Travel Behaviour and Society最新文献

{"title":"Predicting short-term urban bike sharing demand in a coupled continuous and network space","authors":"Shen Liang, Yang Xu, Guangyue Li, Xiaohu Zhang, Qiuping Li","doi":"10.1016/j.tbs.2025.101152","DOIUrl":"https://doi.org/10.1016/j.tbs.2025.101152","url":null,"abstract":"Bike sharing systems support sustainable urban development, with accurate demand prediction being essential for efficient operations. Previous studies have primarily modeled spatial dependency of bike sharing demand in Euclidean space or among bike stations, but often overlooked topological dependency of demand shaped by urban transportation networks. Metro and cycling networks could influence bike sharing usage through their functional connections with bike sharing systems. To address this gap, this study proposes GeoTopo-Net, a novel deep learning framework to improve short-term demand forecast for urban bike sharing systems. Different from existing solutions, GeoTopo-Net jointly models dependencies of travel demand in both continuous and network spaces. The model utilizes convolutional neural networks (CNNs) to capture spatial dependency between urban areas and their surroundings, while integrating graph convolutional networks (GCNs) to model the topological dependency introduced by urban transportation networks. Our evaluation across five global cities shows that GeoTopo-Net significantly reduces prediction errors, by up to 8.9% in RMSE, 6.8% in MAE, and 5.9% in MAPE. Incorporating dependencies from metro networks produces notable improvements in high-demand areas and those near the metro stations. These findings highlight the importance of incorporating urban transportation network structures in bike sharing demand forecast. The GeoTopo-Net architecture can also be adapted to improve short-term forecast for different types of travel demand (e.g., ride-hailing; electric vehicle charging demand) that involve complex interdependencies in continuous and network spaces.","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"80 1","pages":""},"PeriodicalIF":5.2,"publicationDate":"2025-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the role of ride-hailing in multimodal travel to maximize travel utility in urban areas","authors":"Yu Bai,&nbsp;Yuanqing Wang,&nbsp;Sen Wei,&nbsp;Yajuan Deng","doi":"10.1016/j.tbs.2025.101150","DOIUrl":"10.1016/j.tbs.2025.101150","url":null,"abstract":"<div><div>Nowadays, with the widespread adoption of ride-hailing services, urban residents’ travel mode choice behavior has changed significantly. However, few studies have systematically compared ride-hailing with integrated, door-to-door multimodal public transportation—combining subway, bus, and walking—to better understand travelers’ preferences. In this study, we generated matched travel scenarios using real ride-hailing and public transportation trip records, ensuring consistency in departure times and real-time road traffic conditions. This combined dataset incorporated individual traveler characteristics and built environment factors as both internal and external influences on mode choice. Based on this comprehensive data, we developed an analytical framework and applied a logit model to analyze travel mode selection. Key model variables were identified using SHAP feature importance. Subsequently, we conducted comprehensive numerical experiments and sensitivity analyses to evaluate the impact of differentiated pricing strategies on travel mode choice probabilities and operator revenues. The model was applied to Xi’an, a city with a rapidly expanding subway network. Sensitivity analyses focused on key variables such as departure time, ride-hailing cost, and income. The findings reveal that high-income travelers exhibit lower sensitivity to ride-hailing costs, while low-income groups are more cost-sensitive, particularly during peak periods. Departure time significantly amplifies the effect of public transportation travel time on mode choice. All travelers show a strong preference for ride-hailing when the cost is below 30 RMB, whereas most opt for public transportation when the cost exceeds 50 RMB. Numerical simulations further demonstrate that targeted subsidies for low-income travelers can increase their probability of choosing ride-hailing by more than 30% during peak hours, without compromising operator revenue due to increased ridership and premium pricing for high-income users. These results highlight the need for targeted, data-driven policies to enhance both the efficiency and equity of urban multimodal transit systems.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101150"},"PeriodicalIF":5.7,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145261995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The 15-minute city revisited: A GIS approach to measuring, visualizing, and analyzing accessibility by proximity and by public transport supply","authors":"Kostas Mouratidis","doi":"10.1016/j.tbs.2025.101151","DOIUrl":"10.1016/j.tbs.2025.101151","url":null,"abstract":"<div><div>The 15-minute city can offer a meaningful framework for measuring and analyzing accessibility to basic urban functions, if proper theoretical and methodological choices are made. This paper develops a comprehensive methodology and presents the steps for measuring, visualizing, and analyzing x-minute accessibility by proximity (walking accessibility) and accessibility by public transport supply (accessibility potential created by nearby public transport services) using geographic information systems (GIS). Five sequential steps are presented: project definition, data preparation, measuring accessibility, visualizing accessibility and insufficient accessibility, and analyzing accessibility using spatial statistical analysis and modeling. The proposed approach is applied to Copenhagen. Results indicate that, even in a city where sustainable mobility is prominent, there are spatial clusters of lack of accessibility and insufficient accessibility, lying mainly in suburban locations. Proximity-based accessibility and accessibility by public transport supply are found to highly overlap across space. Moreover, density was found to largely predict both 15-minute walking accessibility to local destinations and accessibility to other areas via public transport. This approach can be used as a guide by those aiming to understand the patterns and drivers of accessibility across space, reveal socio-spatial inequalities, and identify locations for potential interventions that improve walking accessibility and reduce car dependence.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101151"},"PeriodicalIF":5.7,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145262011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Between pause and pulse: How travel time shapes opt-out preferences in Hong Kong’s urban street experiments","authors":"Ho-Yin Chan ,&nbsp;Chloe Lai ,&nbsp;Enrica Papa ,&nbsp;Anthony Chen","doi":"10.1016/j.tbs.2025.101147","DOIUrl":"10.1016/j.tbs.2025.101147","url":null,"abstract":"<div><div>Street experimental interventions are increasingly used to test alternative street functions, yet their impacts on travel time and their trade-offs with aesthetic and social benefits remain poorly quantified, particularly in dense urban environments. Existing approaches rely heavily on qualitative, trial-and-error experimentation, offering limited empirical guidance for intervention design. This study introduces a quantitative framework combining generative artificial intelligence (GenAI) and stated preference modeling to assess public acceptance of street experiments in Hong Kong. GenAI-produced photorealistic visualizations were used in a survey of 150 participants (1,200 observations). A nested logit model was estimated, extending the multinomial logit (MNL) approach by relaxing the Independence of Irrelevant Alternatives (IIA) property inherited from MNL. This structure captures correlated preferences among intervention types while treating the opt-out alternative as a distinct manifestation of status quo bias. Preferences were examined across road types (alleys, pavements, minor, major), temporality (temporary vs. permanent, time of day), intervention forms (bike lanes, shared spaces, pocket parks, outdoor dining), and travel time impacts. Results indicate strong aversion to travel time disruptions, with even minor delays significantly reducing acceptance. Visually appealing, socially vibrant interventions featuring seating and greenery are preferred, while bike-related infrastructure encounters cultural and spatial resistance. Opt-out behavior is particularly pronounced among older adults, residents of high-density areas, individuals with lower educational attainment, and frequent public transport users, reflecting heightened time sensitivity, space constraints, and reliance on existing transit networks. Findings underscore the importance of explicitly modeling opt-out choices and provide a transferable, data-driven framework for designing incremental and socially accepted street experiments suited to high-density Asian cities, thereby advancing the evidence base for tactical urbanism.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101147"},"PeriodicalIF":5.7,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220103","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Where I live is what I do – The potential of residential choices to determine energy use and travel behaviour of Norwegian movers","authors":"Tanja Scheffler ,&nbsp;Christian A. Klöckner ,&nbsp;Eva Heinen","doi":"10.1016/j.tbs.2025.101138","DOIUrl":"10.1016/j.tbs.2025.101138","url":null,"abstract":"<div><div>Travel behaviour and energy use are strongly linked to the residence and thus to residential choice. However, in residential choice research, there is still limited evidence on how housing and location choice impact both mobility needs and energy decisions over a long time.</div><div>We surveyed Norwegian homebuyers to analyse the extent to which their residential preferences and former home influence the choice of future residence characteristics related to energy and travel demand. These characteristics include dwelling type and size, energy standard, access to parking and public transport as well as proximity to the city centre.</div><div>Our findings indicate that movers select residences that match their preferences for energy- and travel-related attributes. However, the characteristics of the former home also explain the newly chosen characteristics, suggesting loss aversion or a bias of preferences towards the previously experienced. Additionally, the choice of dwelling type constrains subsequent choice options, particularly regarding floor area and centre proximity. Furthermore, high income is associated with less sustainable choices regarding dwelling size and parking access. Generally, characteristics offer co-benefits for reduced energy and travel demand in proximity to the city centre. Smaller dwellings, fewer detached houses and more public transport stops are expected to lead to lower travel demand and energy use. However, these benefits come with trade-offs in energy standard, which tends to be better outside the city centre.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101138"},"PeriodicalIF":5.7,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerate transit network design problem-solving based on large-scale smart card data and graph-clustering decomposition","authors":"Da Lei ,&nbsp;Long Cheng ,&nbsp;Pengfei Wang ,&nbsp;Xuewu Chen","doi":"10.1016/j.tbs.2025.101145","DOIUrl":"10.1016/j.tbs.2025.101145","url":null,"abstract":"<div><div>Transit network optimization problems, such as the Transit Network Design (TND) problem, are generally difficult to be solved within reasonable computational time, especially for large real-world instances potentially containing thousands of bus stops and millions of stop-level OD pairs. Modifications made in existing TND studies for improving the computational performance could vary across different solution methods, assumptions and problem modeling, raising concerns about their transferability and implementation difficulty. This study presents a general framework to accelerate the TND problem-solving for large instances by decomposing the transit network into smaller subnetworks. We first proposed a modified Louvain algorithm to generate an optimal network partitioning based on transit passenger flows extracted from large-scale smart card data. A solution method (i.e., a Genetic Algorithm, GA) is then implemented to address the TND problem in each subnetwork separately and parallelly, thereby saving much computational time. Transit routes generated and optimized in each subnetwork are then combined into one route set as the solution for the entire transit network. The experiment on a well-known benchmark dataset shows that the proposed method, even incorporated with only a basic version of GA, can yield solutions better than most of its existing competitors with an outstanding computational performance. Moreover, the results indicate that our method could speed up the basic GA nearly 1,000 times faster on the iteration process. Another experiment on a real-world network instance (i.e., the Nanjing bus) shows that our method can optimize the currently operating routes, reducing the average travel time by 18.6% and the number of transfers by 17.7%. Code and data for the implementation of the GCGA framework and metrics calculations are provided at <span><span>https://github.com/Radar-Lei/TBS-D-2023-00544R1</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101145"},"PeriodicalIF":5.7,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel integrated machine learning and inferential modeling approach to explore non-linear effects of built environment on travel: a three-wave repeated cross-sectional study","authors":"Niaz Mahmud Zafri ,&nbsp;Ming Zhang","doi":"10.1016/j.tbs.2025.101146","DOIUrl":"10.1016/j.tbs.2025.101146","url":null,"abstract":"<div><div>This study investigates the dynamic effects of the built environment on travel in Austin, Texas, over a 20-year period. Using three waves of household travel surveys from 1997, 2006, and 2017, the research employs a repeated cross-sectional approach to address the limitations of traditional longitudinal and cross-sectional studies, and to more accurately estimate effect sizes. Methodologically, we introduce a novel integration of machine learning and inferential modeling to uncover non-linear relationships and threshold effects of the built environment characteristics on travel. Using Gradient Boosted Decision Trees (GBDT) and Partial Dependence Plots (PDPs), we first identify optimal threshold points in the relationships, which are then incorporated into piecewise multilevel models.</div><div>Findings from the study reveal that the built environment serves as a sustainable tool for managing travel in the long term, contributing 50 % or more to the total feature importance in predicting individual travel—surpassing the combined effects of personal and household characteristics. Improved transit accessibility, enhanced local and regional accessibility, higher population and employment densities, and greater diversity are all associated with significant reductions in travel—particularly within their identified thresholds—though the magnitude of their influence varies across time periods and shows diminishing marginal returns.</div><div>These findings highlight the potential of smart growth policies—such as expanding transit accessibility, promoting high-density and mixed-use development, and discouraging single-use development and peripheral sprawl—as effective strategies to reduce car dependency and manage travel demand. Moreover, the study demonstrates that the proposed integrated approach can effectively capture complex non-linear effects while enhancing flexibility and interpretability, reducing researcher bias, and enabling statistical inference—ultimately providing more robust and policy-relevant insights.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101146"},"PeriodicalIF":5.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"City Fly: Modeling demand and vertiport location jointly for urban commuting","authors":"Li Tang ,&nbsp;Chuanxiang Yue ,&nbsp;Lijing Ma ,&nbsp;Jiahong Zhao ,&nbsp;Yuanqing Zhou","doi":"10.1016/j.tbs.2025.101142","DOIUrl":"10.1016/j.tbs.2025.101142","url":null,"abstract":"<div><div>The rapid development of electric vertical take-off and landing (eVTOL) aircraft presents transformative opportunities for urban air mobility (UAM). As cities globally accelerate infrastructure development, vertiport placement must reconcile demand-driven accessibility with geographic feasibility to address societal needs. However, only a limited number of studies have embedded precise demand analysis into vertiport location selection models, and empirical research using real-world data remains underexplored. This paper proposes a novel three-step demand forecasting and multi-objective optimization model (3DF-MOM) that jointly addresses these challenges. The model predicts UAM commuting demand with minimal prior knowledge, utilizing urban geographic information system (GIS) layers to optimize vertiport location selection under dual societal-geographic criteria: minimizing noise exposure for densely populated neighborhoods, lowering operational expenditures through cost-effective spatial configuration, and maximizing demand coverage across spatially fragmented urban zones. An empirical study was conducted based on urban geographic information data from Chengdu, China, in combination with ArcGIS. The results show that there will be 155 eVTOL aircraft commuting trips per day in Chengdu by 2030. The model optimally balances noise control, efficiency, and demand coverage with six vertiports of different sizes. The 3DF-MOM framework advances sustainable low-altitude infrastructure development by embedding geographic intelligence and social equity metrics into decision-making, offering policymakers a scalable tool to harmonize environmental, economic, and spatially inclusive service quality objectives.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101142"},"PeriodicalIF":5.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bus drivers’ intention to accept level 4 autonomous buses in ethical dilemmas: An extended technology acceptance model","authors":"Yu-Kai Huang ,&nbsp;Jyun-Kai Liang ,&nbsp;Chung-Cheng Lu","doi":"10.1016/j.tbs.2025.101143","DOIUrl":"10.1016/j.tbs.2025.101143","url":null,"abstract":"<div><div>As autonomous driving technology progresses in the private vehicle sector, research on autonomous buses is gaining global attention. Most studies currently focus on passenger needs and attitudes, with less attention given to the drivers who directly operate these vehicles. This study examines the attitudes and behavioral intentions of current bus drivers under different operational scenarios using Level 4 autonomous buses. By extending the Technology Acceptance Model to include trust and compatibility and integrating it with the Integrative Ethical Decision-Making Framework (IEDMF), the study analyzes drivers’ intentions to use AI systems in moral dilemmas. This theoretical integration provides a comprehensive understanding of how rational and intuitive moral reasoning influence technology acceptance in ethical contexts. Structural equation modeling indicates that perceived usefulness and ease of use are critical factors influencing drivers’ operations of autonomous buses in such contexts. The research also reveals significant differences in decision-making behaviors between urban and intercity bus drivers in moral dilemmas, with urban drivers more likely to rely on AI for ethical judgment and prioritize pedestrian safety in critical situations. These findings highlight the importance of targeted training programs: urban bus drivers should focus on urban safety and ethical considerations of pedestrian areas, whereas intercity drivers should enhance their strategies for managing long-distance driving ethics and highway dilemmas. Furthermore, this study underscores the necessity of investing in robust AI systems capable of making ethical decisions under pressure and advocates for integrating diverse ethical frameworks into these systems to better reflect societal values and norms, providing guidance for the future operation of autonomous buses.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101143"},"PeriodicalIF":5.7,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Impact of sea level rise on aging population’s accessibility to essential services in Honolulu, Hawaii","authors":"Dingyi Liu,&nbsp;Suwan Shen","doi":"10.1016/j.tbs.2025.101139","DOIUrl":"10.1016/j.tbs.2025.101139","url":null,"abstract":"<div><div>With demographic shifts showing an increasing elderly population and growth in low-elevation coastal zones, this study investigates the impacts of sea level rise on elderly accessibility to essential services in Honolulu, Hawai’i, exploring the question how sea level rise will affect road accessibility to essential services for the elderly.</div><div>Using the Cohort Change Ratio (CCR), we project the elderly population in each Traffic Analysis Zone (TAZ) over the coming decades. The study identifies road segments and essential facilities at risk under various sea-level rise scenarios (1.1 feet and 2.0 feet) and analyzes network connectivity from each TAZ to essential services.</div><div>Results indicate that while infrastructure damage is moderate, accessibility to essential services in vulnerable communities will be significantly impacted, even under 1.1 feet rise. Some areas with high elderly populations could be isolated due to transportation bottlenecks. These findings underline the urgent need for transportation network planning to ensure connectivity for vulnerable elderly populations and suggest that long-term land use planning is crucial for climate change adaptation. The methodology and insights from this study are applicable to other coastal regions and can inform adaptation planning practices nationwide.</div></div>","PeriodicalId":51534,"journal":{"name":"Travel Behaviour and Society","volume":"42 ","pages":"Article 101139"},"PeriodicalIF":5.7,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}