Understanding multi-modal urban mobility patterns is essential for effective planning and policy-making. Traditional data sources, such as infrequent surveys or smart card records, often lack the temporal, spatial, and modal comprehensiveness required to fully capture the complexity of multi-modal travel behavior. Emerging mobility data sources are instrumental in capturing these patterns and in enabling additional insights. This study leverages a digitally collected trajectory-level dataset (i.e., TravelSense) obtained from a smartphone application operated by the public transport authority of Helsinki, Finland. Unlike conventional public transport data, TravelSense provides insights into modal choices alongside temporal and spatial travel characteristics. In order to analyze mobility patterns and explore the capabilities of this novel dateset, a Latent Profile Analysis is employed to classify travelers based on these attributes over a week-long period, with profiles compared across three consecutive years (2022, 2023, and 2024). Findings reveal that while spatial travel patterns remain relatively stable, temporal and modal patterns exhibit greater variability. A distinct shift is observed between 2022 and subsequent years, likely reflecting post-pandemic behavioral changes. Key traveler groups identified include exclusive active mode users (13 % annually) and non-private car users, whose share declined from 38 % in 2022 to approximately 20 % in 2023 and 2024. Study findings offer valuable input for shaping evidence-based mobility policies, particularly those aiming to support sustainable travel behavior and adapt to evolving urban mobility needs through enhanced multi-modality. TravelSense enables detailed analysis of temporal, spatial, and modal travel patterns, underscoring the value of novel data for multi-modal transport research.

Providing relevant information is crucial in public transport systems. With the rise of digital passenger information systems (PIS), personalization has emerged as a means to meet passengers’ information needs better. To better understand how personalization can be implemented in PIS, five levels of personalization have been identified in the literature, highlighting varying degrees of system autonomy and passenger involvement. While these levels have advanced the understanding of personalization, their practical application remains limited. This paper builds upon an existing framework of personalization levels. It introduces an evaluation tool composed of distinct performance measures to help PIS developers assess their system’s current personalization level and identify opportunities for technological advancement. The tool enables a comparison of the personalization functionalities against the best practices defined by the personalization levels. The paper further outlines the creation of the tool through functional benchmarking, introduces system behaviors across levels, and evaluates commercial PIS through case studies, offering actionable insights for advancing PIS personalization.

As concerns about climate change increase, the environmental impact of long-distance travel – including academic conference travel – is coming into focus. Multiple universities have recently started to deploy sustainability policies committed to net-zero targets. However, it remains uncertain today whether academics are ready to embrace such initiatives and transform their practices for the sake of the environment. In this study, we explore the motivational factors behind academics’ willingness to limit their conference travel based on a survey conducted in Spain. The results highlight the role played by a set of demographic, socioeconomic, work-related, and attitudinal factors, as estimated by means of an ordered logit model. All else being equal, postdoctoral researchers and individuals who live in single-person households are more likely than others to reduce their travel. In terms of psychological attributes, we detect that individuals with a higher level of green values and more influenced by social norms are more intended to limit their conference trips. Conversely, those who believe that conferences are a driver for professional development are less willing to lower their travel. Our findings can help institutions to identify the segments of academics with a higher (and lower) probability of changing their behaviour towards more sustainable habits.

This research introduces a new method for constructing and training an Urban Space Embedding Model (USEM) by integrating human perceptions and street-level images (SLI) into its formulation. Traditional urban embedding models often overlook subjective human experiences, such as perceptions of safety or attractiveness. To address this gap, our method leverages similarity judgments from over 1500 participants, who compared different urban spaces based on SLI. These human judgments were then used as a supervision signal in training the USEM, allowing the model to capture both visual and perceptual information about urban spaces. The method is implemented across the Netherlands, using around one million geo-tagged SLI, and demonstrated in Rotterdam. This approach represents a significant advancement in urban computing by incorporating human-centered data into urban modeling. It offers new opportunities for city planners and policymakers to better understand how urban spaces are perceived and to consider these perceptions in efforts to design more livable and inclusive environments.

Shared on-demand mobility services, also known as microtransit, have become a major mobility provider around the world, yet this has predominantly taken place within urban areas. In areas with lower population density and poor quality public transport, such services could substantially improve accessibility. In early 2023, a regional microtransit pilot was carried out in the Ljubljana Urban Region in Slovenia. To assess the preferences towards such a service, a stated preference experiment is carried out among pilot participants, comparing car, public transport and microtransit for their daily commute. The obtained data is modelled using a Panel mixed logit model, with random parameters modelled as normally or log-normally distributed. Additionally, we also model for potential nesting effects among the alternatives. The results show participants perceive microtransit as a viable alternative, with public transport commuters finding it particularly attractive, whereas car commuters see it on par with the car. Parking price and a guaranteed parking spot tended to be key factors for decision-making. Simulating different policies, we conclude that combining subsidising microtransit and higher parking prices is the most effective strategy for achieving a modal shift primarily from car to microtransit while not affecting public transport as much.

The emergence of social media offers unprecedented opportunities to map social unrest with high spatiotemporal resolution. This study leverages geolocated social media footage to analyze the spatiotemporal distribution of the 2023 ‘Nahel Merzouk’ riots in France. Using a fine-tuned computer vision model, we detect riot-related content in visual data and validate our approach by comparing the spatiotemporal patterns of detected posts with rioting events reported in the press. Our method yields a spatial resolution of 300 300 m, thereby facilitating a detailed analysis of riot distributions at unprecedented scale. By applying density-based clustering, we map riots across seven French cities, revealing their highly localized and bursty dynamics. This study opens pathways for future research on the causes and dynamics of social unrest, enabling a deeper understanding of urban riots and their potential mitigation.

Recent advances in battery technologies and a global push for greener transport have accelerated the development of electrified public transportation systems. Such systems often face challenges due to the need for large battery capacities and the high costs associated with conventional charging infrastructure. This study examines the potential of Mobile Autonomous Charging Pods (MAPs), which are autonomous charging vehicles, as an innovative solution to enhance both the efficiency and costeffectiveness of electric bus operations in urban environments. Using the case of inner-city trunk bus lines in Stockholm and employing a microscopic simulation-based study, three charging scenarios are evaluated: depot charging only, depot combined with end-station charging, and depot plus MAP charging. The results indicate that the integration of MAPs can significantly reduce the required battery capacities and associated infrastructure costs while enhancing the reliability of the service. By facilitating dynamic, on-the-go charging, MAPs offer a sustainable and economically viable alternative for urban electric bus networks.

On-board crowding in public transportation has significant impact on passengers' travel experience. New land-use planning configurations can have wide-ranging crowding effects in the public transportation system. Nevertheless, there is a lack of knowledge on the crowding implications caused by new urban developments. In this study, we propose a method for quantifying the network-wide crowding implications of a new urban development. We apply the method to different kinds of urban developments in terms of type, size, location, proximity to high-capacity public transportation connections as well as socioeconomic characteristics. Size and proximity to a high-capacity connection are highly influential factors in determining the value and the geographical extent of the crowding implications. The analysis proposed in this paper can serve as a tool for the ex-post quantification of the on-board crowding impacts using automated data sources. The insights gained can be utilized in more efficient dimensioning of the supply (service) for newly developed areas as well as for placement of future urban developments accounting for the resulting crowding effects.

Short-haul Flight (SHF) bans aim to stimulate the air-to-rail modal shift, consequently curbing the aviation sector's environmental impact. We investigate the potential implications of various SHF ban policy designs on CO2-equivalent (CO2e) emissions, passengers’ travel times and rail capacity under the assumption of full air-to-rail modal substitution. Ranging from 0.4 Mt to 7.5 Mt CO2e, respectively 0.6% to 12.3% of the emissions of commercial intra-European aviation, the environmental impact of SHF ban policies is shown to be largely dependent on the policy design, namely the affected journey types and rail in-vehicle time thresholds. Our findings underscore the significant challenges of implementing such policies for the longer rail in-vehicle time thresholds and wider geographical scopes associated with noticeable environmental benefits. Despite the marginal impact of SHF ban policies on capacity utilisation in the case study, considerable interventions on rail infrastructure would be required to absorb existing air demand completely while ensuring attractive schedules. The results contribute to the ongoing policy debate, providing actionable insights to support Europe's ambitious environmental goals in the transport sector.

Demand prediction is essential for effective management of Mobility-on-Demand (MoD) systems, as accurate forecasts enable better resource allocation, reduced wait times, and improved user satisfaction. Beyond that, probabilistic prediction methods that explicitly account for uncertainty are particularly valuable, as it allows decision-makers to assess risk and make robust plans under uncertain operational environments. However, most existing approaches focus on point predictions, which fail to capture the full spectrum of possible future outcomes. For probabilistic prediction, many methods typically rely on strong parametric distributional assumptions that may not accurately reflect the complex real-world environments. Nonparametric methods proposed in the literature, although promising, often suffer from high computational costs and model complexity, limiting their practical applicability. To overcome these challenges, we propose the Spatial-Temporal Graph Convolutional Network Variational Autoencoder (STGCN-VAE), a novel deep learning framework designed for uncertainty-aware probabilistic travel demand prediction in MoD services. The STGCN-VAE effectively captures complex spatial-temporal dependencies and inherent uncertainties in MoD demand data, generating diverse and realistic future demand scenarios and constructing comprehensive demand distributions. Specifically, the proposed framework integrates three key components: a Spatial-Temporal Graph Convolutional Network (STGCN) to learn complex spatial-temporal dependencies, a Variational Autoencoder (VAE) to compress these patterns into a latent space, and a Kernel Density Estimation (KDE) module to accurately construct probabilistic demand distributions and quantify uncertainties. Experiments on four different real-world MoD datasets including both rideshare and bikeshare services across different cities demonstrate that STGCN-VAE consistently outperforms state-of-the-art baselines in both point and probabilistic prediction, highlighting its robustness and broad transferability across service modes and urban contexts.

This dataset contains the outputs of the paper "Replacing short-haul flights with train travel: Exploring impacts, capacity requirements and policy implications", published in Transport Policy. The paper investigates the potential implications of various SHF ban policy designs on CO2-equivalent emissions, passengers’ travel times and rail capacity, under the assumption of full air-to-rail modal substitution. The datasets are published to substantiate paper results and for use by other researchers. The data made available in this repository refers to travel time and emissions assessments, including some inputs and the aggregated outputs. Due to the limitations agreed upon with the data provider, the input data is not complete. The input data has been collected from multiple sources, including OAG, Rome2Rio and Google Distance Matrix API, and has been cleaned and processed using Python. More information is available in the README.txt file and the paper referenced below.

Semi-flexible transit, integrating fixed-route and on-demand services, offers a demand-adaptive and cost-effective alternative for public transit users, particularly in low-demand conditions. Despite the growing interest in this system, existing approaches have failed to develop comprehensive optimization methods for managing demand fluctuations across distinct scenarios, thereby significantly constraining operational adaptability in semi-flexible transit services. To address this research gap, we propose a scenario-based optimization model that jointly determines the fleet size and master routes at the tactical level as well as sub-routes at the operational level. The objective is to minimize travel costs while ensuring service feasibility under varying passenger demand scenarios, accounting for constraints such as travel time, state changes, time windows, and route consistency. Then, an Augmented Lagrangian Relaxation under Alternating Direction Method of Multipliers (ALR-ADMM) decomposition solution framework is introduced to decouple the proposed integrated problem into three sub-problems, namely master route, sub-route and service planning problems. Numerical experiments on the Sioux-Falls network validate the proposed model and solution approach, achieving a 94.93 % reduction in computation time while maintaining an average optimality difference of 0.57 % compared to the Gurobi optimizer. Sensitivity analysis further examines the effects of vehicle capacity limits, penalty parameters, and demand stop selection, revealing their impact on computational efficiency and operational costs. The applicability of our approach is further assessed through a real-world case study on the West Jordan network, which provides evidence of the ALR-ADMM-based algorithm in terms of both solution quality and computational efficiency. Our findings illustrate the feasibility and potential of the proposed model and algorithm in navigating both the tactical and operational scheme of semi-flexible transit within modern urban transit systems.

Ride-hailing has become an important part of the urban mobility landscape. The main contribution of this study is to estimate how travellers perceive time when using ride-hailing compared to using conventional public transport, to better understand ride-hailing mode choice. We combine two unique datasets containing actual, individual passenger behaviour for the Washington DC area from October 2018: a large set of almost 250,000 individual ride-hailing trips made using Uber, and more than 326,000 public transport trips obtained from automated ticketing data. Contrary to previous studies our model estimations rely on over half a million directly observed passenger choices between ride-hailing and public transport, based on which we estimate a discrete choice model to infer travel time perceptions for both modes using a binomial logit model. Our results show that on average ride-hailing in-vehicle time is perceived 35% less negative than public transport in-vehicle time. We also found that waiting time for ride-hailing is valued 1.3 times more negative than ride-hailing in-vehicle time, which is about 20% less negative than the ratio between waiting and in-vehicle time found for public transport. Our study enables a more accurate modelling of ride-hailing by using mode-specific travel time coefficients derived from large-scale empirical data, which can improve the accuracy of modelling outputs and thus improve decision-making processes.

To understand why ridesourcing markets may be prone to evolve towards potentially socially undesirable equilibrium states, we conceptualize the network effects present in ridesourcing provision. In addition, we propose an agent-based model that allows simulating the effect of market conditions and platform strategies on system performance, accounting for such network effects. This day-to-day model captures sequential decentralized processes characterizing both sides of the two-sided ridesourcing market, i.e. information diffusion, platform registration, platform participation, and learning based on experience. We apply the model on a case representing Amsterdam, the Netherlands. Our simulation results suggest that a profit-maximizing ridesourcing platform may trade-off market transaction volume for higher earnings on successful transactions, a strategy that is harmful to the interests of travellers and drivers, and possibly of (very) limited benefit to the platform. Moreover, we find that ridesourcing operations may be viable even when potential supply and demand in an area are limited.

As a two-sided digital platform, ride-sourcing has disruptively penetrated the mobility market. Ride-sourcing companies provide door-to-door transport services by connecting passengers with independent service suppliers labelled as “driver-partners”. Once a passenger submits a ride request, the platform attempts to match the request with a nearby available driver. Drivers have the freedom to accept or decline ride requests. The consequences of this decision, which is made at the operation level, have remained largely unknown in the literature. Using agent-based simulation modelling on the realistic case study of the city of Amsterdam, the Netherlands, we study the impacts of drivers’ ride acceptance behaviour, estimated from unique empirical data, on the ride-sourcing system where the platform applies regular and surge pricing strategies, and riders may revoke their requests and reject the received offers. Furthermore, we delve into the implications of various supply–demand intensities, a centralised fleet (i.e., mandatory acceptance on each ride request) versus a decentralised fleet (i.e., ride acceptance decision by each driver), ride acceptance rates, and surge pricing settings. We find that the ride acceptance decision of ride-sourcing drivers has far-reaching consequences for system performance in terms of passengers’ waiting time, driver's revenue, operating costs, and profit, all of which are highly dependent on the ratio between demand and supply. As the system undergoes a transition from undersupplied (i.e., real-time demand locally exceeds available drivers) to balanced and then oversupplied state (i.e., more available drivers than real-time demand), ride acceptance decisions result in higher income inequality. A high acceptance rate among drivers may lead to more rides, but it does not necessarily increase their profit. Surge pricing is found to be asymmetrically in favour of all the parties despite adverse effects on the demand side due to higher trip fare. This study offers insights into both the aggregated and disaggregated levels of ride-sourcing system operations and outlines a series of transport policy and practice implications in cities that offer such ride-sourcing systems.

The matching radius, defined as the maximum pick-up distance within which waiting riders and idle drivers can be matched, is a critical variable in ride-hailing systems. Optimizing the matching radius can significantly enhance system performance, but determining its optimal value is challenging due to the dynamic nature of ride-hailing environments. The matching radius should adapt to spatial and temporal variations, as well as to real-time fluctuations in supply and demand. To address this challenge, this paper proposes a dual-reply-buffer deep reinforcement learning method for dynamic matching radius optimization. By modeling the matching radius optimization problem as a Markov decision process, the method trains a policy network to adaptively adjust the matching radius in response to changing conditions in the ride-hailing system, thereby improving efficiency and service quality. We validate our method using real-world ride-hailing data from Austin, Texas. Experimental results show that the proposed method outperforms baseline approaches, achieving higher matching rates, shorter average pick-up distances, and better driver utilization across different scenarios.

The shift from private vehicles to public and shared transport is crucial to reducing emissions and meeting climate targets. Consequently, there is an urgent need to develop a multi-modal transport trip planning approach that integrates public transport and shared mobility solutions, offering viable alternatives to private vehicle use. To this end, we propose a preference-based optimization framework for multi-modal trip planning with public transport, ride-pooling services, and shared micro-mobility fleets. We introduce a mixed-integer programming model that incorporates preferences into the objective function of the mathematical model. We present a meta-heuristic framework that incorporates a customized Adaptive Large Neighborhood Search algorithm and other tailored algorithms, to effectively manage dynamic requests through a rolling horizon approach. Numerical experiments are conducted using real transport network data in a suburban area of Rotterdam The Netherlands Model application results demonstrate that the proposed algorithm can efficiently obtain near-optimal solutions. Managerial insights are gained from comprehensive experiments that consider various passenger segments, costs of micro-mobility vehicles, and availability fluctuation of shared mobility.

Railway systems suffer from disturbances in operations, such as extended section running times caused by temporary speed restrictions and prolonged dwell times at stations due to unexpected passenger volumes. These disturbances cause deviations from the original timetable and negatively impact service reliability and passenger experience. Effective and timely rescheduling measures are crucial in reducing the impact of these disturbances. Existing timetable rescheduling models that rely on optimization-based methods often struggle with computational inefficiency, especially when dealing with scenarios involving a large number of train services. To address these challenges, we propose a learning-based timetable rescheduling framework that considers scalability in its formulation to reduce the growing computational burden associated with an increasing number of train services. The proposed framework decomposes the complex rescheduling problem into multiple subtasks, facilitating a systematic approach to managing extensive railway networks with numerous stations and train services. A high-level agent, functioning as a centralized traffic controller, is responsible for decomposing the overall deviation reduction task into subtasks at a low level and assigning them to individual train services with the primary objective of minimizing the time required to restore the original timetable. Low-level agents, acting as distributed train dispatchers, are tasked with rescheduling the timetables of their assigned trains. These low-level agents employ various dispatching strategies, facilitated by inter-train communication, to search for optimal rescheduling solutions while adhering to operational constraints such as minimum headway requirements. The lowlevel agents utilize an actor-critic architecture to generate continuous control decisions for dwell and running times, enabling them to learn and optimize their performance. Knowledge-sharing mechanisms amongst the low-level agents enable faster and more robust learning. Furthermore, advanced exploration methods are integrated to enhance the efficiency of the agents' training process.

Today, there is growing concern over the climate impact of long-distance travel – academic conference travel included. While institutions worldwide develop sustainability policies, it remains unclear whether academics are willing to adopt such measures and change their behaviours for environmental reasons. Based on a survey of 245 Spanish academics, we identify a set of motivational factors underlying individuals’ intentions towards conference travel. Using Latent-Class-Cluster-Analysis, we detect three distinct profiles: “Low-concerned academics”, with limited regard for environmental concerns and social norms; “Performance-oriented academics”, driven by career advancement; and “Flight-shamed academics”, highly aware of environmental and social issues. Additionally, we examine perceptions of the actual, minimum, and expected number of conferences attended annually, recognising notable discrepancies. Our findings can inform targeted policies in four key areas: promoting greener choices, reshaping academic culture to normalise lower-carbon practices, raising awareness and strengthening institutional engagement, and supporting online participation.

Bert van Wee, professor in Transport Policy at Delft University of Technology, the Netherlands, faculty Technology, Policy and Management, is retiring. Given his large contributions to EJTIR as Editor-in-Chief, editorial board member, author and reviewer, this Editorial Note is dedicated to his work for EJTIR. Over 25 years, van Wee published 18 papers and 1 book review in EJTIR covering a wide range of topics from road pricing to urban rail transport, vehicle automation and port throughput. What his studies have in common is that they explore how transport policies affect land-use and travel behaviour, as well as the economic and wider societal impacts of those policies. Bert van Wee’s generalist view on the transport system is rare, but, given the rising complexity of the system, increasingly needed to indeed be able to address the future challenges.