Abstract: Traffic forecasting is vital for urban planning, with deep learning methods excelling in capturing traffic patterns. However, obtaining comprehensive historical data remains challenging, especially for city-wide predictions. To overcome this, we used SceneGCN, a deep learning approach, for city-scale traffic speed forecasting. This method involves extracting scene features from… read more
Quantitative Approach to Assess Social Equity in Road Networks
Abstract: This study addresses the need to quantitatively assess social equity in road network performance, a challenge often approached qualitatively in existing literature. By proposing a quantitative approach and exploring numerical measures, the study aims to provide objective assessments. The approach is applied to street networks in Seattle and New… read more
Testing the Capability of AI Art Tools for Urban Design
Abstract: This study examined three AI image synthesis models—Dall-E 2, Stable Diffusion, and Midjourney—for generating urban design imagery from scene descriptions. 240 images were evaluated using a modified Sensibleness and Specificity Average (SSA) metric by two independent evaluators. Results revealed significant differences among the AI models, with varying scores across… read more
Housing market price movements under tech industry expansion during COVID-19
Abstract: This study investigates the impact of technology-based corporation relocations on housing prices during COVID-19 in Austin, Texas, and Seattle/Bellevue, Washington, focusing on Tesla and Amazon. Using a difference-in-difference (DID) method, changes in housing prices near and away from the new corporate locations are analyzed within 5-mile and 10-mile radii.… read more
Identifying Hospital Deserts in Texas Before and During the COVID-19 Outbreak
Abstract: In our study, we utilized GIS to analyze hospital visitor data from January to June of 2019 and 2020, focusing on the impact of the initial COVID-19 wave. We found that while most demographic groups experienced shifts in visitor levels, American Indian and Pacific Islander groups sometimes showed no… read more
A scoping review of the benefits of face mask use on pedestrian and bicyclist exposure to air pollutants
Abstract: A growing body of research suggests that pedestrians and bicyclists are exposed to substantial levels of harmful air pollutants, including particulate matter and carbon monoxide, during their daily commutes. Disposable and cloth face masks are well-known personal interventions for pedestrian and bicyclist pollutant exposure. However, there is a lack… read more
The Impact of Peer-to-peer Ridesharing on Travel Mode: Empirical Study of Uber Effects on Travel Mode in Seattle
Abstract: Peer-to-peer ridesharing, as a new travel mode, could be a potential solution to two major transportation issues: congestion and air pollution by reducing inefficient driving and promoting public transit ridership. Uber, as one of the leader transport network company, launched in San Francisco in 2010 and expanded around the… read more
The Role of Transportation Networking Companies in Megaregion Mobility
Abstract Transportation Network Companies (TNCs) like Uber and Lyft have become popular forms of transportation in recent years. Researchers have worked to understand the qualitative impacts of these services, such as effects on the taxi industry, spatial and temporal distribution in cities, and effects on public transit; however, few studies… read more
Are There Transit Deserts in Europe? A Study Focusing on Four European Cases through Publicly Available Data
Abstract: Public transit has been proven as an affordable travel method, while the inequitable distribution is a rising concern among practitioners and researchers. A transit desert, based on the demand and supply concept in measuring the mismatch in allocating the level of public transit service, has proved its ability to… read more
Washington State School Walk Score
Abstract We used unique data from the 2016 Washington State Student Travel Survey combined with built environment data to first confirm the factors shown to influence children walking to and from school in previous literature. Walkability scores were then estimated for K-8 Washington state schools under different data availability scenarios.… read more