This paper deals with traffic accident analysis using Geographic Information System (GIS) and Python for identifying traffic accident hotspots as well as for determining the primary parameters affecting the severity of the accidents. The methodology is demonstrated for traffic accidents in the Des Moines city, Polk county of Iowa State, USA. Crash locations are geo-coded using Geographic Information System (GIS). The Kernel density estimation method is applied to locate the crash hotspots. Five hotspots are identified for accidents that result in injury as well as for those resulting only in property damage. Subsequently, feature selection is performed using Python to identify the parameters primarily affecting the severity of the accidents. The top three features relevant to the severity level are determined using chi-square statistic. It is found that the top three features affecting the severity level of accidents are—the type of intersection/interchange at the location of accident, surface condition at the time of accident and the object with which the vehicle collided during the accident. The methodology and results from this study could be utilized for decisions on incorporating traffic safety measures with optimum resource allocation.
Spatial Statistical Analysis of Traffic Accidents Using GIS and Python for Optimum Resource Allocation
Lecture Notes in Civil Engineering
International Conference on Advances in Civil Engineering ; 2020 May 28, 2020 - May 29, 2020
2021-12-15
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
An Analytical Study of Traffic Accidents in Connecticut, USA Using Python
Springer Verlag | 2024
|A Statistical Analysis of Traffic Accidents Causes in Iraq
British Library Conference Proceedings | 1998
|