Spatial autocorrelation analysis of cargo trucks on highway crashes in Chile.

Pattern of road traffic crash hot zones versus probable hot zones in Tunisia: A geospatial analysis.

Reducing road traffic accidents (RTA) and their socioeconomic costs is an increasingly important priority in many countries. In recent years, many authors have proposed various approaches to analys...

Spatial analysis of road traffic accident hotspots: evaluation and validation of recent approaches using road safety audit

Accidents are distressing experiences which affect physical, psychological, and social welfare of clans. Road accident fatalities are increasing in Kerala due to the traffic congestions and increase in both population and number of vehicles. The present study investigates the spatial and temporal patterns of the road accidents from 2013 to 2015 in Thrissur district, Kerala using geospatial technology. Assessment of spatio-temporal clustering of road accidents was carried out using Moran’s I method of spatial autocorrelation, Getis-Ord Gi* hotspot analysis, and Kernel density functions. The year wise total accidents show a clustered pattern, whereas the spatio-temporal breakup of events shows random and clustered distribution in certain classes. The continuous road stretches and isolated zones of hotspots and cold spots were delineated by the Kernel density surface using the results of Getis-Ord Gi* hotspots analysis. Four major road segments such as National highway near Kodungallur to Althara stretch, Thrissur town to Perumpilav stretch via Kunnamangalam, Thrissur town to Vadanappally segment, and Guruvayur to kunnamangalam stretch are identified as highly clustered accident hotspots. The results of this study can be effectively used by local self-governments, police departments, as well as national agencies for implementing better road safety policies in the accident hotspots stretches.

Spatio-Temporal Analysis of Road Accident Incidents and Delineation of Hotspots Using Geospatial Tools in Thrissur District, Kerala, India

Drivers’ lack of alertness is one of the main reasons for fatal road traffic accidents (RTA) in Iran. Accident-risk mapping with machine learning algorithms in the geographic information system (GIS) platform is a suitable approach for investigating the occurrence risk of these accidents by analyzing the role of effective factors. This approach helps to identify the high-risk areas even in unnoticed and remote places and prioritizes accident-prone locations. This paper aimed to evaluate tuned machine learning algorithms of bagged decision trees (BDTs), extra trees (ETs), and random forest (RF) in accident-risk mapping caused by drivers’ lack of alertness (due to drowsiness, fatigue, and reduced attention) at a national scale of Iran roads. Accident points and eight effective criteria, namely distance to the city, distance to the gas station, land use/cover, road structure, road type, time of day, traffic direction, and slope, were applied in modeling, using GIS. The time factor was utilized to represent drivers’ varied alertness levels. The accident dataset included 4399 RTA records from March 2017 to March 2019. The performance of all models was cross-validated with five-folds and tree metrics of mean absolute error, mean squared error, and area under the curve of the receiver operating characteristic (ROC-AUC). The results of cross-validation showed that BDT and RF performance with an AUC of 0.846 were slightly more accurate than ET with an AUC of 0.827. The importance of modeling features was assessed by using the Gini index, and the results revealed that the road type, distance to the city, distance to the gas station, slope, and time of day were the most important, while land use/cover, traffic direction, and road structure were the least important. The proposed approach can be improved by applying the traffic volume in modeling and helps decision-makers take necessary actions by identifying important factors on road safety.

Evaluation of Tree-Based Machine Learning Algorithms for Accident Risk Mapping Caused by Driver Lack of Alertness at a National Scale

The number of fatalities and casualties caused by road accidents is mostly affected by the 3 factors of road, human, and vehicle. Nowadays, tackling with the accident prone locations including the definition, identification, and modification prioritization has attracted attention as an approach to enhance and improve the roads network safety level. A road accident analysis method is through the use of the Geographic Information System (GIS) and spatial and temporal patterns in accident prone locations. Since accidents are temporal phenomena, in this paper, GIS-based spatial statistical methods have been used to identify and model accident hot spots; in other words, we have investigated the use of localization patterns and hot spot distribution with the help of temporal information.Hot spot analysis with identification and data generation helps decision makers to take appropriate measures to decrease road accidents. To specify and analyze accidents distribution, the information regarding the accidents in the roads of Ilam Province (Iran 2013), has been investigated. Information included the accident type (fatality, injury).From the hot spot map, it is concluded that in northwest roads, despite less traffic, the number (spatial weight) of fatalities is more.This can be due to such factors as the route geometrical design, lack of appropriate relief, and so on. To identify the temporal patterns and accidents distribution, and also analyze the hot spots, Moran's method of spatial autocorrelation and Getis - OrdGi * statistic have been used.

Abdolreza Rezaee Arjroody

Papers

Applying GIS to Identify the Spatial and Temporal Patterns of Road Accidents Using Spatial Statistics (case study: Ilam Province, Iran)