Black Spot Identification and Road Accident Prediction Model on Cebu South Coastal Road (CSCR)

Abstract

Millions of people die in road accidents yearly, causing significant damage to the economy and humanity. The main focus of the study is to analyze road accidents through Black Spot Identification and to establish a Prediction Model on the Cebu South Coastal Road (CSCR)-N840 Highway. The data gathered from government agencies were digitized using SPSS and MS Excel. The study revealed that the year 2018 has the highest number of accident cases with 555 (46.52%) and the lowest severity ratio of 0.41. In contrast, 2019 has the lowest frequency of accident cases with 159 (13.33%) and a severity ratio of 0.72. Through the APW system, the CSCR-N840 Highway’s top black spot locations were at 2.6 km, 1.2 km, 2.3 km, 0.9 km,2.2 km, 5.3 km, 4.6 km, 4.7 km, 3.7 km, 5.9 km, 7.6 km, 7.7 km, 8.2 km, 8.5 km, 6.5 km, 10.2km, 11.4 km, 9.4 km, 12.1 km, and 12.0 km. Also, the researchers presented a heat mapping through QGIS for visual analysis, where severe road traffic accidents usually occur on the Talisay side of CSCR N840 Highway due to 13 junctions, 7 intersections, and 6 curvatures. Lastly, in the developed regression model the accident rate decreases gradually with an increase in the traffic volume. Also, Poisson prediction model, as the accident probability increases, the accident rate may either increase or slowly decrease.

A Comprehensive Literature Review of Traditional and Spatial Methods for Black Spot Identification in Road Crash Analysis

“…Machine learning algorithms, such as logistic regression and clustering, have also been used to identify black spots and establish prediction models (Sisbreño, Sumilhig et al 2023). These models utilize data from accident records and can effectively classify data sets and establish connections between factors and the severity of accidents ).…”