Abstract

Traffic congestion is a severe problem in urban areas and it leads to the emission of greenhouse gases and air pollution. In general, drivers lack knowledge of the location and availability of free parking spaces in urban cities. This leads to people driving around searching for parking places, and about one-third of traffic congestion in cities is due to drivers searching for an available parking lot. In recent years, various solutions to provide parking information ahead have been proposed. The vast majority of these solutions have been applied in large cities, such as Beijing and San Francisco. This thesis has been conducted in collaboration with Knowit and Dukaten to predict parking occupancy in car parks one hour ahead in the relatively small city of Linköping. To make the predictions, this study has investigated the possibility to use long short-term memory and gradient boosting regression trees, trained on historical parking data. To enhance decision making, the predictive uncertainty was estimated using the novel approach Monte Carlo dropout for the former, and quantile regression for the latter. This study reveals that both of the models can predict parking occupancy ahead of time and they are found to excel in different contexts. The inclusion of exogenous features can improve prediction quality. More specifically, we found that incorporating hour of the day improved the models’ performances, while weather features did not contribute much. As for uncertainty, the employed method Monte Carlo dropout was shown to be sensitive to parameter tuning to obtain good uncertainty estimates.

Abstract

Site characterisation necessarily relies on engineering judgement, usually combined with some level of statistics to define characteristic values for design purposes. A suitable method for this task is quantile regression, which allows for the definition of lower, upper, and best-estimate characteristic values. The application of quantile regression to homogeneous profiles is relatively straightforward. Although such sites are common in some areas, there is need for a more comprehensive approach to quantile regression that covers the more general scenario of heterogeneous stratified profiles. This paper takes piezocone penetrometer data from a relatively complex seabed site and demonstrates the streamlined application of quantile regression, highlighting and analysing some of the assumptions and choices behind the approach. The work shows the nuances of the method and suggests workarounds for potential scenarios where its application may be challenging.