Infrastructure & Transportation Archives - Page 18 of 20

Cluster-based LSTM Network for Short-term Passenger Flow Forecasting in Urban Rail Transit

Zhang, Jinlei; Chen, Feng; Shen, Qing. (2019). Cluster-based LSTM Network for Short-term Passenger Flow Forecasting in Urban Rail Transit. Ieee Access, 7, 147653 – 147671.

View Publication

Abstract

Short-term passenger flow forecasting is an essential component for the operation of urban rail transit (URT). Therefore, it is necessary to obtain a higher prediction precision with the development of URT. As artificial intelligence becomes increasingly prevalent, many prediction methods including the long short-term memory network (LSTM) in the deep learning field have been applied in road transportation systems, which can give critical insights for URT. First, we propose a novel two-step K-Means clustering model to capture not only the passenger flow variation trends but also the ridership volume characteristics. Then, a predictability assessment model is developed to recommend a reasonable time granularity interval to aggregate passenger flows. Based on the clustering results and the recommended time granularity interval, the LSTM model, which is called CB-LSTM model, is proposed to conduct short-term passenger flow forecasting. Results show that the prediction based on subway station clusters can not only avoid the complication of developing numerous models for each of the hundreds of stations, but also improve the prediction performance, which make it possible to predict short-term passenger flow on a network scale using limited dataset. The results provide critical insights for subway operators and transportation policymakers.

Keywords

Traffic Flow; Neural-network; Prediction; Ridership; Models; Volume; Lstm; Short-term Passenger Flow Forecasting; Urban Rail Transit; K-means Clustering; Deep Learning

Does the Built Environment Have Independent Obesogenic Power? Urban Form and Trajectories of Weight Gain

Buszkiewicz, James H.; Bobb, Jennifer F.; Hurvitz, Philip M.; Arterburn, David; Moudon, Anne Vernez; Cook, Andrea; Mooney, Stephen J.; Cruz, Maricela; Gupta, Shilpi; Lozano, Paula; Rosenberg, Dori E.; Theis, Mary Kay; Anau, Jane; Drewnowski, Adam. (2021). Does the Built Environment Have Independent Obesogenic Power? Urban Form and Trajectories of Weight Gain. International Journal Of Obesity, 45(9), 1914 – 1924.

View Publication

Abstract

Objective To determine whether selected features of the built environment can predict weight gain in a large longitudinal cohort of adults. Methods Weight trajectories over a 5-year period were obtained from electronic health records for 115,260 insured patients aged 18-64 years in the Kaiser Permanente Washington health care system. Home addresses were geocoded using ArcGIS. Built environment variables were population, residential unit, and road intersection densities captured using Euclidean-based SmartMaps at 800-m buffers. Counts of area supermarkets and fast food restaurants were obtained using network-based SmartMaps at 1600, and 5000-m buffers. Property values were a measure of socioeconomic status. Linear mixed effects models tested whether built environment variables at baseline were associated with long-term weight gain, adjusting for sex, age, race/ethnicity, Medicaid insurance, body weight, and residential property values. Results Built environment variables at baseline were associated with differences in baseline obesity prevalence and body mass index but had limited impact on weight trajectories. Mean weight gain for the full cohort was 0.06 kg at 1 year (95% CI: 0.03, 0.10); 0.64 kg at 3 years (95% CI: 0.59, 0.68), and 0.95 kg at 5 years (95% CI: 0.90, 1.00). In adjusted regression models, the top tertile of density metrics and frequency counts were associated with lower weight gain at 5-years follow-up compared to the bottom tertiles, though the mean differences in weight change for each follow-up year (1, 3, and 5) did not exceed 0.5 kg. Conclusions Built environment variables that were associated with higher obesity prevalence at baseline had limited independent obesogenic power with respect to weight gain over time. Residential unit density had the strongest negative association with weight gain. Future work on the influence of built environment variables on health should also examine social context, including residential segregation and residential mobility.

Keywords

Body-mass Index; Physical-activity; Food Environment; Structural Racism; Obesity; Neighborhoods; Associations; Health; Walkability; Exposure; Environment Models; Minority & Ethnic Groups; Urban Environments; Regression Analysis; Regression Models; Residential Density; Body Mass Index; Property Values; Body Weight Gain; Government Programs; Body Weight; Electronic Medical Records; Electronic Health Records; Fast Food; Buffers; Real Estate; Body Mass; Body Size; Socioeconomics; Health Care

Does Polycentric Development Produce Less Transportation Carbon Emissions? Evidence from Urban Form Identified by Night-Time Lights Across US Metropolitan Areas

Jung, Meen Chel; Kang, Mingyu; Kim, Sunghwan. (2022). Does Polycentric Development Produce Less Transportation Carbon Emissions? Evidence from Urban Form Identified by Night-Time Lights Across US Metropolitan Areas. Urban Climate, 44.

View Publication

Abstract

Identifying the comprehensive metropolitan urban form is important to propose effective policies to mitigate transportation carbon emissions. A publicly accessible night-time light dataset was used to identify urban centers and develop two polycentric indices to compute the composition and configuration of urban form, respectively. We used the most populous 103 U.S. metropolitan statistical areas (MSAs), with their corresponding transportation carbon emissions, polycentric indices, population sizes, gross domestic product (GDP) per capita, and road network densities. We first explored the typology of urban form and classified MSAs into six types based on two polycentric indices. We then introduced correlation analysis and statistical models to test the relationships between polycentric urban form and transportation carbon emissions. We found: (1) more urban centers lead to more emissions (compositional dimension), (2) more spatially distributed urban centers result in less emissions (configurational dimension), and (3) population and GDP per capita are positively related to carbon emissions. These findings suggest the importance of measuring two polycentric dimensions separately but using them together. Urban planners should consider mixed strategies that combine the traditional intra-center-based smart growth principles and the metropolitan-level inter-centers spatial plan to effectively counteract climate change.

Keywords

Polycentric Urban Form; Urban Centers; Carbon Emissions; Night-time Lights; Smart Growth; Climate Change; Co2 Emissions; Spatial Structure; Satellite Imagery; Cities; Patterns; Trends; Growth; Determinants; China

Jan Whittington and Qing Shen funded for project examining lessons learned from high-speed rail innovation

This year, the Washington State Legislature allocated $4 million to continue work on a Cascadia Corridor high-speed rail and another $150 million to use as matching funds over the next six years to leverage federal funds available under the Infrastructure Investment and Jobs Act (IIJA). Now that there is a significant funding commitment, how can an effort in Cascadia take the lessons learned and build on the success of others? That’s what a new Mobility Innovation Center project will examine, led…

The need for more equitable fare enforcement: An examination by Isis Moon Gamble, recent graduate of CBE’s Master of Urban Planning program

Though Transit Equity Day is just one day, the issue of equity on Seattle’s public transit is an ongoing and important conversation to Seattle and King County residents. Neighborhoods across the county have unequal access to transit lines; bus stops are often located in inconvenient or dangerous places due to oncoming traffic and lack of sidewalks; and bus schedules are irregular or sparse, with long wait times. These are just a few of the challenges folks might experience before getting…

Jerry Watson

My current Ph.D. research is investigating the history of transportation in the U.S. national parks. My research will explore from a historical and ecological perspective how to protect and preserve the park’s natural resources, while accommodating the public’s ability to visit the parks without causing irreparable harm. I believe a new strategy is required to address the critical transportation issues in these parks. I would like to formulate, develop, and evaluate a strategic model that explores alternatives to traditional modes of transport within national parks. There are three basic components of my research: conflict resolution, environmental ethics, and the ecological effects of roads (road ecology).

The main impetus for my decision to apply to the PhD program in the Built Environment, at the University of Washington is the opportunity to work in a program that offers me a unique opportunity to investigate the complicated problem of human-environment relationships. This will allow me to realize my belief that environments can be manipulated and planned to enhance the quality of people’s lives. I believe that significant impacts on the development of sustainable responses to environmental challenges can best be achieved through education and research.

UDP scholars among UW team receiving $2M from National Science Foundation to design an ‘adaptable society’

A team led by the University of Washington has received a nearly $2 million grant from the National Science Foundation to further research into how urban societal systems can be organized to be both efficient and resilient. The Leading Engineering for America’s Prosperity, Health and Infrastructure (LEAP-HI) project, based in the UW College of Engineering, supports fundamental research to generate the knowledge, mechanisms and tools needed to design an adaptable society. That is one, researchers say, that can switch between different operating strategies depending…

Qing Shen’s proposal among those selected for funding by PacTrans

The Pacific Northwest Transportation Consortium (PacTrans) announced in January 2021 the project proposals selected for funding. Qing Shen, Professor of Urban Design and Planning and Chair of the Interdisciplinary PhD Program in Urban Design and Planning is among those selected for project funding. Shen is working alongside Co-Principal Investigator Catherine (Casey) Gifford–Innovative Mobility Senior Planner–on the applied research project titled “Supplementing fixed-route transit with dynamic shared mobility services: a marginal cost comparison approach”. The project goal is to address a…

Sensol Systems to participate in the National Science Foundation (NSF) I-Corps program

Sensol Systems, a startup founded in 2020 by Janie Bube–a recent UW Masters of Landscape Architecture graduate–along with other students at University of Washington, was recently awarded a National Science Foundation (NSF) award to participate in the I-Corps program. This NSF program uses experiential education to help researchers gain valuable insight into entrepreneurship, starting a business or industry requirements and challenges. The curriculum integrates scientific inquiry and industrial discovery in an inclusive, data-driven culture driven by rigor, relevance, and evidence….

SHARE Lab produces ergonomics best practice booklet and training videos

The SHARE Lab (Safety and Health Advancement through Research and Education) has produced two ergonomics best practice booklets and two training videos on the use of 4-wheel carts in the roofing trade. Housed in the Department of Construction Management, the mission of the SHARE Lab is to promote construction safety and health through evidence-based innovative research, education, and practices. For more information, please contact Contact Dr. Ken-Yu Lin, Associate Professor, if you’d like access to the guide book or the…