Vulnerable road users (VRUs) represent a large portion of fatalities and injuries occurring on European Union roads. It is therefore important to address the safety of VRUs, particularly in urban areas, by identifying which factors may affect the injury severity level that can be used to develop countermeasures. This paper aims to identify the risk factors that affect the severity of a VRU injured when involved in a motor vehicle crash. For that purpose, a comparative evaluation of two machine learning classifiers—decision tree and logistic regression—considering three different resampling techniques (under-, over- and synthetic oversampling) is presented, comparing both imbalanced and balanced datasets. Crash data records were analyzed involving VRUs from three different cities in Portugal and six years (2012–2017). The main conclusion that can be drawn from this study is that oversampling techniques improve the ability of the classifiers to identify risk factors. On the one hand, this analysis revealed that road markings, road conditions and luminosity affect the injury severity of a pedestrian. On the other hand, age group and temporal variables (month, weekday and time period) showed to be relevant to predict the severity of a cyclist injury when involved in a crash.

Urban mobility accounts for 38 and 19% of nitrogen oxide (NO_x) and particulate matter (PM) emissions at European urban areas, respectively. Despite of all the technological development around automobile industry, urban areas are still facing problems related to exposure to high levels of air pollutants. Increasing the accuracy of both emissions and air quality modelling from road traffic is a key-issue for the management of air pollution in road transport sector. This study assessed the influence of using different road traffic emission models on the accuracy of air quality modelling with street-level resolution, having as a case study an urban area located on the centre region of Portugal. Two emission models, with different complexity levels regarding the ability to characterise the traffic dynamics were analysed, namely, transport emission model for line sources (TREM) and vehicle-specific power (VSP), based on data obtained in an experimental campaign. To perform the air quality simulations, the pollutant dispersion in the atmosphere under variable wind conditions (VADIS) model was used and two pollutants were analysed: NO_x and PM10. The results showed that the magnitude of PM10 and NO_x concentrations were result of a conjoint influence of traffic dynamics and meteorological conditions. Comparison between measured and modelled data showed that the VADIS model could track the evolution of NO_x levels, for both emission models considered, displaying a high correlation (> 0.8) between traffic-related NO_x emissions and NO_x concentrations. For PM10, VADIS model is more sensitive to the differences in the emissions calculation; however, it was observed that the traffic-related PM10 emissions accounts 1.3–8.4% to the PM10 concentration levels at the study area.

Urban area’s rapid growth often leads to adverse effects such as traffic congestion and increasing accident risks due to the expansion in transportation systems. In the frame of smart cities, active modes are expected to be promoted to improve living conditions. To achieve this goal, it is necessary to reduce the number of vulnerable road users (VRUs) injuries. Considering injury severity levels from crashes involving VRUs, this article seeks spatial and temporal patterns between cities and presents a model to predict the likelihood of VRUs to be involved in a crash. Kernel Density Estimation was applied to identify blackspots based on injury severity levels. A Multinomial Logistic Regression model was developed to identify statistically significant variables to predict the occurrence of these crashes. Results show that target spatial and temporal variables influence the number and severity of crashes involving VRUs. This approach can help to enhance road safety policies.