SYSTRA has exploited datasets and performed analysis to help the UK’s Department for Transport (DfT) identify and prioritise road collision causes, combining analysis and cutting-edge technology.
A combination of statistical analysis, geospatial analysis and innovative machine learning* techniques were applied to highlight the circumstances and contributory factors that lead to death and serious injury on roads in Great Britain and determine the key components affecting the outcome of reported collisions.
Fine-tuning data
More specifically, the machine learning* techniques were applied to correlate collision data with detailed mapping information (OpenStreetMap and OS MasterMap), allowing exploration of relationships between collisions and the physical environment.
The key findings were that most collisions occur in densely populated areas, however fatal and serious collisions are more commonly observed on rural roads. The most vulnerable road users in these rural areas are motorcyclists or pedal cyclists.
A clear view of results
An interactive StoryMap was delivered to visualise the project outcomes, highlighting problematic areas and demonstrating the value of maps to assist in decision making.
*Machine learning is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalise to unseen data and thus perform tasks without explicit instructions.