Accident prediction models in urban areas: Lisbon case study

Abstract

This paper on the use of accident prediction models in urban areas is from the proceedings of 14th international Conference on Urban Transport and the Environment in the 21st Century, which was held in Malta in 2008. The authors present a case study in Lisbon, Portugal, to demonstrate the use of an accident prediction model. They stress that in order to develop an efficient and affective strategy towards road safety, administrators must have the proper tools for the quantification of safety levels and the explicit consideration of safety issues in the road management process. Accident prediction models are mathematical functions that describe the relation between the road safety and explanatory variables, such as traffic, road length, and carriageway width, number of intersections, etc. Accident prediction models for intersections include traffic volume and pedestrian data. Accident prediction models can be adapted to the urban context where they are applied, and supplemented by the use of a Geographic Information System (GIS) based methodology to analyze spatial patterns of road accidents. The authors discuss accident prediction models applied to urban areas and the use of data collected on road accidents, road infrastructure characteristics and traffic and land use information. The authors briefly describe the GIS Accident database that is currently in construction for the city of Lisbon (covering 2003 - 2007).