Search

Abstract Background Road safety remains a critical concern in Europe’s transport sector. In urban areas, where 40% of total road fatalities occur, pedestrians are particularly vulnerable, since according to road safety data accidents involving a pedestrian are 2.8 and 15 times more probable to be fatal than in rural areas and motorways respectively. In line with the Vision Zero concept and the European Commission’s directives, many EU members are taking steps to improve road safety. Accordingly, the identification of the key factors behind pedestrian accident occurrence and pedestrian accident severity in urban areas is ever more relevant. Methodology The proposed methodology employs traditional logistic regression models and artificial neural networks, using accident data from Berlin, Germany, sourced from the Berlin Open Data portal. The dataset comprises information on 3,257 accidents involving pedestrians in 2018 or 2019, including details about involved vehicles, accident details, and injury severity information. Additionally, the dataset was augmented with average network speed data from Uber Movement and road network information from Geographic Information System (GIS) applications. Results Formal analysis results indicated several factors as significant to accident severity, such as involvement of bicycle or heavy vehicles, lighting conditions, speed limit and accident type. Additionally, a comparison between modelling approaches shows a clear performance advantage of ANNs over statistical models. Research findings provide insight for various stakeholders working to enhance pedestrian safety in urban areas.