Evaluation of Vehicular Emissions in Chittagong City Using Machine Learning Algorithm

Abstract: This research conducts a comprehensive evaluation of vehicular emissions in Chittagong City, utilizing machine learning algorithms to analyze traffic data. The primary aim of this project is to quantify emissions generated by urban traffic and propose effective strategies to improve mobility while reducing environmental impacts. The study focuses on the Kaptai Rastar Matha intersection, one of the busiest locations in Chittagong City. Machine learning models are applied to traffic flow data, vehicle types, and road infrastructure to predict and calculate emissions of CO2, NOx, and particulate matter (PM) produced by vehicles at this intersection. To ensure the relevance and accuracy of the analysis, data on traffic patterns, vehicle categories, and road conditions were collected during peak traffic periods. The study then conducts a scenario analysis, exploring how various factors such as traffic volume, road conditions, and vehicle composition affect emission levels. The results highlight the importance of employing data-driven, evidence-based policies to address urban environmental challenges related to transportation. The findings advocate for the adoption of sustainable practices aimed at reducing emissions and improving air quality in the city. Ultimately, this research contributes to the development of greener, healthier, and more livable urban spaces by promoting efficient and environmentally friendly transportation solutions for Chittagong Contributing to the development of greener, healthier, and more livable cities in the future.