Large-scale prediction of trip production is essential for origin–destination (OD) demand estimation and prediction. One of the main challenges in predicting trip production patterns lies in addressing spatial-temporal correlations and variations. Whereas many studies focus on temporal correlations, very few consider spatial adjacency between traffic analysis zones (TAZ) as explanatory variables. This research proposes a method that integrates a graph convolutional neural network (GCN) into a long short-term memory network (LSTM) to do exactly that. By introducing a nationwide graph that encodes the adjacency of TAZs, spatial heterogeneity is considered in the prediction process, and a single prediction model is trained for the entire network, thereby avoiding the need to train multiple separate models and potentially reducing overall training overhead, while increasing the prediction accuracy. Moreover, with this model, we investigate the effect of spatial scale on spatial uncertainty and prediction accuracy and analyze prediction errors, residual patterns, and their associations with socio-spatial features at different spatial scales. The findings of this research have important implications for improving OD demand prediction models and provide valuable insights into the role of spatial scale and socio-spatial features in travel demand prediction.

The advent of Connected and Automated Vehicles (CAVs) has ushered in substantial changes in the transportation sector, particularly impacting the resilience of road networks. CAVs can exchange real-time information about road conditions, allowing them to bypass congestion and optimise their routes, thereby enhancing network resilience through dynamic rerouting. Additionally, these vehicles significantly affect road capacity, further bolstering the overall resilience of the network. As a result, it is essential to assess the impact of CAVs on road network resilience comprehensively. However, to the best of the authors’ knowledge, there is a notable gap in research that thoroughly evaluates the resilience of large-scale road networks, taking into account all dimensions of resilience, such as redundancy, robustness, and recovery speed. This paper aims to fill this gap by assessing the influence of CAVs on the resilience of a large-scale road network in Belgium. Utilising a simulation-based approach, the study quantifies the network's resilience triangle, addressing all facets of network resilience. The findings reveal that the integration of CAVs can markedly improve network resilience under various scenarios, with improvements ranging from 4.4% at a 10% penetration rate to 59.9% at full penetration. These insights are valuable for researchers and policymakers focused on the implementation of autonomous vehicles.

The bicycle is a very important mode for travel in various countries, particularly in the Netherlands. However, it is in practice often modelled with less detail than other urban modes, such as the car and public transport. Moreover, the increasing use of e-bikes and the differences with conventional bikes show that more research into this transport mode is needed. E-bikes require less physical effort and allow higher speeds, making the e-bike suitable for longer distances. The goals of this research are to (1) create a mode choice model that predicts an accurate modal split for urban areas in the Netherlands and this model is used to (2) find significant factors that influence the modal split, in order to support municipalities of Dutch urban areas to stimulate the use of the (e-)bike. Within both goals, potential differences between conventional bikes and e-bikes are considered. A conceptual model, following from the literature, describes the assumed modal choice including factors relevant to cycling. Data was used mainly from the Dutch National Travel Survey (ODiN). Discrete choice models, a multinomial logit and a nested logit, are estimated to identify significant influencing factors. Results show that a nested logit model is the most explanatory one compared to the other models, with a rho-square-bar of 0.469. The model includes 15 main variables, 3 quadratic components and 4 interaction effects. The nested structure is formed by a correlation between the bike and the e-bike. The factors that show to be generally highly influential for the bike and the e-bike are the travel distance, owning a driver’s license and street density. The model is practically applicable for municipalities to form expectations in the modal shift for changes in their networks or policies. However, modelling these changes has not been validated and thus needs further research.

To improve the accuracy of large-scale strategic transport models in congested conditions, this paper presents a straightforward extension of a static capacity-constrained traffic assignment model into a semi-dynamic version. The semi-dynamic model is more accurate than its static counterpart as it relaxes the empty network assumption, but, unlike its dynamic counterpart, maintains the stability and scalability properties required for application in large-scale strategic transport model systems. Applications show that, contrary to static models, semi-dynamic queue sizes and delays are very similar to dynamic outcomes, whereas only the congestion patterns differ due to the omission of spillback. The static and semi-dynamic models are able to reach user equilibrium conditions, whereas the dynamic model cannot. On a real-world transport model, the static model omits up to 76% of collective losses. It is therefore very likely that the empty network assumption influences (policy) decisions based on static model outcomes.

This paper explores temporal patterns in travel production using a full month of production data from traffic analysis zones (TAZ) in the (entire) Netherlands. The mentioned data is a processed aggregated derivative (due to pr ivacy concerns) from GSM traces of a Dutch telecommunication company. This research thus also sheds light on whether such a processed data source is representative of both regular and non-regular patterns in travel production and how such data can be used for planning purposes. To this end, we construct normalized matrix (heatmap) representations of weekly hour-by-hour travel production patterns of over 1200 TAZs, which we cluster using K-means combined with deep convolutional neural networks (inception V3) to extract relevant features. A silhouette score shows that three dominant clusters of temporal patterns can be discerned (K=3). These three clusters have distinctly different within-day and day-to-day production patterns in terms of peak period intensity over different days of the week. Subsequently, a spatial analysis of these clusters reveals that the differences can be related to (easily observable) land-use features such as urbanization levels (i.e., Urban, Rural, and mixed-level). To substantiate this hypothesis and the usefulness of this clustering result, we apply an OVR-SMOTE-XGBoost ensemble classification model on the land-use features of the TAZs (i.e., to identify their cluster). The results of our clustering analysis show that given the land-use features, the overall production patterns are identifiable. Further analysis of the mixed-level areas shows a more complex relationship between temporal heterogeneity and spatial characteristics. Population density seems to impose additional uncertainty on the temporal patterns. All in all, feature selection and spatial and temporal discretization play essential roles in identifying the dominant trip production patterns. These findings are directly useful for data-driven estimation and prediction of demand time series. Furthermore, this study provides further insights into people's mobility, relevant for transportation analysis and policies.

Global System for Mobile Communications (GSM) data provides valuable insights into travel demand patterns by capturing people's consecutive locations. A major challenge, however, is how the polling interval (PI; the time between consecutive location updates) affects the accuracy in reconstructing the spatio-temporal travel patterns. Longer PIs will lead to lower accuracy and may even miss shorter activities or trips when not properly accounted for. In this paper, we analyze the effects of the PI on the ability to reconstruct an origin–destination (OD) matrix. We also propose and validate a new data-driven method that improves accuracy in case of longer PIs. The new method first learns temporal patterns in activities and trips, based on travel diaries, that are then used to infer activity-travel patterns from the (sparse) GSM traces. Both steps are data-driven thus avoiding any a priori (behavioral, temporal) assumptions. To validate the method we use synthetic data generated from a calibrated agent-based transport model. This gives us ground-truth OD patterns and full experimental control. The analysis results show that with our method it is possible to reliably reconstruct OD matrices even from very small data samples (i.e., travel diaries from a small segment of the population) that contain as little as 1% of the population’s movements. This is promising for real-life applications where the amount of empirical data is also limited.

This paper presents an efficient solution method for the matrix estimation problem using a static capacity constrained traffic assignment (SCCTA) model with residual queues. The solution method allows for inclusion of route queuing delays and congestion patterns besides the traditional link flows and prior demand matrix whilst the tractability of the SCCTA model avoids the need for tedious tuning of application specific algorithmic parameters. The proposed solution method solves a series of simplified optimization problems, thereby avoiding costly additional assignment model runs. Link state constraints are used to prevent usage of approximations outside their valid range as well as to include observed congestion patterns. The proposed solution method is designed to be fast, scalable, robust, tractable and reliable because conditions under which a solution to the simplified optimization problem exist are known and because the problem is convex and has a smooth objective function. Four test case applications on the small Sioux Falls model are presented, each consisting of 100 runs with varied input for robustness. The applications demonstrate the added value of inclusion of observed congestion patterns and route queuing delays within the solution method. In addition, application on the large scale BBMB model demonstrates that the proposed solution method is indeed scalable to large scale applications and clearly outperforms the method mostly used in current practice.

Due to the uncertain and dynamic environment around scheduling systems, timely revisions or reschedules of the master plans are essential for achieving optimal utilization. With the recent development of Industry 4.0 technologies, many researchers perceive the creation of cyber-physical systems as a solution for managing systems under uncertainty. This article focuses on a loading facility under uncertain truck arrivals due to road congestion and proposes utilizing real-time truck location information to improve performance. We do this by developing an integrated system consisting of a predictive model using machine learning (MC) classifiers and a mathematical model for real-time slot rescheduling. The ML classifier is used to predict the presence probabilities of all the incoming trucks at a particular slot based on the historical traffic data and the real-time truck location. Subsequently, a Mixed-Integer Quadratic Programming (MIQP) model is developed to solve a Probabilistic Slot Rescheduling Problem (P-SRP), which uses the estimated truck presence probabilities and minimizes the total expected cost of rescheduling. We implemented this by first testing multiple ML classifiers and selected the ANN classifier for prediction as it outperformed others. Our limited experiments showed that the proposed method reduced the total rescheduling cost by 42%. Furthermore, our sensitivity analysis with different congestion levels, complexity, and rescheduling strategy also showed the practicality of the proposed approach.

Predictions on public transport ridership are beneficial as they allow for sufficient and cost-efficient deployment of vehicles. At an operational level, this relates to short-term predictions with lead times of less than an hour. Where conventional data sources on ridership, such as Automatic Fare Collection (AFC) data, may have longer lag times, in contrast, trip planner data is often available in (near) real-time. This paper analyzes how such data from a trip planner app can be utilized for short-term bus ridership predictions. This is combined with AFC data (in this case smart card data) to construct a ground-truth on actual ridership. The trip planner data is studied using correlation analysis to select informative variables, that are then used to develop 4 supervised machine learning models (linear, k-nearest neighbors, random forest, and gradient boosting decision tree). The best performing model relies on random forest regression and reduces the error by approximately half compared to a baseline model based on the weekly trend. We show that this model performance is maintained even for prediction lead times up to 30 minutes ahead, and for different periods of the day.

Due to the environmental crisis, there is a need for a more conscious and integrating design process within the field of urban infrastructure development. Through cooperation between civil engineering and spatial design resilience of the built environment can be increased. Delft University of Technology investigates interdisciplinary design as a method and incorporates this into its MSc-level education of students in the faculties of civil engineering and architecture. The focus of the research was on the reconstruction projects after disasters like hurricanes and tsunamis. By way of surveys of the participating students, the effectiveness of the interdisciplinary design methods used, and the interpretation of the terms multidisciplinary and interdisciplinary are revealed. From survey results about understanding of multidisciplinary and interdisciplinary it can be concluded that interdisciplinary design should entail a conscious and orchestrated process in which the disciplines present their ideas within a shared value system before systematic integration. The challenges are at personal and cognitive levels, an open attitude is necessary to be able to perceive and react, process and understand, retrieve information. Only then decisions on - and production of - appropriate responses come out of co-creation between engineering within the spatial design process.

Predictions on Public Transport (PT) ridership are beneficial as they allow for sufficient and cost-efficient deployment of vehicles. On an operational level, this relates to short-term predictions with lead times of less than an hour. Where conventional data sources on ridership, such as Automatic Fare Collection (AFC) data, may have longer lag times and contain no travel intentions, in contrast, trip planner data are often available in (near) real-time and are used before traveling. In this paper, we investigate how such data from a trip planner app can be utilized for short-term bus ridership predictions. This is combined with AFC data (in this case smart card data) to construct a ground truth on actual ridership. Using informative variables from the trip planner dataset through correlation analysis, we develop 3 supervised Machine Learning (ML) models, including k-nearest neighbors, random forest, and gradient boosting. The best-performing model relies on random forest regression with trip planner requests. Compared with the baseline model that depends on the weekly trend, it reduces the mean absolute error by approximately half. Moreover, using the same model with and without trip planner data, we prove the usefulness of trip planner data by an improved mean absolute error of 8.9% and 21.7% and an increased coefficient of determination from a 5-fold cross-validation of 7.8% and 18.5% for two case study lines, respectively. Lastly, we show that this model performance is maintained even for the trip planner requests with prediction lead times up to 30 min ahead, and for different periods of the day. We expect our methodology to be useful for PT operators to elevate their daily operations and level of service as well as for trip planner companies to facilitate passenger replanning, in particular during peak hours.

Transport infrastructure owners are moving from reactive toward proactive infrastructure management. This involves computation of costs associated with failure or maintenance, including expected transport delays. These delays are often computed by multiplying additional travel time by the number of travellers. However, this does not reflect the process of decision-making by travellers using the infrastructure asset, such as mode choices, departure time changes and trip cancellations to reduce time wasted in a traffic jam. Therefore, we introduce a multi-modal transport model that simulates travellers’ behaviour after a large-scale infrastructure failure at a critical node in the European TEN-T network. We use a novel approach of modelling the region around the infrastructure disruption in a very detailed manner, whereas the rest of Europe is modelled in a more basic way. This enables us to model impacts of disruptions in high detail, whereas also effects throughout Europe are considered, within reasonable computation time.

By extending static traffic assignment with explicit capacity constraints, quasi-dynamic traffic assignment yields more realistic results while avoiding many disadvantages of a dynamic assignment. We analyse the computation of travel times in quasi-dynamic assignment models. We formulate and check requirements for the correctness of resulting travel times, addressing both the calculation of travel times for individual routes and links itself, as well as the differences between travel times of different travel choices. We demonstrate that existing approaches for travel time computation in the literature fail to satisfy all requirements and derive a new link travel time formula from the vertical queuing theory that does meet all requirements. We discuss expected changes to assignment results and methodological advantages for pathfinding and model extensions, including horizontal queuing. The new link travel time formulation is finally applied to three example scenarios from literature.

This paper analyzes the observed decision-making behavior of a sample of individuals impacted by Hurricane Irma in 2017 (n = 645) by applying advanced methods based in discrete choice theory. Our first contribution is identifying population segments with distinct behavior by constructing a latent class choice model for the choice whether to evacuate or not. We find two latent segments distinguished by demographics and risk perception that tend to be either evacuation-keen or evacuation-reluctant and respond differently to mandatory evacuation orders. Evacuees subsequently face a multi-dimensional choice composed of concurrent decisions of their departure day, departure time of day, destination, shelter type, transportation mode, and route. While these concurrent decisions are often analyzed in isolation, our second contribution is the development of a portfolio choice model (PCM), which captures decision-dimensional dependency (if present) without requiring choices to be correlated or sequential. A PCM reframes the choice set as a bundle of concurrent decision dimensions, allowing for flexible and simple parameter estimation. Estimated models reveal subtle yet intuitive relations, creating new policy implications based on dimensional variables, secondary interactions, demographics, and risk-perception variables. For example, we find joint preferences for early-nighttime evacuations (i.e., evacuations more than three days before landfall and between 6:00 pm to 5:59 am) and early-highway evacuations (i.e., evacuations more than three days before landfall and on a route composed of at least 50% highways). These results indicate that transportation agencies should have the capabilities and resources to manage significant nighttime traffic along highways well before hurricane landfall.

By extending static traffic assignment with explicit capacity constraints, quasidynamic traffic assignment yields more realistic results while avoiding many disadvantages of dynamic assignment. We analyse the computation of travel times in quasi-dynamic assignment models. We formulate and check requirements for the correctness of resulting travel times, addressing both the calculation of travel times for individual routes and links itself, as well as the differences between travel times of different travel choices. We demonstrate that existing approaches for travel time computation in literature fail to satisfy all requirements and derive a new link travel time formula from vertical queuing theory that does meet all requirements. We discuss expected changes to assignment results and methodological advantages for pathfinding and model extensions, including horizontal queuing. The new link travel time formulation is finally applied to three example scenarios from literature.

By extending static traffic assignment with explicit capacity constraints, quasi-dynamic traffic assignment yields more realistic results while avoiding many disadvantages of dynamic assignment. We analyse the computation of travel times in quasi-dynamic assignment models. We formulate requirements for the correctness of resulting travel times, addressing both the calculation of travel times for individual routes and links itself, as well as the differences between travel times of different travel choices. We derive a new link travel time formula from vertical queuing theory that meets all requirements, unlike existing approaches in literature.

Recent years have shown an interest in developing and using quick-scan
analysis tools for the evaluation of policy options, such as planning issues,
investments in infrastructure or public transport or other measures to cope with the increasing mobility problem. These tools can give a quick and easy insight into the impacts of all kinds of measures, without the large amount of work associated with the use of transport models. The assignment procedure of these tools can be improved and made more consistent with transport models. Therefore, it is needed that the calculation time of standard assignment algorithms is decreased. One possibility is to decrease the size of the route sets used. In this paper, this possibility was investigated for a number of small and medium-sized networks, using a dynamic traffic assignment framework. It was found that a route set in which each OD-pair has a maximum of 4-6 routes is sufficient to get comparable results with the situation with larger route sets. This rule of thumb for the maximum number of routes seems stable if demand increases and is not influenced by the overlap factor, which is an important parameter in the generation of route sets. Further research should focus on the scale factor in the route set generation algorithm and also larger networks need to be studied to be able to come a better founded conclusion about the size of the route set, which can be used in quick-scan tools.

Several traffic modeling tools are currently available for evacuation planning and real-time decision support during emergencies. This paper reviews potential traffic-modeling approaches in the context of wildland-urban interface (WUI) fire-evacuation applications. Existing modeling approaches and features are evaluated pertaining to fire-related, spatial, and demographic factors; intended application (planning or decision support); and temporal issues. This systematic review shows the importance of the following modeling approaches: dynamic modeling structures, considering behavioral variability and route choice; activity-based models for short-notice evacuation planning; and macroscopic traffic simulation for real-time evacuation management. Subsequently, the modeling features of 22 traffic models and applications currently available in practice and the literature are reviewed and matched with the benchmark features identified for WUI fire applications. Based on this review analysis, recommendations are made for developing traffic models specifically applicable to WUI fire evacuation, including possible integrations with wildfire and pedestrian models.

This paper presents the findings of the workshop “New approaches to evacuation modelling”, which took place on the 11th of June 2017 in Lund (Sweden)within the Symposium of the International Association for Fire Safety Science (IAFSS). The workshop gathered international experts in the field of fire evacuation modelling from 19 different countries and was designed to build a dialogue between the fire evacuation modelling world and experts in areas outside of fire safety engineering. The contribution to fire evacuation modelling of five topics within research disciplines outside fire safety engineering (FSE)have been discussed during the workshop, namely 1)Psychology/Human Factors, 2)Sociology, 3)Applied Mathematics, 4)Transportation, 5)Dynamic Simulation and Biomechanics. The benefits of exchanging information between these two groups are highlighted here in light of the topic areas discussed and the feedback received by the evacuation modelling community during the workshop. This included the feasibility of development/application of modelling methods based on fields other than FSE as well as a discussion on their implementation strengths and limitations. Each subject area is here briefly presented and its links to fire evacuation modelling are discussed. The feedback received during the workshop is discussed through a set of insights which might be useful for the future developments of evacuation models for fire safety engineering.