Authors: Khaula Alkaabi*, United Arab Emirates University
Topics: Transportation Geography, Geographic Information Science and Systems, Spatial Analysis & Modeling
Keywords: GIS, Hotspot Map, Statistical Approach, Spatial Autocorrelation, Getis Ord Gi* statistic, UAE, USA
Session Type: Paper
Start / End Time: 12:40 PM / 2:20 PM
Room: Marriott Ballroom Salon 3, Marriott, Lobby Level
Presentation File: No File Uploaded
This study presents a Geographical Information System (GIS) statistical approach on spatial autocorrelation analysis for traffic accidents occurring in Abu Dhabi City, UAE and Dallas City, Texas, USA for the period 2014-2015. Crash Count data acquired through various official sources are used for analysis and ranking. Getis Ord Gi* statistic is used to identify the clustering of low and High index values and to generate an accidental risk hotspot map. As many earlier studies related to hotspot analysis for traffic accident identified a strong correlation between various factors such as speed, road condition, driver behaviour, population density, car density and many more. This study focused on evaluating traffic accident and validating the hypothesis stating that most traffic accident in a city occurs near central business areas. Two similar cities (Abu Dhabi, UAE; and Dallas, USA) are taken for analysis which is nearly equal in area size, population, number of accidents, standard of living. The approach is evaluated using crash data available in 2014 for both cities. Analysis results show that the hypothesis is correct, and the approach is efficient and reliable in identifying the vehicle crash hotspots near the central business area and ranked accordingly.