STRIDE Researchers Developing GIS-based Tool for Teaching Crash Prediction Methods to Transportation Professionals

Dr. Ilir Bejleri and Dr. Siva Srinivasan of the University of Florida, are in the process of developing an instructional tool that uses Geographic Information Systems (GIS) to predict crashes on roads using methods of the Highway Safety Manual (HSM).  The purpose of this tool is to train current and future professionals on the underlying theory behind these methods so they can run analysis of streets that have potential traffic safety issues and create countermeasures for addressing them.

The tool is conceptualized as an integral part of a GIS crash database for the state of Florida called Signal Four Analytics. This database contains crash-type distributions, traffic volume, and roadway geometry information for selected segments and intersections. The research team is working on coding the appropriate Safety Performance Functions that estimate crashes and Crash Modification Factors that show the effects of various countermeasures to reduce crashes.

The tool includes self-instructing modules that provide step-by-step guidance for segment and intersection level analyses.  They can be used by students independently or in the context of a course or as a webinar for practitioners. These tutorials use real world data from Florida. The GIS environment will facilitate the students appreciating the context in which the data are obtained and methods applied, thereby leading to improved understanding of the methods. Since the software is web-based, these can be accessed and used easily by anyone outside Florida. The image below shows the interface of Signal Four Analytics showing streets and crashes with interactive views.


The project directly contributes to enhancing the goals of transportations safety within Region 4 (Southeast) of the U.S. In the long term, the software will lead to improvements in data and methods, which in turn, would translate into better predictive capabilities.

The instructional module is conceptualized to allow incorporation of the full crash prediction feature in the Signal Four Analytical system in order to support the needs of researchers and practitioners in their traffic safety improvements efforts.

For more information, contact Dr. Ilir Bejleir at ilir@ufl.edu.