This document discusses predicting CO2 emissions from vehicles using data analytics. It begins with an introduction on the importance of addressing CO2 emissions and climate change. Next, it discusses the urgency of curbing CO2 emissions given the impacts of climate change. The document then explains how data analytics can be used to develop predictive models for CO2 emissions by examining historical emissions data for trends. It outlines the objectives of predicting emissions, identifying key data sources, modeling techniques, and case studies. Finally, it presents the results of building different predictive models for CO2 emissions using techniques like linear regression, random forests, and ridge regression. The highest performing model was ridge regression, achieving 99.78% accuracy and the lowest error.