Network-Based Highway Crash Prediction Using Geographic Information Systems

The objectives of this project are to estimate network-based crash prediction models that will predict the expected crash experience in any given geographic area as a function of the highway link, intersection and land use features observed in the area. The result will be a system of Geographic Information Systems (GIS) programs that permit a polygon to be drawn on a map, or a set of links and intersections to be selected, and then predict the number of crashes expected to occur on the selected traffic facilities. These expected values can then be compared with observed values to identify locations that are particularly dangerous and require attention for improving safety. Alternatively, this tool could be used to estimate the safety impacts of proposed changes in highway facilities or in different land development scenarios. Another project objective is to demonstrate the value of the resulting system in helping planners and engineers to consider road safety when conducting transportation and land use planning and design and policy-making. This will be done by presenting and demonstrating the resulting model system at a workshop given to each of the New England State Departments of Transportation (DOT's). The particular novelty with the approach is that land use data by zone is used for accident prediction models for roads on a link level. The land use is used for enhancing the estimates of exposure to accidents by taking into account the amount of traffic that can be expected in and out of areas, exiting and entering the state routes for which the models are developed.

  • Record URL:
  • Supplemental Notes:
    • This research was funded by the U.S. Department of Transportation, University Transportation Centers Program.
  • Corporate Authors:

    New England Transportation Consortium

    C/O Advanced Technology and Manufacturing Center
    University of Massachusetts, Dartmouth, 151 Martine Street
    Fall River, MA  United States  02723

    University of Connecticut, Storrs

    Department of Civil and Environmental Engineering, 261 Glenbrook Road
    Storrs, CT  United States  06269-2037
  • Authors:
    • Ivan, John N
    • Garder, Per E
    • Bindra, Sumit
    • Johnson, B Thomas
    • Shin, Hyeon-Shic
    • Deng, Zuxuan
  • Publication Date: 2007-6-6


  • English

Media Info

  • Media Type: Print
  • Edition: Final Report
  • Features: Appendices; Figures; References; Tables;
  • Pagination: 82p

Subject/Index Terms

Filing Info

  • Accession Number: 01076724
  • Record Type: Publication
  • Report/Paper Numbers: NETCR67, NETC 04-5
  • Files: UTC, TRIS
  • Created Date: Sep 10 2007 11:43AM