The provision of good accessibility is the main function of a well-functioning public transport (PT) system, the quality of which affects the ability of people to access basic needs such as employment, education, and healthcare. It is therefore important that PT accessibility is distributed in an equitable, or fair, manner. This thesis evaluates the equity of a PT network according to three distinct distribution principles, defined as alternative ideas of what constitutes a fair distribution of resources. Egalitarianism, proportionality, and sufficientarianism are applied in separate equity evaluations of the same area, resulting in the identification of zones of surplus and deficit accessibility according to each principle. When comparing the results of the three equity evaluations, it is found that both the locations and magnitudes of accessibility surpluses and deficits differ between principles. Some principles have deficit zones in common at the periphery of the study area, indicating that the borders of concessions may have been somewhat neglected in the service planning process. However, overall, the main finding is that a PT network that is equitable according to one principle may not be equitable according to another. It is also attempted to use the results of each equity evaluation to make frequency modifications to achieve a more equitable PT network according to each principle. Equity evaluation according to egalitarianism and proportionality were found to not be possible due to the circular calculations inherent in the methodology. It was possible to use the results of the sufficientarianism equity evaluation in network design, therefore this principle can be used as an input in the network planning process. Although further research is still required, these findings can help to inform the incorporation of equity in future PT planning policy, for example through inclusion in concession requirements.

As traffic demands are ever increasing and building new infrastructure poses challenges in densely populated areas, it is important to optimally utilise existing infrastructure. Short-term traffic forecasting can help with this task, as its predictions can help to prevent congestion by rerouting vehicles. Recently, neural networks developed for traffic forecasting have lead to an unprecedented accuracy, but deploying these on large scale can be difficult as the resulting models likely overfit to the highway they were trained on. This thesis therefore performs an in-depth assessment of the accuracy of neural networks traffic speed predictions on highway stretches containing different types of congestion patterns. By relating the results back to traffic flow theory, these results can be put into perspective.

Service reliability is one of the most important performance measures to public transport users. Detecting disruptions helps to measure service reliability, which can be used by public transport operators to improve this reliability. In this thesis, a methodology is described to automatically detect disruptions offline, using smart card data. The day-to-day regularity of delays is investigated using hierarchical clustering on a training set, to distinguish between regular and irregular delays. The clustering result is used to create a probabilistic classifier. This classifier is applied to the test set to find days that do not correspond to a regular pattern: irregular days. After that, disruptions are detected within the irregular days. The outcomes of this study can be applied in multiple ways. Locations where disruptions have occurred can be found and the related passenger delay can be calculated. This can help public transport operators to prioritise which locations to focus on to reduce passenger delays. Furthermore, not only public transport networks, but also other networks can benefit from the outcomes of this study. Speed data of road networks could be used to find disruptions that are caused by accidents, instead of regular traffic jams. On top of that, this study could be used as a step towards real-time disruption detection, for both public transport and road networks.

Public transport (PT) plays a vital role in commuting billions of travellers in cities all over the world, providing a mode that is both sustainable and accessible. Metro networks are especially apt at this considering their high-capacity and high-speed operation in urban environments. Comparing different metro networks to one another is a suitable manner for transport planners to gain insights into the characteristics of their networks and which areas of improvement exist. In the field of network science, metro networks have been studied extensively in recent decades. While this provided many new insights in the field of network science, the practical relevance for the field of transport science often remained limited. This limited relevance is primarily caused by the lack of realism of the network representations used, not incorporating the actual operation and service that the network provides. As such, this study proposes a comprehensive comparison of metro networks worldwide including service information. This comparison study includes service characteristics in the form of the total travel time indicator for shortest path calculations, which is a combination of the in-vehicle time, waiting time and number of transfers. The median of this total travel time is taken for each network and compared to that of other networks. This metric in turn is contrasted with network- and city-related characteristics in order to explore relations between these factors and to explain the patterns discovered. From this analysis, it is revealed that the travel time increases with network size. The indicator that is especially apt at explaining the differences in total travel time between networks is the number of stations combined with the average direct station distance. The total travel time methodology applied in this study shows significantly different results to other commonly used methods that rely only on in-vehicle time or hops to calculate shortest path travel times. The waiting time turns out to be the main contributor to these significant differences. Future studies can expand on this by considering other network science indicators and looking further into local indicators. In addition, the methodology could be expanded with more detailed transfer information and other PT modes.

E-bike sharing has gradually gained popularity in recent years, while the research in this field is still quite limited. This study applies data-driven methods, mainly demand pattern analysis, to facilitate the development of operational strategies in a cost-effective and operator-friendly way. Demand pattern is analysed in an innovative spatial analytical unit, overlapping circle, which is proven to achieve more beneficial effects than the traditional units (i.e., the administrative units), and hourly clustering is conducted to derive the reallocation strategies by mitigations of imbalance in supply and demand in recurrent hourly clusters. Additionally, this work constructs several indicators to evaluate the strategies in a real-life context, taking both the operator and the users into account. The proposed methodology is applied in a case study, bondi’s e-bike sharing in The Hague with a 4-month time frame from 19-06-2021. There are 5 hourly clusters emerging via agglomerative hierarchical clustering: 1) the first peak hour (16:00-16:59); 2) the second peak hour (17:00-17:59); 3) the first transition hour (18:00-18:59); 4) the second transition hour (19:00-19:59); 5) the off peak (20:00-15:59). The corresponding reallocation strategies are then proposed to alleviate the imbalance in different periods. Additionally, adjustment in the operational areas is suggested by the supply efficiency and trip duration/distance analyses. The results prove that the operational strategies obtained from demand patterns indeed improve the service, with almost 1.5 times ridership, circa 20% decrease in vehicle idle time, compared to the baseline. and a decent monthly net retention rate at around 60%.

A comprehensive understanding of shippers’ preferences can help transport freight forwarders create targeted transport services and enhance long-term business relationships. Nevertheless, limited research examined the benefit of considering shippers’ preferences in the decision-making of synchromodal transport planning and the collection of relevant data is still not straightforward. This research proposes an innovative framework to learn shippers’ preferences in synchromodal transport operations and optimize transport services accordingly. A preference learning method is developed to capture shippers' preferences through pairwise comparisons of transport plans. In order to model the underlying complex nonlinear relationships and detect heterogeneity in preferences, artificial neural networks are employed to approximate shippers' utility for a specific plan. Based on the learned preference information, a synchromodal transport planning model with shippers’ preferences (STPM-SP) is proposed, with the objectives of minimizing the total transportation cost and maximizing shippers’ satisfaction. An Adaptive Large Neighborhood Search algorithm is developed for solving this optimization problem. This algorithm takes into account the two different objective functions and searches for Pareto solutions to the planning problem. A case study is conducted based on the European Rhine-Alpine corridor to demonstrate the feasibility and effectiveness of the proposed methodological framework. Basic discrete choice models, binary logit models, are used as benchmarks for preference learning and the synchromodal transport planning model without preferences (STPM) is used as the benchmark for planning. The results show that the proposed preference learning method has better predictive power than the baseline model, achieving higher accuracy and lower variation. With the consideration of shippers’ preferences, STPM-SP can significantly increase shippers' satisfaction with transport services. Scenarios with different types of preferences are tested and results show that the average of maximum improvements in satisfaction reached 37.76%. This research contributes to learning shippers' preferences in the transport operation process and highlights the importance of incorporating these preferences into the decision-making process of synchromodal transport planning.

Accurate and trustworthy short-term traffic prediction is crucial in the modern world for the comfort of drivers and decision-makers as it is used to improve the performance of traffic management systems, lessen congestion, increase safety, and shorten journey times. It is possible to discover useful information for network transportation planning, such as forecasting demand, finding bottlenecks, and prioritizing infrastructure improvements, by concentrating on network-wide traffic prediction. Scholars have developed a variety of methods that can be generally divided into model-based and data-based methods in order to accurately predict network-wide traffic. However, while studies have demonstrated the capability of deep learning methods, particularly convolutional neural networks (CNNs), in predicting traffic states, the complex nonlinear spatial and temporal traffic characteristics, the time-consuming model creation and training, and the unexplained methodology and predictions continue to pose challenges to the task. This thesis seeks to address these issues by analyzing how deep neural networks identify spatiotemporal traffic patterns for network-wide traffic predictions. To this end, a hybrid CNN-RNN model utilizing a pretrained Inception ResNet v2 feature extractor and a long short-term memory encoder-decoder is constructed to forecast network traffic speeds. A pretrained Inception ResNet v2-based image classifier is built based on the predictions to identify traffic patterns, and Grad-CAM is used to explore how the model identifies them. A freeway network in Amsterdam, Netherlands, is used as a case study. While it is expected that the hybrid CNN-RNN model can give comparable performance to the state-of-the-art methods, e.g. the DGCN proposed by Li et al., results indicate that it cannot fully capture the dynamic characteristics of the traffic, nor can it accurately provide predictions. The image classifier failed to identify the distinct traffic patterns as well, despite Grad-CAM's success in indicating locations with rapid changes of values. Overall, the findings highlight the influence of inductive bias on deep learning models, and the importance of fine-tuning and model-data compatibility. Although further research is required, the conclusions are still beneficial to make informed decisions when choosing appropriate models for future network-wide traffic speed prediction tasks.

Moving block signalling promises a significant reduction of the infrastructure occupation compared to a fixed block system, such as NS’54/ATB. This is mainly caused by a strong reduction of the approach and running time. However, to assess the capacity gains track occupation data, such as blocking times are needed. ETCS L3 Moving Block is still in development, so gathering data out of daily operations is not possible. Also gathering moving block data out of simulation isn’t always a convenient solution. For example, in simulation software FRISO, used at ProRail, ETCS L3 Moving Block is not (yet) implemented. With infrastructure data, rolling stock parameters and planned time-distance data, blocking times for a moving block signalling system can be estimated. The model presented in this thesis has an average error of 0.87s to the blocking time. In 95% of the cases the error is within a range of (-3,3) seconds. Given that ProRail plans with a precision of 6 seconds, it can be concluded that the model both precise as accurate. With the blocking times of all trains, bottlenecks in both railway corridors and complex nodes can be identified. One could sum all blocking times per block and consider blocks with the highest summed blocking times as bottleneck. However, this can only be applied for homogeneous traffic situations. Another approach is identifying bottlenecks by the shortest buffer time between two trains, also called a critical block. This can be applied for both homogeneous as heterogeneous traffic situations. An advantage is that it is not needed to split corridors into line sections. One could analyse a whole network at once and identify bottleneck at a microscopic level. By keeping the same timetable, the buffer time between two trains increases on average by 75 seconds (60%) using moving block over NS’54.

To address the increasing passenger demand in the coming years and make public transport less crowded and delayed, insights into predicted passenger flow are needed. A wide range of studies has used and validated that smart card data can be one of the sound bases for predicting short-term passenger demand. However, it also has several disadvantages, such as the relatively long collection time, the insufficiency to reflect the relationship between passenger behavior and ridership. Trip planner data, which emerged as a type of real-time transit information, could reduce the perceived waiting time of passengers and increase the transit ridership due to the improved satisfaction. Combining these two types of data could potentially cater to the interest of operators in matching the vehicle supply and passenger flow demand at an operational level. Our results show that it is novel and useful to incorporate trip planner data in short-term ridership prediction, however, entirely based on this kind of data would be inaccurate. Random Forest Regression outperforms the other six models that we have selected. The request-related features (variables) can take up 20% of the importance of short-term ridership prediction.

In this thesis, the functioning of passenger delay-based refund schemes in urban public transportation settings is evaluated, such as metros or light-rails. These are used when a passenger encounters a delay on their trip, in order to grant a form of refund to them. To the best of knowledge, no research has been carried out yet on several aspects of these refund schemes, such as which design considerations can be taken into account upon establishing one, or how their performance can be evaluated. To clarify these issues, the state of the practice is reviewed by surveying the internet and the information that is being provided by the individual public transport operators. By categorising this information, it can be established what the design aspects of these refund schemes are. These are the delay type such as departure or arrival delay, the delay threshold, i.e., the minimum delay from which a trip taken is elegible for a refund, the refund type, which is the form of refund that the passenger receives, and the possibility for alternative transport to be refunded. In order to determine whether there could be a form of linearity between delays and refunds, and to facilitate the evaluation of different refund schemes, a regression analysis was carried out on approximately a year of passenger trip data and vehicle data from the Washington Metro. This enabled acquiring more reliable, i.e., excluding individual passenger’s possibly erroneous behaviour, observations of the departure delay and arrival delay of every trip taken during this study period. Using this data, a possible link between the total amounts of delays encountered and refunds granted per day was analysed. It could be concluded that there is indeed a strong linear effect between these two. Furthermore, a number of key performance indicators (KPI’s) was established which allowed to assess the performance of a set of synthetic refund schemes, in which the parameters were varied that resulted from the aforementioned survey. Furthermore, a refund scheme was recreated that uses the general punctuality on a line and subsequently refunds all travelers that can have been expected to be effected by a possible drop in this punctuality. Using these KPI’s, conclusions could be drawn on the performance of different refund schemes, in the sense of how many refunds per trip are granted, how the ratio of the average delay of all refunded trips vs. the average delay of all trips is, how many revenue losses the refund schemes yield for the operator, and how much of the time losses (using a certain Value of Time) are compensated for.

Inaccurate truck cycle time (TCT) prediction in earthworks impacts construction projects because more equipment and human resources must be added to complete the project. It also increases fuel consumption and emissions from the machinery. However, the current method gives inaccurate prediction because of subjectivity and human error. This research aims to utilize the historical data for improving the accuracy of TCT prediction in earthworks. Two historical data are explored, such as manual and automated data provided by BAM, using a machine learning approach in which regression techniques: Multi Linear Regression (MLR), Support Vector Regression (SVR), and Artificial Neural Network (ANN). The result concluded that automated data could develop predictive models because of its quality and variance. ANN develops most predictive models with feature combination one or two, where is distance is the important feature. The benefits of the predictive model are analyzed by comparing them with the traditional method in predicting truck cycle time. The models are more accurate in predicting truck productivity and have lower inefficient truck cycle time than the traditional method. The reduction of inefficient truck cycle time can reduce the cost for fuel and drivers, fuel emission. Models also have intangible benefits to stakeholders, such as gaining partners trust and a better strategic plan to complete the project. In conclusion, the historical data can improve the prediction accuracy of TCT and give benefits to stakeholders. And practitioners are suggested to raise awareness about the importance of data and improve earthmoving documentation for better predictive models.

With the electrification in freight transportation, fast-charging facilities are crucial to support enroute charging for long-distance freight trips. The goal of this study is to develop an integrated fast-charging facility planning framework to prepare for the increasing enroute freight charging demand in the Netherlands. Based on highway traffic data, the travel temporal and spatial patterns of general traffic flow and freight flow are extracted and analyzed comparatively. The charging demand is derived from freight traffic data, and network evaluation based on graph theory is used to identify traffic nodes with significance in highway networks. A candidate selection method is proposed to obtain potential deployment locations for charging stations and to-go chargers. On this basis, a multi-period bi-objective optimization model with minimum investment cost and maximum demand coverage is proposed to find optimal solutions for charging facility planning. The case study is formulated based on the Amsterdam highway network. The results show that the proposed model can leverage the potential of early investment to increase the final demand coverage in the last planning horizon.

To analyze latent multiple specific patterns in the line-based public transport daily delay occurrence, a data-driven explorative analysis of public transport daily delay spatial-temporal distribution pattern is performed based on the k-means clustering algorithm. Firstly, we used aggregated daily delay profile to visualize how the delay is distributed in space and time. And the pattern of daily delay distribution is represented by the image features. Secondly, the image features are extracted by the pre-trained neural network ResNet50, and the output image feature vector are used for implementing unsupervised k-means clustering algorithm. Finally, the k-means clustering results reveal five different daily delay patterns. The distinctive characteristics of these five delay patterns are analyzed and lead to some significant results, which could provide public transport operators with a better understanding of how delays occur on a specific line.

This research explored two types of models, ARIMA and multiple linear regression, for forecasting tourist counts in 7 locations around Amsterdam red light district, for the prediction horizon of up to 30 minutes.

On-demand transit has become a common mode of transport with ride-sourcing companies like Uber, Lyft, Didi transforming the way we move. With the increase in popularity for such services, the supply needs to adapt according to the demand. For this, the demand needs to analyzed to examine if there are recurrent patterns in them; making it predictable and easily manageable. The identified demand patterns can then be used for optimized fleet management. In this paper, we propose three steps for extracting such demand patterns from travel requests (1) constructing the origin-destination zones by spatial clustering (2) calculating the hourly origin-destination matrix for each day, and (3) temporal clustering to extract the dynamic demand patterns. We demonstrate the three step approach on the open-source Didi taxi data. The data is composed of 1 month (November 2016) of travel requests data from a small area in Chengdu, China with approximately 200 000 rides for a single day on average. It can provide insight into the day-to-day regularity and within-day regularity of the demand patterns in Chengdu.