DC9. AI for road safety monitoring and crash prediction from micro- to macro levels



  • To investigate the effect of spatial scale on road safety monitoring and crash prediction
  • To develop a new art AI framework to observe and analyse road safety KPIs and predict crashes by achieving transition from smaller scales (e.g., on a segment, intersection or neighbourhood level) to larger ones (e.g., highway corridor or prefecture/county level), taking into account the time dimension
  • To assess the effectiveness and scalability of microscopic road safety models for macroscopic crash prediction and vice versa

Expected results:

  • Evaluation of several scaling combinations that will also feature capabilities of ‘zooming in/zooming out’ of study areas using different levels of telematics (e.g., trip-based, driver-based or network-based using several drivers)
  • Knowledge on comparable advantages and disadvantages for each analysis scale
  • A case study utilising driver telematics in an urban area, with actionable results, compatible with the vision and activities of OSeven – showcasing the impact of using AI for micro-analysis based on driver telematics and integrating the findings to larger scales

Planned secondment(s):

  • EIRA-SI, Purpose: to test the developed methods on additional datasets and countries, with an emphasis on transferability techniques