Data-driven analysis of the correlation between traffic accidents and rainfall

• Main Author: Tan, Chong Wei
• Other Authors: Justin Dauwels
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/76351
• Institution: Nanyang Technological University

This project aims at studying the impact of rainfall on the overall traffic flow. We are particularly interested to analyse the correlation between occurrence of traffic incidents with the occurrence of rain. Moreover, we examine if there is a differing impact on the frequency of traffic incidents before, during, or after rain. For comparison, the frequency of traffic incidents is also computed for dry periods (without any rainfall). The data acquired from LTA and NEA from August 2016 to January 2017 is used to determine the correlation of incidents, traffic speed and traffic volume with the rainfall. Overall, the results obtained support the hypothesis that the frequency of traffic incidents is higher in rain and after rain weather conditions, as compared to dry periods. Furthermore, it is observed that the traffic speed decreases during rainy weather condition as compared to dry weather conditions.