Journal of Geographic Information System, 2021, 13, 98-121
https://www.scirp.org/journal/jgis
ISSN Online: 2151-1969
ISSN Print: 2151-1950
DOI: 10.4236/jgis.2021.132007 Mar. 15, 2021 98 Journal of Geographic Information System
GIS-Based Methodology for Crash Prediction on
Single-Lane Rural Highways
Márcia Macedo
1*
, Emilia Kohlman Rabbani
1
, Maria Maia
1
, Marlos Macedo
2
,
Bianca Ferreira
3
1
Post-Graduate Program in Civil Engineering, UPE, Recife, Brazil
2
Post-Graduate Program in Systems Engineering, UPE, Recife, Brazil
3
Graduate Program in Architecture and Urban Planning, UNICAP, Recife, Brazil
Abstract
Due to the need to update the current guidelines for highway design to focus
on safety, this study sought to build an accident prediction model using a
Geographic Information System (GIS) for single-lane rural highways, with a
minimum of statistically significant variables, adequate to the Brazilian reali-
ty, and improve accident prediction for places with similar characteristics. A
database was created to associate the accident records with the geometric pa-
rameters of the highway and to fill in the gaps left by the absence of geometric
highway plans through geometric reconstitution or semi-automatic extrac-
tion of highways using satellite images. The Generalized Estimating Equation
(GEE) method was applied to estimate the coefficients of the model, assum-
ing negative distribution of the binomial error for the count of observed ac-
cidents. The accident frequency and annual average daily traffic (AADT)
were analyzed, along with the spatial and geometric characteristics of 215 km
of federal single-lane rural highways between 2007 and 2016. The GEE pro-
cedure was applied to two models having three variations of distinct homo-
geneous segmentation, two based on segments and one based on the kernel
density estimator. To assess the effect of constant traffic, two more variations
of the models using AADT as an offset variable were considered. The predo-
minant correlation structure in the models was the exchangeable. The prin-
cipal contributing factors for the occurrence of collisions were the radius of
the horizontal curve, the grade, segment length, and the AADT. The study
produced clear indicators for the design parameters of roadways that influ-
ence the safety performance of rural highways.
Keywords
Roads, GEE, Single-Lane Rural Highways, GIS, Crash Prediction
How to cite this paper: Macedo, M., Rab-
bani, E.K., Maia, M., Macedo, M. and Fer-
reira, B. (2021) GIS-Based Methodology for
Crash Prediction on Single-Lane Rural
Highways. Journal of Geographic Informa-
tion System, 13, 98-121.
https://doi.org/10.4236/jgis.2021.132007
Received: February 17, 2021
Accepted: March 12, 2021
Published: March 15, 2021
Copyright © 2021 by author(s) and
Scientific Research Publishing Inc.
This work is licensed under the Creative
Commons Attribution International
License (CC BY 4.0).
http://creativecommons.org/licenses/by/4.0/
Open Access