Road traffic crashes are on the rise worldwide, particularly in African countries. Rwanda, in this context, faces the challenge of an increasing frequency of crashes each year. Kigali, the capital city of Rwanda, witnesses over three-quarters of the total population as daily road users, leading to high traffic volumes and congestion during peak hours. Identifying dangerous locations and providing insights to transport policymakers is crucial to minimise the severity of crashes in the city. This study focuses on identifying crash hotspots through spatial analysis and explores the various factors contributing to crash severity in the capital city of Rwanda. The study utilises crash data recorded between 2015 and 2022 by the Rwanda National Police, conducting temporal, spatial, and statistical analyses. A multinomial regression model was employed to examine the significance of contributing factors to crash severity. Additionally, six supervised machine learning classifiers were employed to assess their predictive capabilities for accident severity in Kigali city. The findings indicate that the Gasabo district recorded the highest number of crashes among all districts. Time series analysis reveals a decrease in fatal accidents from 2020 to 2022 in Kigali city, while the number of injury and property damage crashes progressively increased from 2019 to 2022. Among the predictive models, the Random Forest model demonstrated strong predictive abilities, achieving an accuracy of 88.11% compared to other models. These results provide valuable insights for road safety policymakers to proactively make decisions and take precautions to prevent crashes before they occur.
Read full abstract