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.

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.

This study aims to quantify the impact on the traffic flow performance of different regulation strategies for a centralised route guidance system where road authorities and service providers work together in a coordinated approach. Previous research concentrates on the effect of a centralised route guidance system when every vehicle participates and all vehicles have perfect knowledge of the traffic state. This is not the real case with human drivers and multiple service providers and the impact of cooperation may be limited. This study combines habitual driving behaviour, the effect of the quality of information and a congestion avoiding user optimum algorithm to quantify the impact of a centralised route guidance system. The congestion avoiding user optimum algorithm will add a perceived time penalty to all routes with links above a certain intensity/capacity ratio to avoid choosing the congested route. The cooperation is described by the coordinated approach model of the SOCRATES²·⁰ project. In this model, the cooperation is organised by an intermediary who takes on the management tasks. Because a lack of commitment could be a problem for the success of the system, the services of the intermediary can be regulated with four regulation strategies starting with no regulation to regulation for both service providers and road users. The impact is determined with the dynamic macroscopic traffic model MARPLE. The result shows that without commitment the system does not improve the traffic state. For the maximum potential of the system, it must be fully regulated for both service providers and road users. Although with only the commitment of service providers, there is already a positive impact on the traffic flow and in less complex networks it can already solve all congestion.

Predicting crowd movements in real-time during mass events has been shown to be a complex yet valuable task in order to reduce the risk of overcrowding. The aim of this research is to propose and validate a crowd movement forecasting method for which simulation is performed offline (i.e. prior to the event) but the forecast is done online, in real-time. A number of scenarios is formulated and simulated creating what is called a database of scenarios. In real-time, based on information from the event's crowd monitoring systems, a scenario from this database is then selected which corresponds to the prediction. The research is focused on addressing the concepts related to the two pillars of the method: the formulation of the scenarios to be included in the database, and the operationalization of the system to select a scenario in real-time.

The aim of this master thesis is to develop a dynamic zone-based traffic model for large areas, using the concept of the Network Fundamental Diagram (NFD), which relates the average internal flow (production) and speed in a zone to the number of vehicles in the same zone (accumulation). The model that has been developed is then applied to the Randstad area, and it is analyzed whether the model is able to reproduce the observed congestion patterns and travel times between the zones.

Non-recurrent traffic events, consisting of events of an unpredictable nature such as incidents and vehicle breakdowns, can either directly or indirectly influence road traffic. A better understanding of these events could prove beneficial towards improving a multitude of facets concerning the management of the Dutch road network. Traditional traffic event detection, based on significant changes in traffic flow/speed characteristics, is often limited by sparse road sensor coverage. More importantly, traditional detection methods are unable to categorize and describe traffic events.

The aim of this study is to explore to which extent geosocial data (e.g., data from Twitter and Waze) could enrich traditional traffic data (e.g., traffic speed/flow data), in order to improve the detection, categorization, and description of traffic events in the Netherlands. In order to achieve this, a pipeline was designed for extracting knowledge on traffic events from geosocial data sources. We collected geosocial data from Twitter, Waze, and TomTom and used traffic data provided by DiTTLab. We specifically focused on reports by real road users, which we define as natural persons that report on their own account, therefore excluding all legal person entity accounts such as public/private organizations, and bots. A machine learning approach was applied to automatically classify tweets as either traffic event related or not. In order to categorize tweets into a traffic event category, a rule-based traffic domain annotator was created. Additionally, a geocoding method to link tweets to a geographic location was developed. As Waze and TomTom event reports are classified and geocoded by default, we could cluster these reports together with the processed tweets based on their categorical, spatial and temporal extent into a combined traffic event. These combined traffic event reports were then linked to traffic data, based on corresponding spatial and temporal aspects. In order to present the collected data, a web-based interactive map application was built.

This methodology was applied to data collected over the period from 05-12-2017 to 17-02-2018. From the set of collected tweets approximately 6.71% proved traffic event related. Based on a linear support vector machine classification model we achieved an average f1-score of 0.95 and an accuracy of 0.954, for detecting traffic event-related tweets. The rule-based traffic domain annotator showed an average f1-score of 0.874, and an accuracy of 0.964. The geocoding method proved able to geocode tweets to a location that covers all place indicators in a tweet in 86% of the evaluated cases. The remaining 14% of the tweets either got geocoded to a part of relevant indicators or to no relevant indicators at all. Our clustering approach is able to cluster 39.61% of the event reports into a traffic event report cluster consisting out of more than one event report, from which 48.66% could be linked to traffic data.

All in all, based on the achieved results, this work shows that geosocial data can be used to enrich traffic data towards the improvement of the detection, categorization, and description of non-recurrent traffic events.

A Master Thesis Research to determine the effects various demand distributions and operational cost functions have on the evolution and shape of a monocentric metropolitan transport network using a conceptual model, evaluated using network indicators.