2023
Yue, Yifan; Chen, Jun; Feng, Tao; Ma, Xinwei; Wang, Wei; Bai, Hua
Classification and Determinants of High-Speed Rail Stations Using Multi-Source Data: A Case Study in Jiangsu Province, China Journal Article
In: Sustainable Cities and Society, pp. 104640, 2023, ISSN: 2210-6707.
Abstract | Links | BibTeX | Tags: Built environment, Geographically Weighted Multinomial Logit Model, High-Speed Rail Station, Influential factors, Mobile Phone Data
@article{YUE2023104640,
title = {Classification and Determinants of High-Speed Rail Stations Using Multi-Source Data: A Case Study in Jiangsu Province, China},
author = {Yifan Yue and Jun Chen and Tao Feng and Xinwei Ma and Wei Wang and Hua Bai},
url = {https://www.sciencedirect.com/science/article/pii/S2210670723002512},
doi = {https://doi.org/10.1016/j.scs.2023.104640},
issn = {2210-6707},
year = {2023},
date = {2023-01-01},
journal = {Sustainable Cities and Society},
pages = {104640},
abstract = {High-speed rail (HSR) stations play a vital role in the HSR system. HSR stations not only facilitate the accessibility of interregional transportation but also stimulate population movements across various cities in China. HSR stations in different cities can vary greatly, and an efficient HSR system requires an in-depth understanding of the interrelations between the related influential factors and spatiotemporal passenger flow patterns of different HSR stations. This study adopts a new scheme for clustering HSR stations based on passengers' arrival and departure time series using mobile phone data in Jiangsu, China. To this end, 71 HSR stations are clustered into 3 classes and the spatiotemporal characteristics of passenger flow at different stations are compared. Finally, a geographically weighted multinomial logit model (GWMNL) is built to explore the influence of the built environment, socioeconomic indicators, and HSR station attributes on the classification results of HSR stations related to the time-varying characteristics of passenger flow. The model results show that the number of entertainment POIs, population, population density, area, GDP and building area are significantly associated with the classification results of HSR stations. Additionally, for HSR stations under the same classification result, these variables also have different effects on them in the geographical dimension. According to these findings, quantitative analysis of the linkages between the passenger flow patterns at different HSR stations and the impacting factors would offer implications for planners and policymakers in HSR station planning and associated urban development.},
keywords = {Built environment, Geographically Weighted Multinomial Logit Model, High-Speed Rail Station, Influential factors, Mobile Phone Data},
pubstate = {published},
tppubtype = {article}
}
High-speed rail (HSR) stations play a vital role in the HSR system. HSR stations not only facilitate the accessibility of interregional transportation but also stimulate population movements across various cities in China. HSR stations in different cities can vary greatly, and an efficient HSR system requires an in-depth understanding of the interrelations between the related influential factors and spatiotemporal passenger flow patterns of different HSR stations. This study adopts a new scheme for clustering HSR stations based on passengers’ arrival and departure time series using mobile phone data in Jiangsu, China. To this end, 71 HSR stations are clustered into 3 classes and the spatiotemporal characteristics of passenger flow at different stations are compared. Finally, a geographically weighted multinomial logit model (GWMNL) is built to explore the influence of the built environment, socioeconomic indicators, and HSR station attributes on the classification results of HSR stations related to the time-varying characteristics of passenger flow. The model results show that the number of entertainment POIs, population, population density, area, GDP and building area are significantly associated with the classification results of HSR stations. Additionally, for HSR stations under the same classification result, these variables also have different effects on them in the geographical dimension. According to these findings, quantitative analysis of the linkages between the passenger flow patterns at different HSR stations and the impacting factors would offer implications for planners and policymakers in HSR station planning and associated urban development.
Wu, Jishi; Jia, Peng; Feng, Tao; Li, Haijiang; Kuang, Haibo
Spatiotemporal analysis of built environment restrained traffic carbon emissions and policy implications Journal Article
In: Transportation Research Part D: Transport and Environment, vol. 121, pp. 103839, 2023, ISSN: 1361-9209.
Abstract | Links | BibTeX | Tags: Built environment, GPBoost, Machine learning, Nonlinear effects, SHapley Additive ExPlanation, Traffic carbon emissions
@article{WU2023103839,
title = {Spatiotemporal analysis of built environment restrained traffic carbon emissions and policy implications},
author = {Jishi Wu and Peng Jia and Tao Feng and Haijiang Li and Haibo Kuang},
url = {https://www.sciencedirect.com/science/article/pii/S1361920923002365},
doi = {https://doi.org/10.1016/j.trd.2023.103839},
issn = {1361-9209},
year = {2023},
date = {2023-01-01},
journal = {Transportation Research Part D: Transport and Environment},
volume = {121},
pages = {103839},
abstract = {Urban environmental policies need to be rectified considering the spatioemporal variations of traffic emissions. However, knowledge to support such a decision-making process is insufficient. This study analyzes the spatiotemporal distributions of traffic emissions in the built environment and their potential nonlinear associations. Considering the recent innovations in machine learning, a tree-boosting algorithm combined with Gaussian process and random effects models (GPBoost) is applied using the big GPS taxi data from Dalian, China. The nonlinear relationships between built environment variables and traffic carbon (CO2) emissions are interpreted using the SHapley Additive ExPlanation (SHAP). It is found that the proposed GPBoost model that considers spatial heterogeneity enhances the overall predictive power compared to traditional machine learning models. Most of the built environment variables have a nonlinear relationship with traffic carbon emissions and the threshold effects vary over time, indicating the necessity of dynamic urban management.},
keywords = {Built environment, GPBoost, Machine learning, Nonlinear effects, SHapley Additive ExPlanation, Traffic carbon emissions},
pubstate = {published},
tppubtype = {article}
}
Urban environmental policies need to be rectified considering the spatioemporal variations of traffic emissions. However, knowledge to support such a decision-making process is insufficient. This study analyzes the spatiotemporal distributions of traffic emissions in the built environment and their potential nonlinear associations. Considering the recent innovations in machine learning, a tree-boosting algorithm combined with Gaussian process and random effects models (GPBoost) is applied using the big GPS taxi data from Dalian, China. The nonlinear relationships between built environment variables and traffic carbon (CO2) emissions are interpreted using the SHapley Additive ExPlanation (SHAP). It is found that the proposed GPBoost model that considers spatial heterogeneity enhances the overall predictive power compared to traditional machine learning models. Most of the built environment variables have a nonlinear relationship with traffic carbon emissions and the threshold effects vary over time, indicating the necessity of dynamic urban management.
2022
Li, Bo; Liu, Qiuhong; Wang, Tong; He, He; Peng, You; Feng, Tao
Analysis of Urban Built Environment Impacts on Outdoor Physical Activities—A Case Study in China Journal Article
In: Frontiers in Public Health, vol. 10, 2022, ISSN: 2296-2565.
Abstract | Links | BibTeX | Tags: Built environment, Health, Physical Activity
@article{10.3389/fpubh.2022.861456,
title = {Analysis of Urban Built Environment Impacts on Outdoor Physical Activities—A Case Study in China},
author = {Bo Li and Qiuhong Liu and Tong Wang and He He and You Peng and Tao Feng},
url = {https://www.frontiersin.org/article/10.3389/fpubh.2022.861456},
doi = {10.3389/fpubh.2022.861456},
issn = {2296-2565},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {Frontiers in Public Health},
volume = {10},
abstract = {Outdoor physical activities can promote public health and they are largely influenced by the built environment in different urban settings. Understanding the association between outdoor physical activities and the built environment is important for promoting a high quality of life. Existing studies typically focus on one type of outdoor activity using interview-based small samples and are often lack of systematic understanding of the activities' intensity and frequency. In this study, we intend to gain deeper insight into how the built environment influences physical activities using the data extracted from individual's wearables and other open data sources for integrated analysis. Multi-linear regression with logarithm transformation is applied to perform the analysis using the data from Changsha, China. We found that built environment impacts on outdoor physical activities in Changsha are not always consistent with similar studies' results in other cities. The most effective measures to promote outdoor physical activities are the provision of good arterial and secondary road networks, community parks, among others in Changsha. The results shed light on future urban planning practices in terms of promoting public health."},
keywords = {Built environment, Health, Physical Activity},
pubstate = {published},
tppubtype = {article}
}
Outdoor physical activities can promote public health and they are largely influenced by the built environment in different urban settings. Understanding the association between outdoor physical activities and the built environment is important for promoting a high quality of life. Existing studies typically focus on one type of outdoor activity using interview-based small samples and are often lack of systematic understanding of the activities’ intensity and frequency. In this study, we intend to gain deeper insight into how the built environment influences physical activities using the data extracted from individual’s wearables and other open data sources for integrated analysis. Multi-linear regression with logarithm transformation is applied to perform the analysis using the data from Changsha, China. We found that built environment impacts on outdoor physical activities in Changsha are not always consistent with similar studies’ results in other cities. The most effective measures to promote outdoor physical activities are the provision of good arterial and secondary road networks, community parks, among others in Changsha. The results shed light on future urban planning practices in terms of promoting public health."
2021
Li, B.; Peng, Y.; He, H.; Wang, M.; Feng, T.
Built environment and early infection of COVID-19 in urban districts: A case study of Huangzhou Journal Article
In: Sustainable Cities and Society, vol. 66, 2021, ISSN: 22106707.
Abstract | Links | BibTeX | Tags: Built environment, Commercial prosperity, COVID-19, DBSCAN, GIS, Medical service, SEM, Transportation infrastructure
@article{Li2021,
title = {Built environment and early infection of COVID-19 in urban districts: A case study of Huangzhou},
author = {B. Li and Y. Peng and H. He and M. Wang and T. Feng},
doi = {10.1016/j.scs.2020.102685},
issn = {22106707},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Sustainable Cities and Society},
volume = {66},
abstract = {Since COVID-19 spread rapidly worldwide, many countries have experienced significant growth in the number of confirmed cases and deaths. Earlier studies have examined various factors that may contribute to the contagion rate of COVID-19, such as air pollution, smoking, humidity, and temperature. As there is a lack of studies at the neighborhood-level detailing the spatial settings of built environment attributes, this study explored the variations in the size of the COVID-19 confirmed case clusters across the urban district Huangzhou in the city of Huanggang. Clusters of infectious cases in the initial outbreak of COVID-19 were identified geographically through GIS methods. The hypothetic relationships between built environment attributes and clusters of COVID-19 cases have been investigated with the structural equation model. The results show the statistically significant direct and indirect influences of commercial vitality and transportation infrastructure on the number of confirmed cases in an infectious cluster. The clues ch inducing a high risk of contagions have been evidenced and provided for the decision-making practice responding to the initial stage of possible severe epidemics, indicating that the local public health authorities should implement sufficient measures and adopt effective interventions in the areas and places with a high probability of crowded residents.},
keywords = {Built environment, Commercial prosperity, COVID-19, DBSCAN, GIS, Medical service, SEM, Transportation infrastructure},
pubstate = {published},
tppubtype = {article}
}
Since COVID-19 spread rapidly worldwide, many countries have experienced significant growth in the number of confirmed cases and deaths. Earlier studies have examined various factors that may contribute to the contagion rate of COVID-19, such as air pollution, smoking, humidity, and temperature. As there is a lack of studies at the neighborhood-level detailing the spatial settings of built environment attributes, this study explored the variations in the size of the COVID-19 confirmed case clusters across the urban district Huangzhou in the city of Huanggang. Clusters of infectious cases in the initial outbreak of COVID-19 were identified geographically through GIS methods. The hypothetic relationships between built environment attributes and clusters of COVID-19 cases have been investigated with the structural equation model. The results show the statistically significant direct and indirect influences of commercial vitality and transportation infrastructure on the number of confirmed cases in an infectious cluster. The clues ch inducing a high risk of contagions have been evidenced and provided for the decision-making practice responding to the initial stage of possible severe epidemics, indicating that the local public health authorities should implement sufficient measures and adopt effective interventions in the areas and places with a high probability of crowded residents.
Chen, C.; Feng, T.; Shao, M.; Yao, B.
Understanding the determinants of spatial-temporal mobility patterns based on multi-source heterogeneous data Proceedings Article
In: 2021, ISSN: 23521465.
Abstract | Links | BibTeX | Tags: Built environment, Multi-source heterogeneous data, OLRs, POIs, Urban mobility
@inproceedings{Chen2021,
title = {Understanding the determinants of spatial-temporal mobility patterns based on multi-source heterogeneous data},
author = {C. Chen and T. Feng and M. Shao and B. Yao},
doi = {10.1016/j.trpro.2021.01.056},
issn = {23521465},
year = {2021},
date = {2021-01-01},
journal = {Transportation Research Procedia},
volume = {52},
abstract = {With the advance of intelligent transportation systems (ITSs) and data acquisition systems (DAS), it is possible to explore the determinants of urban spatial-temporal mobility patterns using multi-source heterogeneous data. This study aims to use the points-of-interests (POIs) data, house-price data, and floating car data to identify the factors influencing urban mobility in Shanghai. Within a scale of 0.5 km grid, trip production and attraction were stratified according to the traveling intensity, and the critical information related to economy, intermodal connection, land use, and time were also obtained through the multi-source data. The experiment results from an ordinal logistic regression (OLR) analysis show that average house price has a dominating and positive effect on the traveling intensity for both trip production and attraction, followed by land-use factors. However, the effect of scenic spots is found significant only on trip attraction. In addition, shopping is found to insignificantly affect the traveling intensity for both trip production and attraction. Unexpectedly, time factors also have diverse impacts. These findings are expected to help better understand the relationship between urban mobility and built environment factors, providing passengers with better services, and offering useful insights into future urban and transportation planning.},
keywords = {Built environment, Multi-source heterogeneous data, OLRs, POIs, Urban mobility},
pubstate = {published},
tppubtype = {inproceedings}
}
With the advance of intelligent transportation systems (ITSs) and data acquisition systems (DAS), it is possible to explore the determinants of urban spatial-temporal mobility patterns using multi-source heterogeneous data. This study aims to use the points-of-interests (POIs) data, house-price data, and floating car data to identify the factors influencing urban mobility in Shanghai. Within a scale of 0.5 km grid, trip production and attraction were stratified according to the traveling intensity, and the critical information related to economy, intermodal connection, land use, and time were also obtained through the multi-source data. The experiment results from an ordinal logistic regression (OLR) analysis show that average house price has a dominating and positive effect on the traveling intensity for both trip production and attraction, followed by land-use factors. However, the effect of scenic spots is found significant only on trip attraction. In addition, shopping is found to insignificantly affect the traveling intensity for both trip production and attraction. Unexpectedly, time factors also have diverse impacts. These findings are expected to help better understand the relationship between urban mobility and built environment factors, providing passengers with better services, and offering useful insights into future urban and transportation planning.
2020
Gan, Z.; Yang, M.; Feng, T.; Timmermans, H. J. P.
Examining the relationship between built environment and metro ridership at station-to-station level Journal Article
In: Transportation Research Part D: Transport and Environment, vol. 82, 2020, ISSN: 13619209.
Abstract | Links | BibTeX | Tags: Built environment, Gradient boosting regression trees, Metro, Non-linear effect, Station-to-station ridership
@article{Gan2020,
title = {Examining the relationship between built environment and metro ridership at station-to-station level},
author = {Z. Gan and M. Yang and T. Feng and H. J. P. Timmermans},
doi = {10.1016/j.trd.2020.102332},
issn = {13619209},
year = {2020},
date = {2020-01-01},
journal = {Transportation Research Part D: Transport and Environment},
volume = {82},
abstract = {Very few studies have examined the impact of built environment on urban rail transit ridership at the station-to-station (origin-destination) level. Moreover, most direct ridership models (DRMs) tend to involve simple a prior assumed linear or log-linear relationship in which the estimated parameters are assumed to hold across the entire data space of the explanatory variables. These models cannot detect any changes in the linear (or non-linear) effects across different values of the features of built environment on urban rail transit ridership, which possibly induces biased results and hides some non-negligible and detailed information. Based on these research gaps, this study develops a time-of-day origin-destination DRM that uses smart card data pertaining to the Nanjing metro system, China. It applies a gradient boosting regression trees model to provide a more refined data mining approach to investigate the non-linear associations between features of the built environment and station-to-station ridership. Data related to the built environment, station type, demographics, and travel impedance including a less used variable – detour, were collected and used in the analysis. The empirical results show that most independent variables are associated with station-to-station ridership in a discontinuous non-linear way, regardless of the time period. The built environment on the origin side has a larger effect on station-to-station ridership than the built environment on the destination side for the morning peak hours, while the opposite holds for the afternoon peak hours and night. The results also indicate that transfer times is more important variables than detour and route distance.},
keywords = {Built environment, Gradient boosting regression trees, Metro, Non-linear effect, Station-to-station ridership},
pubstate = {published},
tppubtype = {article}
}
Very few studies have examined the impact of built environment on urban rail transit ridership at the station-to-station (origin-destination) level. Moreover, most direct ridership models (DRMs) tend to involve simple a prior assumed linear or log-linear relationship in which the estimated parameters are assumed to hold across the entire data space of the explanatory variables. These models cannot detect any changes in the linear (or non-linear) effects across different values of the features of built environment on urban rail transit ridership, which possibly induces biased results and hides some non-negligible and detailed information. Based on these research gaps, this study develops a time-of-day origin-destination DRM that uses smart card data pertaining to the Nanjing metro system, China. It applies a gradient boosting regression trees model to provide a more refined data mining approach to investigate the non-linear associations between features of the built environment and station-to-station ridership. Data related to the built environment, station type, demographics, and travel impedance including a less used variable – detour, were collected and used in the analysis. The empirical results show that most independent variables are associated with station-to-station ridership in a discontinuous non-linear way, regardless of the time period. The built environment on the origin side has a larger effect on station-to-station ridership than the built environment on the destination side for the morning peak hours, while the opposite holds for the afternoon peak hours and night. The results also indicate that transfer times is more important variables than detour and route distance.
2019
Gan, Z.; Feng, T.; Yang, M.; Timmermans, H.; Luo, J.
Analysis of Metro Station Ridership Considering Spatial Heterogeneity Journal Article
In: Chinese Geographical Science, vol. 29, iss. 6, 2019, ISSN: 1993064X.
Abstract | Links | BibTeX | Tags: Built environment, rapid transit ridership, spatial heterogeneity, spatial models, station level
@article{Gan2019,
title = {Analysis of Metro Station Ridership Considering Spatial Heterogeneity},
author = {Z. Gan and T. Feng and M. Yang and H. Timmermans and J. Luo},
doi = {10.1007/s11769-019-1065-8},
issn = {1993064X},
year = {2019},
date = {2019-01-01},
journal = {Chinese Geographical Science},
volume = {29},
issue = {6},
abstract = {This study aims to explore the role of spatial heterogeneity in ridership analysis and examine the relationship between built environment, station attributes and urban rapid transit ridership at the station level. Although spatial heterogeneity has been widely acknowledged in spatial data analysis, it has been rarely considered in travel behavior studies. Four models (three global models-ordinary least squares (OLS), spatial lag model (SLM), spatial error model (SEM) and one local model-geographically weighted regression (GWR) model) are estimated separately to explore the relationship between various independent variables and station ridership, and identify the influence of spatial heterogeneity. Using the data of built environment and station characteristics, the results of diagnostic identify evidence the existence of spatial heterogeneity in station ridership for the metro network in Nanjing, China. Results of comparing the various goodness-of-fit indicators show that, the GWR model yields the best fit of the data, performance followed by the SEM, SLM and OLS model. The results also demonstrate that population, number of lines, number of feeder buses, number of exits, road density and proportion residential area have a significant impact on station ridership. Moreover, the study pays special attention to the spatial variation in the coefficients of the independent variables and their statistical significance. It underlines the importance of taking spatial heterogeneity into account in the station ridership analysis and the decision-making in urban planning.},
keywords = {Built environment, rapid transit ridership, spatial heterogeneity, spatial models, station level},
pubstate = {published},
tppubtype = {article}
}
This study aims to explore the role of spatial heterogeneity in ridership analysis and examine the relationship between built environment, station attributes and urban rapid transit ridership at the station level. Although spatial heterogeneity has been widely acknowledged in spatial data analysis, it has been rarely considered in travel behavior studies. Four models (three global models-ordinary least squares (OLS), spatial lag model (SLM), spatial error model (SEM) and one local model-geographically weighted regression (GWR) model) are estimated separately to explore the relationship between various independent variables and station ridership, and identify the influence of spatial heterogeneity. Using the data of built environment and station characteristics, the results of diagnostic identify evidence the existence of spatial heterogeneity in station ridership for the metro network in Nanjing, China. Results of comparing the various goodness-of-fit indicators show that, the GWR model yields the best fit of the data, performance followed by the SEM, SLM and OLS model. The results also demonstrate that population, number of lines, number of feeder buses, number of exits, road density and proportion residential area have a significant impact on station ridership. Moreover, the study pays special attention to the spatial variation in the coefficients of the independent variables and their statistical significance. It underlines the importance of taking spatial heterogeneity into account in the station ridership analysis and the decision-making in urban planning.