AI Case Study
Seattle is identifying collision patterns and factors that contribute to higher levels of injury severity
DataKind, Microsoft and the City of Seattle collaborated to demonstrate how a solution based on predictive analytics and machine learning can aid at reducing road accidents and easing traffic. The DataKind team applied the exposure model capability, which estimates the total volume of road users using analytics and machine learning, to then be able to focus on bicycle and pedestrian safety issues. The models were able to identify patterns of collision and factors associated with higher levels of injury severity, such as crosswalks effectiveness.
Public And Social Sector
"Using Seattle’s collision, roadway traffic, exposure data and environment characteristics, the DataKind team developed models to uncover collision patterns involving pedestrians or bicyclists and determined the extent to which contributing circumstance and street design are correlated with collision rates, as well as the severity level of specific types of crashes. The team also applied the methodology developed for their work with New York to calculate exposure or total traffic volume citywide for Seattle.
By incorporating incident-specific information such as time of day, weather, lighting conditions and behavioral aspects, the team was also able to further develop a crash model to evaluate elements that may contribute to crashes at intersections and to what extent driver behavior, road conditions and street design played a role.
The DataKind team was able to determine several variables that had the greatest impact on mid-block collisions — traffic volume, land use, number of traffic lanes, street width and pedestrian concentration were the most demonstrative inputs associated with collisions."
"While Seattle has seen a 30 percent decline in traffic fatalities over the last decade, traffic collisions are still a leading cause of death for Seattle residents age 5 to 24. Older adults are also disproportionately affected, so this trend could grow as the population ages. To supplement the findings of the City’s Bicycle and Pedestrian Safety Analysis project and provide policy makers and engineers with actionable information for developing and implementing interventions, Seattle sought to find out what mid-block street designs are most correlative with collisions involving vulnerable roadway users and what the probability of such collisions occurring is at identified locations."
"It was found that the fact of whether a motor vehicle is making a right turn or left turn at a given intersection will influence the severity of the collision. Researchers were also able to identify in which months of the year incidences of crashes appeared to be better or worse. Interestingly, the number of crosswalks was found to be significant and that more crosswalks at an intersection showed reduction in the severity of crashes.
With these insights, Seattle will be able to pinpoint high risk areas and the factors that can be addressed to help reduce future crashes. The city recently passed a levy to fund multi-modal transportation improvements city-wide and the results from this project, along with additional safety studies, will help guide more than $300 million in Vision Zero investments over the next nine years."
"Knowing the total volume of road users or “exposure” is necessary to understand the true rate of crashes, but most cities don’t have this data available. To overcome this, the team designed an innovative exposure model that can accurately estimate traffic volume in streets throughout the city. The model has two main components. The first is an algorithm that propagates traffic counts on a single street segment to adjacent street segments. It assumes that traffic on one city block is very similar to traffic on adjacent blocks. This process can be run many times and allows one to widely propagate traffic count values along neighboring streets. However, some streets may not have any nearby traffic counts available, so the second component of the model is a machine learning model, with high predictive accuracy, that predicts traffic volumes on streets based on their characteristics."
Seattle’s collision, roadway traffic, exposure data and environment characteristics