Testing the Capability of AI Art Tools for Urban Design.

This study aimed to evaluate the performance of three artificial intelligence (AI) image synthesis models, Dall-E 2, Stable Diffusion, and Midjourney, in generating urban design imagery based on scene descriptions. A total of 240 images were generated and evaluated by two independent professional evaluators using an adapted sensibleness and specificity average metric. The results showed significant differences between the three AI models, as well as differing scores across urban scenes, suggesting that some projects and design elements may be more challenging for AI art generators to represent visually. Analysis of individual design elements showed high accuracy in common features like skyscrapers and lawns, but less frequency in depicting unique elements such as sculptures and transit stops. AI-generated urban designs have potential applications in the early stages of exploration when rapid ideation and visual brainstorming are key. Future research could broaden the style range and include more diverse evaluative metrics. The study aims to guide the development of AI models for more nuanced and inclusive urban design applications, enhancing tools for architects and urban planners.

Hourly Associations between Heat Index and Heat-Related Emergency Medical Service (EMS) Calls in Austin-Travis County, Texas.

This paper aims to investigate the following research questions: (1) what are the hourly patterns of heat index and heat-related emergency medical service (EMS) incidents during summertime?; and (2) how do the lagged effects of heat intensity and hourly excess heat (HEH) vary by heat-related symptoms? Using the hourly weather and heat-related EMS call data in Austin-Travis County, Texas, this paper reveals the relationship between heat index patterns on an hourly basis and heat-related health issues and evaluates the immediate health effects of extreme heat events by utilizing a distributed lag non-linear model (DLNM). Delving into the heat index intensity and HEH, our findings suggest that higher heat intensity has immediate, short-term lagged effects on all causes of heat-related EMS incidents, including in cardiovascular, respiratory, neurological, and non-severe cases, while its relative risk (RR) varies by time. HEH also shows a short-term cumulative lagged effect within 5 h in all-cause, cardiovascular, and non-severe symptoms, while there are no statistically significant RRs found for respiratory and neurological cases in the short term. Our findings could be a reference for policymakers when devoting resources, developing extreme heat warning standards, and optimizing local EMS services, providing data-driven evidence for the effective deployment of ambulances.

DownScaleBench for developing and applying a deep learning based urban climate downscaling- first results for high-resolution urban precipitation climatology over Austin, Texas.

Cities need climate information to develop resilient infrastructure and for adaptation decisions. The information desired is at the order of magnitudes finer scales relative to what is typically available from climate analysis and future projections. Urban downscaling refers to developing such climate information at the city (order of 1 - 10 km) and neighborhood (order of 0.1 - 1 km) resolutions from coarser climate products. Developing these higher resolution (finer grid spacing) data needed for assessments typically covering multiyear climatology of past data and future projections is complex and computationally expensive for traditional physics-based dynamical models. In this study, we develop and adopt a novel approach for urban downscaling by generating a general-purpose operator using deep learning. This 'DownScaleBench' tool can aid the process of downscaling to any location. The DownScaleBench has been generalized for both in situ (ground- based) and satellite or reanalysis gridded data. The algorithm employs an iterative super-resolution convolutional neural network (Iterative SRCNN) over the city. We apply this for the development of a high-resolution gridded precipitation product (300 m) from a relatively coarse (10 km) satellite-based product (JAXA GsMAP). The high-resolution gridded precipitation datasets is compared against insitu observations for past heavy rain events over Austin, Texas, and shows marked improvement relative to the coarser datasets relative to cubic interpolation as a baseline. The creation of this Downscaling Bench has implications for generating high-resolution gridded urban meteorological datasets and aiding the planning process for climate-ready cities.

Identifying Hospital Deserts in Texas Before and During the COVID-19 Outbreak.

In this study, we proposed a GIS-based approach to analyzing hospital visitors from January to June 2019 and January to June 2020 with the goal of revealing significant changes in the visitor demographics. The target dates were chosen to observe the effect of the first wave of COVID-19 on the visitor count in hospitals. The results indicated that American Indian and Pacific Islander groups were the only ones that sometimes showed no shift in visitor levels between the studied years. For 19 of the 28 hospitals in Austin, TX, the average distance traveled to those hospitals from home increased in 2020 compared with 2019. A hospital desert index was devised to identify the areas in which the demand for hospitals is greater than the current hospital supply. The hospital desert index considers the travel time, location, bed supply, and population. The cities located along the outskirts of metropolitan regions and rural towns showed more hospital deserts than dense city centers.

Disparities in the Impacts of the COVID-19 Pandemic on Public Transit Ridership in Austin, Texas, U.S.A.

The COVID-19 pandemic has disrupted day-to-day lives and infrastructure across the United States, including public transit systems, which saw precipitous declines in ridership beginning in March 2020. This study aimed to explore the disparities in ridership decline across census tracts in Austin, TX and whether demographic and spatial characteristics exist that are related to these declines. Transit ridership data from the Capital Metropolitan Transportation Authority were used in conjunction with American Community Survey data to understand the spatial distribution of ridership changes caused by the pandemic. Using a multivariate clustering analysis as well as geographically weighted regression models, the analysis indicated that areas of the city with older populations as well as higher percentages of Black and Hispanic populations were associated with less severe declines in ridership, whereas areas with higher unemployment saw steeper declines. The percentage of Hispanic residents appeared to affect ridership most clearly in the center of Austin. These findings support and expand on previous research that found that the impacts of the pandemic on transit ridership have emphasized the disparities in transit usage and dependence across the United States and within cities.

Bike-Sharing Station Usage and the Surrounding Built Environments in Major Texas Cities.

This study analyzes the effect of different built environments on bike-share usage in nascent dock-based systems in three Texas cities. Past research offers little insight as to whether elements associated with higher bicycle usage in major cities affect ridership in secondary, developing bike-share markets within lower density American cities. In Austin and Houston, a positive relationship emerges between bike-share usage and proximity to high-comfort bicycle facilities. All three cities demonstrated surprisingly minimal relationship between bike-share usage and other proven drivers of bicycling activity in urban areas, which may result from system design for leisure- and recreation-based trips.

Durations of Dockless E-Scooter Trips Before and During the COVID-19 Pandemic in Austin, TX: An Analysis Using Hazard-Based Duration Models.

The pandemic arising from the 2019 coronavirus disease has significantly affected all facets of human life across the world, including economies and transportation systems, thereby changing people's travel behaviors. This research was aimed at exploring the relationship between socio-economic factors and e-scooter trip durations before and during the pandemic. We developed a hazard-based duration approach and estimated multiple spatial and non-spatial models on the basis of 2019 and 2020 dockless e-scooter data collected from the City of Austin's Open Data Portal. The results indicated an overall increase in e-scooter trip durations after the pandemic. Moreover, analysis of variables revealed potential changes in users' behavior before and during the pandemic. In particular, whereas e-scooter trip durations were found to be positively associated with aggregate travel time to work before the pandemic, this trend was reversed during the pandemic. In addition, during the pandemic, e-scooter travel time was positively correlated with the ratio of individuals with bachelor's degrees or greater to those with associate degrees or lower. However, no specific pattern was observed before the pandemic. Lastly, the results showed the presence of disparities within the study area; therefore, it is vital to extend e-scooter service areas to cover underserved communities.

Rental Housing Spot Markets: How Online Information Exchanges Can Supplement Transacted-Rents Data.

Traditional U.S. rental housing data sources such as the American Community Survey and the American Housing Survey report on the transacted market-what existing renters pay each month. They do not explicitly tell us about the spot market-that is, the asking rents that current homeseekers must pay to acquire housing-though they are routinely used as a proxy. This study compares governmental data to millions of contemporaneous rental listings and finds that asking rents diverge substantially from these most recent estimates. Conventional housing data understate current market conditions and affordability challenges, especially in cities with tight and expensive rental markets.

Impacts of COVID-19 on bike-sharing usages in Seoul, South Korea.

The COVID-19 pandemic and social distancing restrictions have had a significant impact on urban mobility. As micro mobility offers less contact with other people, docked or dockless e-scooters and bike-sharing have emerged as alternative urban mobility solutions. However, little empirical research has been conducted to investigate how COVID-19 might affect micro mobility usage, especially in a major Asian city. This research aims to study how COVID-19 and other related factors have affected bike-sharing ridership in Seoul, South Korea. Using detailed urban telecommunication data, this study explored the spatial-temporal patterns of a docked bike-sharing system in Seoul. Stepwise negative binomial panel regressions were conducted to find out how COVID-19 and various built environments might affect bike-sharing ridership in the city. Our results showed that open space areas and green infrastructure had statistically significant positive impacts on bike-sharing usage. Compared to registered population factors, real-time telecommunication floating population had a significant positive relationship with both bike trip count and trip duration. The model showed that telecommunication floating population has a significant positive impact on bike-sharing trip counts and trip duration. These findings could offer useful guidelines for emerging shared mobility planning during and after the COVID-19 pandemic.

Modeling factors contributing to dockless e-scooter injury accidents in Austin, Texas.

OBJECTIVE: Over the past few years, increased e-scooter ridership has raised concerns about the growing number of injury accidents involving e-scooters. Additionally, given the lack of appropriate e-scooter accident data, the extent to which built environment and socioeconomic factors affect e-scooter safety is unclear. In consideration of these issues, this study was aimed at identifying the factors contributing to the number of e-scooter injury accidents in Austin. METHODS: We developed zero-inflated Poisson (ZIP) and zero-inflated negative binomial (ZINB) models on the basis of 2018 dockless e-scooter injury accident data collected from the Patch platform. The results indicated that the ZIP model better fit the accident data. RESULTS: Significant variables included the ratio of 18- to 34-year-old males to their female counterparts, the median annual household income (in thousands), the ratio of public transport users to private transport users, the land use entropy index, the percentage of restaurants, and the percentage of educational centers in the study site. CONCLUSIONS: As e-scooter accidents are likely to occur in dense urban settings, a critical initiative is to develop new infrastructure, such as bike lanes, and/or extend sidewalks beyond core urban areas. Another highly recommended measure is to implement a demerit point system for the suspension of riders who engage in unsafe behaviors. Lastly, launching educational campaigns by e-scooter operators and law enforcement agencies will raise riders' awareness about road and personal safety.

Exploring temporal varying demographic and economic disparities in COVID-19 infections in four U.S. areas: based on OLS, GWR, and random forest models.

Although studies have previously investigated the spatial factors of COVID-19, most of them were conducted at a low resolution and chose to limit their study areas to high-density urbanized regions. Hence, this study aims to investigate the economic-demographic disparities in COVID-19 infections and their spatial-temporal patterns in areas with different population densities in the United States. In particular, we examined the relationships between demographic and economic factors and COVID-19 density using ordinary least squares, geographically weighted regression analyses, and random forest based on zip code-level data of four regions in the United States. Our results indicated that the demographic and economic disparities are significant. Moreover, several areas with disadvantaged groups were found to be at high risk of COVID19 infection, and their infection risk changed at different pandemic periods. The findings of this study can contribute to the planning of public health services, such as the adoption of smarter and comprehensive policies for allocating economic recovery resources and vaccines during a public health crisis.

Cities reshaped by Airbnb: A case study in New York City, Chicago, and Los Angeles.

In the last 10 years, Airbnb has rapidly grown from a simple, online bed and breakfast operation to a leading global hospitality service provider. Scholars have been using different spatial analysis tools to study its potential impacts on cities. To better understand Airbnb's impact this featured graphic applied a cartogram processing tool to reshape census tracts based on Airbnb listing intensity in three major US cities (New York City, Chicago, and Los Angeles). Results showed that different cities have different patterns of Airbnb listings. Census tracts in New York City became completely unrecognizable after the analysis, which indicted a highly skewed Airbnb distribution in the city. Compared with New York City, we saw less and least deformation in Chicago and Los Angeles, respectively, where Airbnb was more evenly distributed. The results showed that Airbnb listings were very evenly distributed in the large US cities. Airbnb would impose completely different impacts on different neighborhoods based on their locations.

Understanding the Shared E-scooter Travels in Austin, TX.

This paper investigated the travel patterns of 1.7 million shared E-scooter trips from April 2018 to February 2019 in Austin, TX. There were more than 6000 active E-scooters in operation each month, generating over 150,000 trips and covered approximately 117,000 miles. During this period, the average travel distance and operation time of E-scooter trips were 0.77 miles and 7.55 min, respectively. We further identified two E-scooter usage hotspots in the city (Downtown Austin and the University of Texas campus). The spatial analysis showed that more trips originated from Downtown Austin than were completed, while the opposite was true for the UT campus. We also investigated the relationship between the number of E-scooter trips and the surrounding environments. The results show that areas with higher population density and more residents with higher education were correlated with more E-scooter trips. A shorter distance to the city center, the presence of transit stations, better street connectivity, and more compact land use were also associated with increased E scooter usage in Austin, TX. Surprisingly, the proportion of young residents within a neighbourhood was negatively correlated with E-scooter usage.

An empirical analysis of Airbnb listings in forty American cities.

In the past ten years, Airbnb has rapidly grown from a small, online bed and breakfast product to a leading peer-to-peer hospitality magnate which operates in eighty thousand cities globally. It now offers rooms-for-rent, entire houses for rent, and even allows people to book 'experiences' through the platform. Consequently, cities, researchers, and the concerned public are focusing more on its impacts and exploring viable ways to regulate and facilitate the business while minimizing its potentially negative effects. To better understand Airbnb's operation in US cities, this paper explored how demographics, socioeconomics, and transportation might affect Airbnb listings in forty US cities. The results showed that Airbnb rentals were more likely to locate in neighborhoods with good transit service, short distances to the city center, and high median house value and household income. This study indicated the possible social inequality risk in the shared economy.

Using Open Source Data to Identify Transit Deserts in Four Major Chinese Cities.

The concept of transit deserts stems from the concept of food deserts. There is substantial research on transit deserts in developed countries. However, there is no known research that has studied this subject in Chinese cities. Using open-source data, this paper identified transit desert areas in four major Chinese cities (Beijing, Shanghai, Wuhan, Chengdu). The results show that: (1) In these four cities, the transit desert areas are mainly concentrated in city centers and hardly occur in any suburban areas, which is very different from the cases in the US. (2) Shanghai has the largest transit-dependent population living in transit deserts, followed by Beijing, Chengdu, and Wuhan. Chengdu has the smallest transit desert areas, followed by Shanghai, Wuhan, and Beijing. (3) An oversized transit-dependent population and incomplete transit systems in these cities might contribute to the transit deserts' occurrences. (4) Different distribution of population density, traveling preference, and transportation investment policy in Chinese and American cities might contribute to the different findings. By examining transit desert problems in major Chinese cities, this study brought people's attention to the gap between transit demand and supply in China.

Zoning changes and social diversity in New York City, 1990-2015.

The writings of Jane Jacobs led urbanists to advocate for increased social diversity in neighborhoods as a method of promoting vitality in public spaces. Since then, New York City has become both a role model and a testing ground for zoning changes that support this objective. However, since the 2000s community activists and scholars have argued that these zoning changes have led to the dislocation of communities of color and incentivized gentrification. This project analyzed panel social and housing census data from 1990 and 2015 to assess the validity of these arguments. Results suggest that zoning changes have limited and differentiated effects on the different dimensions of social diversity. For instance, they have strong effects on household income diversity, a nuanced effect on race diversity, and slightly negative effects on family type diversity.

Integrating social equity in highway maintenance and rehabilitation programming: A quantitative approach.

With limited funds and an aging highway infrastructure network, agency decision-makers are tasked with making the most cost-effective decisions while accounting for the environment and social equity. Several studies have accounted for the economic and environmental considerations in infrastructure management decisions. However, there have been limited studies which have proposed quantitative approaches for integrating social equity as part of the highway Maintenance and Rehabilitation (M&R) decision-making process. To address this gap in the literature, this paper proposes four optimization models (corresponding to policies) for achieving social equity in highway M&R programming. The underlying rationales behind these models include combinations of egalitarian, utilitarian, socialism, and Rawlsian equity theories. The developed models were then implemented in a numerical case study consisting of a network of 500 pavement sections. The case study results were evaluated using average condition scores and adaptations of the Gini Coefficient and the Theil Index. An inter-policy analysis suggests that for a similar performance in network condition, different policies yield varying inequity levels over time. Furthermore, step changes in the budget size also suggest that a higher budget size generally leads to a reduction in inequity although some policies perform better than others.

The Geography and Equity of Crowdsourced Public Participation for Active Transportation Planning.

Transportation planners increasingly use new forms of online public participation alongside traditional in-person approaches, including crowdsourcing tools capable of encouraging geographically specific input. Digital involvement may be particularly valuable in exploring methods to plan at a megaregional scale. Research is beginning to address digital inequalities, recognizing that broadband and smartphone access may restrict opportunities for disadvantaged groups. However, the geography and equity of participation remain pragmatic issues for practice and research. This paper reviews the geography and equity of the participation methods in Austin, Texas for active transportation (bicycling and pedestrian) through three approaches to co-produce informed plans: in-person meetings, public participation geographic information system (PPGIS), and an emerging smartphone platform that logs trips and encourages input on route quality. In addition to spatial analysis with standard deviational ellipses, we include qualitative case analysis to contextualize the geographic and equity implications of different participation approaches. Results show that both online techniques resulted in a larger geography for participation than in-person meetings, with the regional PPGIS covering the most area. However, review of the income levels in each area shows that use of the smartphone-based crowdsourcing platform was aligned with lowest-income areas. This study shows that online participation methods are not homogeneous regarding geography or equity. In some contexts, smartphone applications can help reach lower-income communities, even when compared with in-person meetings. Crowdsourcing tools can be valuable approaches to increase geography and equity of public participation in transportation planning.

Crowdsourcing Bike Share Station Locations: Evaluating Participation and Placement.

Problem research strategy and findings: Planners increasingly involve stakeholders in co-producing vital planning information by crowdsourcing data using online map-based commenting platforms. Few studies, however, investigate the role and impact of such online platforms on planning outcomes. We evaluate the impact of participant input via a public participation geographic information system (PPGIS), a platform to suggest the placement of new bike share stations in New York City (NY) and Chicago (IL). We conducted 2 analyses to evaluate how close planners built new bike share stations to those suggested on PPGIS platforms. According to our proximity analysis, only a small percentage of built stations were within 100 feet (30m) of suggested stations, but our geospatial analysis showed a substantial clustering of suggested and built stations in both cities that was not likely due to random distribution. We found that the PPGIS platforms have great promise for creating genuine co-production of planning knowledge and insights and that system planners did take account of the suggestions offered online. We did not, however, interview planners in either system, and both cities may be atypical, as is bike share planning; moreover, multiple factors influence where bike stations can be located, so not all suggested stations could be built. Takeaway for practice: Planners can use PPGIS and similar platforms to help stakeholders learn by doing and to increase their own local knowledge to improve planning outcomes. Planners should work to develop better online participatory systems and to allow stakeholders to provide more and better data, continuing to evaluate PPGIS efforts to improve the transparency and legitimacy of online public involvement processes.

How does 'park and ride' perform? An evaluation using longitudinal data.

The efficiency of park and ride (PnR) lots has not been investigated in serious depth in prior literature. This study examines the effect of various factors on the utilization rate of PnR lots with panel Tobit models. The examined factors consist of land use features, roadway design features, transit ridership, sociodemographic attributes, travel characteristics, policy tools, gasoline prices, and weather conditions. The data is drawn from PnR lots in King County, Washington. Results show that: (1) degree of mixed land use, road density, employment density, percentages of people aged between 18 and 34 and people over 65, the percentage of white people, the percentage of poor people, and transit ridership are positively associated with the utilization rate of PnR lots; (2) the percentage of drive lanes in total roadway miles, the percentage of males, and the mode share percentage of driving are negatively correlated with the utilization rate of PnR lots; (3) various policy interventions, including countermeasures for preserving transit after the economic recession, congestion reduction charge, and bus-rail integration, are all positively correlated with the utilization rate of PnR lots. Contextualized to US cities, PnR is a practical way to attract bus riders, especially young adults, senior citizens, and low-income people to public transit. Dense urban development is encouraged for the full utilization of PnR lots. Additionally, the integration between bus and rail appears to be an effective policy tool to promote PnR utilization.