Search

The accurate prediction of travel demand by bus is crucial for effective urban mobility demand management. However, most models of travel demand prediction by bus tend to focus on the bus's spatiotemporal dependencies, while ignoring the interactions between buses and other transportation modes, such as metros and taxis. We propose a Multiview Spatiotemporal Graph Neural Network (MSTGNN) model to predict short-term travel demand by bus. It emphasizes the ability to capture the interaction dependencies among the travel demand of buses, metros, and taxis. Firstly, a multiview graph consisting of bus, metro, and taxi views is constructed, with each view containing both a local and global graph. Secondly, a multiview attention-based temporal graph convolution module is developed to capture spatiotemporal and cross-view interaction dependencies among different transport modes. Especially, to address the uneven spatial distributions of features in multiview learning, the cross-view spatial feature consistency loss is introduced as an auxiliary loss. Finally, we conduct intensive experiments using a real-world dataset from Shenzhen, China. The results demonstrate that our proposed MSTGNN model performs better than the existing models. Ablation experiments validate the contributions of various modes of transportation to the improvement of the model's performance. [ABSTRACT FROM AUTHOR]

Inhalable particulate pollution has adverse effects on human health. Many studies have been conducted to investigate levels and risks of exposure to particulate pollution in public transit, but scant attention has been paid to variations in the pollution levels among different positions inside the cabin. Differences can be observed among different positions inside transit vehicles, like passenger density and activities, which may lead to differentiated exposure risks between different positions. Therefore, this study investigates the level of PM2.5 concentrations and the spatiotemporal variations among three different positions (front, middle, and rear) inside the cabin during bus travel. The three positions represent the three areas inside the bus cabin, i.e., front area (FA), middle area (MA), and rear area (RA). We developed a portable monitoring system for in-cabin measurements, which consists of a mobile device with the designated app, a PM2.5 collecting device, and a temperature-relative humidity monitor. Surveys were carried out on buses of a route in Shenzhen, China, which include inbound and outbound trips during both morning and evening peaks of two working days. Based on spatial and temporal information embedded in data collection devices, PM2.5 concentration data were spatially and temporally referenced. Comparative and descriptive statistical analyses were employed to examine the differences and variations in PM2.5 concentration among the areas inside the bus cabin. There are three major findings. First, for all of the surveyed trips, FA showed the highest and RA showed the lowest PM2.5 concentration. Second, concerning the average pollution level of route segments along the routes, the PM2.5 concentrations in the three cabin areas were higher during inbound trips than during outbound trips. Third, within route segments, PM2.5 concentrations in FA and MA increased rapidly after the bus stopped at stops, and then gradually decreased, while in RA they were relatively stable. In general, a higher level of passenger density increased in-cabin PM2.5 concentration. The findings of our study could provide insight into improving the bus in-cabin microenvironment, such as the seating arrangement for vulnerable passengers. [ABSTRACT FROM AUTHOR]

Due to continuous urban sprawl, large-scale bus network design has become a major challenge in urban transport planning. The continuous increase in urban population and scale makes the factors considered in the urban route network design increasingly complex. Contemporary public transportation network design problems are based more on efficiency goals such as the accessibility and comfort of the transportation network, which increases the difficulty of analyzing the problem. Bus network design is not only an NP-hard (nondeterministic polynomial) problem but also a multivariable and multiobjective problem. This paper focuses on the bivariate and multiobjective bus network design problem of route generation and station selection. This paper proposes an algorithm called the Pseudo Force Field. By combining the idea of Particle Swarm Optimization (PSO) and the properties of the force field, a feasible route generation scheme is provided for the design of the bus network. The algorithm does not need to determine the end station and has a high degree of completion of the demand. This solves the problem of the selection of terminal stations in large-scale road network design. On this basis, the article combines Genetic Algorithm (GA) and Pareto frontier to provide a new route optimization algorithm and proves the effectiveness of the algorithm. The model has achieved theoretical results in the design of the bus route network in the megacity of Shenzhen, China. [ABSTRACT FROM AUTHOR]

Accurate and robust short-term bus travel prediction facilitates operating the bus fleet to provide comfortable and flexible bus services. The built environment, including land use, buildings, and public facilities, has an important influence on bus travel demand prediction. However, previous studies regarded the built environment as a static feature thus even ignored its influence on bus travel in deep learning framework. To fill this gap, we propose a graph deep learning-based approach coupling with spatiotemporal influence of built environment (GDLBE) to enhance short-term bus travel demand prediction. A time-dependent geographically weighted regression method is used to resolve the dynamic influence of the built environment on bus travel demand at different times of the day. A graph deep learning module is used to capture the comprehensive spatial and temporal dependency behind massive bus travel demand. The short-term bus travel demand is predicted by fusing the dynamic built environment influences and spatiotemporal dependency. An experiment in Shenzhen is conducted to evaluate the performance of the proposed approach. Baseline methods are compared, and the results demonstrate that the proposed approach outperforms the baselines. These results will help bus fleet dispatch for smart transportation. • Coupling graph deep learning and dynamic built environment influences to forecast short-term bus travel demand. • Multitime GWR is used to reveal that dynamic influence of built environment on bus travel demand. • Deep graph neural network is designed to capture spatial and temporal dependency. • Experiment in Shenzhen demonstrates that the GDLBE approach outperform baseline methods. [ABSTRACT FROM AUTHOR]

Exposure to ambient fine particulate matter (PM) in transit microenvironments (TMEs), which mainly comes from traffic emissions, is associated with various adverse health effects. Many studies have investigated the exposure levels and health risk to commuters in TMEs; however, the application of spatial techniques has been limited to a handful of in-transit studies, and information on spatiotemporal variations of in-transit particle concentrations remains sparse. This study aims to examine spatiotemporal variations of in-cabin particle concentrations in transit and the correlations between en-route environmental factors and the variations of particle concentrations in transit. To this end, we propose a portable monitoring system for measuring the particle concentrations and corresponding travel conditions on public transit trips. The measurements were performed during peak hours of both bus and metro services in Shenzhen China. Our results highlight that temporal variations of particle concentrations exist between different trips during the same peak hours. The particle concentrations are higher on the start/end segments of the routes than on any other segment. The variations in particle concentrations on different route segments are significantly correlated with travel conditions (p < 0.01 and p < 0.05) and urban ambient conditions (p < 0.01). Moreover, opposite effects of ventilation, wind speed, and the posture of the investigators on the variations of particle concentrations on different segments are identified between bus and metro. In addition, passengers are exposed to higher particle concentrations on longer trips. Utilizing our methodology and results, policy makers and other researchers may further explore the exposure to particle pollution on public transit. • This study proposes a portable monitoring system to monitor in-transit microenvironment. • Spatiotemporal variations in particle concentrations in transit are highlighted. • The particle concentrations are higher on the start/end points of the routes than on any other segment. • Passengers are exposed to higher particle concentrations on longer trips. [ABSTRACT FROM AUTHOR]

In recent years, promoting regional synergistic development has become the shared objective in city-regions during the new stages of development. This paper aims to uncover the dynamics of synergistic development in urban agglomerations by constructing an index measurement system based on four dimensions: industrial synergy, innovation synergy, infrastructure synergy, and institutional synergy. By comprehensively employing theories and methods such as "space of flow" big data analysis, network analysis, and interlocking network models, this study examines patterns and capacities of synergistic development in the Guangdong-Hong Kong-Macao Greater Bay Area. The main instances of industrial cooperation between cities are observed in Hong Kong-Shenzhen and Guangzhou-Shenzhen; capital flows primarily concentrate in Guangzhou-Shenzhen and Hong Kong-Shenzhen. Research paper and patent collaborations between cities are predominantly concentrated in Hong Kong-Shenzhen; joint laboratories are mainly established in Hong Kong-Macao and Hong Kong-Guangzhou; inter-city co-construction of higher education institutions is mainly focused on Guangzhou-Foshan and Shenzhen-Hong Kong. Infrastructure synergistic development performs best in Guangzhou-Shenzhen, Guangzhou-Foshan, and Shenzhen-Dongguan. Cross-border collaboration benefits from institutional advantages held by Hong Kong and Macao. Urban interactions with outstanding performance include Guangzhou-Shenzhen, Hong Kong-Shenzhen, Guangzhou-Foshan, Shenzhen-Dongguan. Additionally, increasing interaction trends can be observed between Guangzhou-Dongguan as well as Shenzhen-Zhuhai/Shenzen-Foshan partnerships. Understanding the typical characteristics and potential trends of synergetic development within the GBA holds significant practical value for establishing a first-class bay area along with a world-class urban agglomeration. • Concept and connotation of synergistic development in urban agglomeration area was examined. • Indicators and methods for evaluation of synergistic development in the GBA were conducted. • Patterns and capacities of synergistic development at urban scale in the GBA were explained. • Urban interaction with highest synergistic development level is Guangzhou-Shenzhen. [ABSTRACT FROM AUTHOR]

• Large-scale and high-resolution approach sensing urban soundscapes without ground measurements with machine learning. • A dataset of street view imagery tagged with multivariate soundscape indicators. • Quantifying the relationships between visual features and human soundscape perception. • Validation with sound intensity and corresponding street view imagery using noise meters and cameras. • Comparative analysis including two cities and a scalable approach. A healthy acoustic environment is an essential component of sustainable cities. Various noise monitoring and simulation techniques have been developed to measure and evaluate urban sounds. However, sensing large areas at a fine resolution remains a great challenge. Based on machine learning, we introduce a new application of street view imagery — estimating large-area high-resolution urban soundscapes, investigating the premise that we can predict and characterize soundscapes without laborious and expensive noise measurements. First, visual features are extracted from street-level imagery using computer vision. Second, fifteen soundscape indicators are identified and a survey is conducted to gauge them solely from images. Finally, a prediction model is constructed to infer the urban soundscape by modeling the non-linear relationship between them. The results are verified with extensive field surveys. Experiments conducted in Singapore and Shenzhen using half a million images affirm that street view imagery enables us to sense large-scale urban soundscapes with low cost but high accuracy and detail, and provides an alternative means to generate soundscape maps. R 2 reaches 0.48 by evaluating the predicted results with field data collection. Further novelties in this domain are revealing the contributing visual elements and spatial laws of soundscapes, underscoring the usability of crowdsourced data, and exposing international patterns in perception. [ABSTRACT FROM AUTHOR]