to pick up on the impact of technology on planning research and practice. In this column, I will try to make up for some lost time. There is a continuum between the initial conception of a research paper, draft submission to a journal, revision and resubmission, online publication, and final publication in hard copy. The two papers reviewed in this column are earlier in the process than my norm, but it in no way changes the basic point of the column. Planning, meet technology.

Planning still has a long way to go when it comes to taking advantage of drones, particularly in assessing how large parcels of land like parks are used. Photos courtesy Keunhyun Park and ewg3D/iStock/Getty Images Plus.

Uber's impacts

Online collaborative consumption models have emerged as a major trend over the recent years. Uber, Lyft, Booking.com, Airbnb, LendingClub, eBay, and other internet-enabled two-sided platforms are part of that push, made possible by advances in information and communication technology and human machine interaction.

These models are still relatively new for urban planners and designers. But it's time to explore their potential in planning — they allow for a never-before-seen amount of data: "big data." As an example, here, we will focus on ride-sourcing services like Uber and Lyft, which can be categorized as new modes of transportation.

Ride-sourcing services are getting more popular each year and their markets are growing, as have the publications related to the emergence of these services in multiple disciplines. Last year, Sadegh Sabouri, a doctoral student at the University of Utah, presented a paper titled "Does Uber Reduce Vehicle Ownership?" at the Association of Collegiate Schools of Planning Annual Conference. Since then, he and I have been working on this topic using National Household Travel Survey data for 2017 — by far the most up-to-date, authoritative source on the travel behavior of the American public.

The paper, which will be soon sent to a journal and is available from the authors, demonstrates that after controlling for sociodemographic and built environment variables, households using ride-sourcing services tend to have lower vehicle ownership. In addition, households living in counties where Uber, as the biggest ride-sourcing service in the world, has been established longer are more likely to own fewer vehicles.

With "data science" in the forefront getting lots of attention and interest, this paper uses both machine learning techniques (gradient boosting decision tree and random decision forests) and traditional statistics (Poisson and logistic regression) to reach the aforementioned conclusions and argues the superiority of the former techniques over the latter ones. Again, machine learning techniques and big data are new realms in planning, and there are myriad opportunities to utilize their great potential.

Big Data Keeps Getting Bigger

Ride-share companies are exploding across global markets — and amassing never-before-seen amounts of data vital to planning research.

Photo courtesy Uber.

Data source: Uber.

Use of drones

My February 2014 column describes how observational methods are often appropriate for urban-design research — particularly when it comes to what makes an active and successful street, plaza, or park — using examples of well-known observers like Jane Jacobs, Donald Appleyard, and William H. Whyte. Existing tools such as direct observation or video recording, however, suffer from limited reliability and cost-efficiency as employed by planners.

Keunhyun Park, an assistant professor at Utah State University, claims that unmanned aerial vehicles, or drones, can be a reliable and effective alternative because they can cover larger areas easily and provide video footage of user behaviors. While the use of UAVs has become popular in agriculture, forestry, engineering, and other fields, planners have yet to fully explore their potential.

Since his first drone paper came out in 2017, Park has published three articles on the use of UAVs for measuring behaviors in public spaces. The first two papers, which I coauthored, established and tested a new method of UAV observation in neighborhood parks (Landscape and Urban Planning, 2017) and streets (Journal of Planning Education and Research, in press), respectively. We found that UAV observations are reliable and valid enough compared to traditional on-the-ground protocols and discussed practical and social implications.

Using UAV-observed park-use data, Park has another paper in press at Environment & Behavior, a journal I have not yet featured, that accounts for neighborhood park use in light of park attributes and neighborhood conditions. Unlike studies in urban planning and travel behavior literature, those pertaining to park use have not fully explored urban form factors. His study provides insights into the role of neighborhood compactness and mixed land use on park vitality through the lens of drones. He also calls for interdisciplinary collaboration among urban planners and designers, landscape architects, and policy makers.

The incorporation of drone use in planning research and practice is far from finished, especially as technology continues to advance. Areas of exploration might include computer vision and machine-learning techniques for automated data collection and analysis and behavior mapping techniques for a micro-level understanding of design implications.

My first genuine foray into the interface between planning and technology came with the publication, in November 2018, of "Planning for Cars that Drive Themselves." As planning research and practice continue to embrace new technologies, expect to see a lot more related content in future columns.

Reid Ewing is a distinguished professor of city and metropolitan planning at the University of Utah, an associate editor of the Journal of the American Planning Association, and an editorial board member of the Journal of Planning Education and Research, Landscape and Urban Planning, and Cities. He coauthored this column with the two scholars mentioned above.