Predictive Analytics and Forecasting of CO₂ Emission in Vehicles for Urban Sustainability and Lifecycle Optimization

The rapid increase in CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emissions from vehicles poses a significant risk to air quality and environmental sustainability in urban areas, and as a result, there is a need for advanced predictive solutions. The present work develops a framework for CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emissions forecasting using machine learning tools that consider a vehicle’s engine parameters, fuel efficiency, and transmission type. The proposed approach consists of data cleaning and feature extraction, along with model implementation through Linear Regression, Random Forest, Support Vector Regression, and K-Nearest Neighbor. The framework also integrates sustainability proxies, as it fosters enhanced forecasting of emissions from various vehicles and also measures the emission performance of different vehicle types. Moreover, the framework offers vehicle life cycle optimization solutions that assist various stakeholders, including policymakers and vehicle owners, to make decisions that lead to emission reductions. The findings validate the effectiveness to optimize emission reduction on the strategies for achieving sustainable urban mobility and carbon footprint reduction. This work addresses the gap between predictive analytics and environmental issues with the goal of developing a scalable model for emission control and transportation eco-planning.