Urbanization has caused a historical transformation at a global scale, and humanity is moving towards a fully connected society where cities will concentrate population, infrastructure and economic activity. A key element in the cities’ infrastructure is the transportation system, as it facilitates the mobility of people and goods. Transportation systems are constantly generating data from, e.g., GPS, sensors and cameras, and the statistical modeling is challenging due to the complex structure and dynamics of the system, and the inherent uncertainty. In this thesis, we develop Bayesian models with applications to transportation. We specifically focus on models that can be trained on spatiotemporal data coming from transport networks to make predictions on, e.g., bus delays or the actual network topology. Special attention has been given to model scalability issues and uncertainty quantification. We have used real-world data from transportation systems in every study to keep a balance between statistical rigor, novelty, and applicability. 

The thesis consists of four papers. The first study presents a state-of-the-art probabilistic latent network model to forecast multilayer dynamic graphs. The model uses stochastic blockmodeling to reduce the computational burden, and is illustrated on a sample of 10-year data from four major airlines within the US air transportation system. In the second paper, we develop a robust model for real-time bus travel time prediction that departs from Gaussian assumptions by using Student-t errors, and show how Bayesian inference naturally allows for predictive uncertainty quantification in a highly stochastic environment. Experiments are performed using data from high-frequency buses in Stockholm, Sweden. The third paper shows the potential of multi-output Gaussian processes to tackle network-wide travel time prediction in an urban area. We develop a responsive online model based on a coregionalized covariance and test its accuracy on real data from GPS-equipped taxis. Finally, we propose a novel regularization strategy for the vector autoregressive model that is based on a graphical spike-and-slab prior, and present a case study with real airline delay data to assess its predictive performance and analyze network patterns related to the propagation of delays across airports. 

Urbaniseringen har orsakat en historisk förändring på en global skala, och mänskligheten går mot ett uppkopplat globalt nätverkssamhälle där städer kommer att koncentrera befolkning, infrastruktur och ekonomisk aktivitet. Ett nyckelelement i städernas infrastruktur är transportsystemet, eftersom det underlättar rörligheten av människor och varor. Transportsystem genererar ständigt data från tex. GPS, sensorer och kameror, och den statistiska modelleringen är utmanande på grund av systemets komplexa struktur och dynamik, samt dess naturliga osäkerheter.

I denna avhandling utvecklar vi Bayesianska modeller med tillämpningar för transporter. Vi fokuserar specifikt på modeller som kan tränas på spatiotemporala data från transportnätverk för att göra prediktioner av t ex. bussförseningar eller verklig nätverkstopologi. Särskild uppmärksamhet har ägnats åt modellskalbarhetsfrågor och kvantifiering av osäkerhet. Vi har använt data från riktiga transportsystem i varje studie för att skapa en balans mellan statistisk korrekthet, praktiskt tillämpbarhet och vetenskaplig höjd. Avhandlingen består av fyra artiklar. Den första artikeln presenterar en probabilistisk latent nätverksmodell för att prognostisera dynamiska grafer med multipla lager. Modellen använder stokastisk blockmodellering för att minska beräkningsbördan, och illustreras på ett datamaterial bestånde av tio års data från fyra stora flygbolag inom det amerikanska lufttransportsystemet. I den andra artikeln utvecklar vi en robust modell för realtidsprognoser av bussförseningar genom att använda Student-t fördelning och vi visar hur Bayesiansk inferens ger en naturlig kvantifiering av osäkerhet i en mycket stokastisk miljö. Experiment utförs med hjälp av högfrekventa data från bussar i Stockholm. Den tredje artikeln visar potentialen hos fler-dimensionella Gaussiska processer för att generera nätverksövergripande prediktioner av trafikflöden i en tätortsmiljö. Vi utvecklar en responsiv onlinemodell baserad på en co-regionaliserad kovariansstruktur och utvärderar prognosförmåga på verkliga data från GPS-utrustade taxibilar. Slutligen föreslår vi en ny regularisering av den vektorautoregressiva modellen via en nätverksbaserad variabelsselektionsprior, och presenterar en fallstudie på verkliga data över förseningar i kommersiell flygtrafik där vi utvärderar prediktiv förmåga och analyserar nätverksmönster för hur förseningar sprids mellan flygplatser.  

Dynamic transportation networks have been analyzed for years by means of static graph-based indicators in order to study the temporal evolution of relevant network components, and to reveal complex dependencies that would not be easily detected by a direct inspection of the data. This paper presents a state-of-the-art probabilistic latent network model to forecast multilayer dynamic graphs that are increasingly common in transportation and proposes a community-based extension to reduce the computational burden. Flexible time series analysis is obtained by modeling the probability of edges between vertices through latent Gaussian processes. The models and Bayesian inference are illustrated on a sample of 10-year data from four major airlines within the US air transportation system. Results show how the estimated latent parameters from the models are related to the airlines’ connectivity dynamics, and their ability to project the multilayer graph into the future for out-of-sample full network forecasts, while stochastic blockmodeling allows for the identification of relevant communities. Reliable network predictions would allow policy-makers to better understand the dynamics of the transport system, and help in their planning on e.g. route development, or the deployment of new regulations.

The unscented Kalman filter (UKF) is a method to solve nonlinear dynamic filtering problems, which internally uses the unscented transform (UT). The behavior of the UT is controlled by design parameters, seldom changed from the values suggested in early UT/UKF publications. Despite the knowledge that the UKF can perform poorly when the parameters are improperly chosen, there exist no wide spread intuitive guidelines for how to tune them. With an application relevant example, this paper shows that standard parameter values can be far from optimal. By analyzing how each parameter affects the resulting UT estimate, guidelines for how the parameter values should be chosen are developed. The guidelines are verified both in simulations and on real data collected in an underground mine. A strategy to automatically tune the parameters in a state estimation setting is presented, resulting in parameter values inline with developed guidelines.

In a context of intense airport and airline competition, a few European airports have recently started offering self-connection services to price-sensitive holiday passengers travelling with a combination of tickets where the airline/s involved do not handle the transfer themselves. This paper provides an exploratory analysis of the potential and implications of self-connectivity for European airports and airlines using a case study of air travel routes to holiday destinations in the Mediterranean. With the help of a forecasting model based on a zero-inflated Poisson regression, we identify the airports and airlines that have the highest potential to facilitate self-connections in the selected markets. The results also explore some implications of the widespread development of self-connection services in Europe.

The connectivity provided by full-service network carriers under the umbrella of airline alliances is increasingly challenged by the services of Middle Eastern airlines via their own hubs, and the rise of new passenger strategies like self-connectivity. While these two developments can potentially benefit consumers with more services and lower fares, the rise of Middle East carriers has been met with opposition by EU and US airlines that call for increased protectionism. In addition, only a few airports in the world actively support self-connections. In this context, this study aims to investigate (1) the markets in which Middle East carriers exert a stronger dominance in terms of the number of passenger connections, (2) whether EU, US, or Asian hubs provide a competitive quality of connectivity in terms of travel time, and (3) whether a significant potential for self-connections is hidden at major airports worldwide. To that end, several datasets of passenger bookings (MIDT), airline schedules, and minimum connecting times between 2012 and 2015 are combined in a connections-building methodology that delivers six market-specific airport connectivity indicators for our benchmarking exercise. Our findings show that although European and some Asian hubs have lost traffic in global markets, they remain competitive from a quality perspective. US hubs have maintained their market share and competitive position. Finally, we identify the airports and airlines with the highest potential to provide self-connecting travel options, which can become an attractive new source of revenue for the parties involved.

The paper explores the potential of Multi-Output Gaussian Processes to tackle network-wide travel time prediction in an urban area. Forecasting in this context is challenging due to the complexity of the traffic network, noisy data and unexpected events. We build on recent methods to develop an online model that can be trained in seconds by relying on prior network dependences through a coregionalized covariance. The accuracy of the proposed model outperforms historical means and other simpler methods on a network of 47 streets in Stockholm, by using probe data from GPS-equipped taxis. Results show how traffic speeds are dependent on the historical correlations, and how prediction accuracy can be improved by relying on prior information while using a very limited amount of current-day observations, which allows for the development of models with low estimation times and high responsiveness.

This paper analyzes the vulnerability of the European air transport network to major airport closures from the perspective of the delays imposed to disrupted airline passengers. Using an MIDT dataset on passenger itineraries flown during February 2013, full-day individual closures of the 25 busiest European airports are simulated and disrupted passengers then relocated to minimum-delay itineraries. Aggregate delays are used to rank the criticality of each airport to the network, with the possibility of disaggregating the impact across geographical markets. The results provide useful reference values for the development of policies aimed at improving the resilience of air transport networks.

Government agencies classify airports for different purposes, including the allocation of public funding for capacity developments. In a context of hub classification, determining the contribution of each airport to the national network in terms of the two dimensions of hubbing -i.e., traffic generation and connectivity- is a key aspect. In this regard, the choice of an appropriate connectivity indicator is still an unresolved issue. This paper adapts the well-known flow centrality indicator to an air transport context and develops a novel measure of airport connectivity. An application to the US domestic network is provided, using quarterly data on passenger demand to perform a detailed time-series analysis of airport connectivity patterns between 1993 and 2012. The flow centrality indicator is then used to define an alternative airport classification method within the context of the Federal Aviation Administration’s National Plan of Integrated Airport Systems (NPIASs). Results show that there is potential for improving the existing airport typology by explicitly separating connectivity and traffic generation as classification criteria.

The recent economic downturn led to a significant contraction in the global demand for air travel and cargo. In spite of that, airports’ operating costs did not mirror the traffic trends and kept increasing during the same period, showing evident signs of lack of flexibility. With this background, this paper aims at identifying the drivers of airport cost flexibility in a context of economic recession. This is done by estimating a short-run stochastic cost frontier over a balanced pool database of 194 airports worldwide between 2007 and 2009. Using the total change in cost efficiency during the sample period as a proxy for cost flexibility, the impact of variables such as ownership, outsourcing, airline dominance, low-cost traffic, and revenue diversification is tested in a second-stage regression. Contrary to the existing literature, a higher level of outsourcing is shown to reduce cost flexibility. Results also indicate that low-cost traffic, diversification, and corporatization increase the airports’ ability to control costs. The negative impact of airline dominance suggests the need for more stringent regulations on slot allocation at congested airports in order to ensure optimal infrastructure usage.