Abstract: Machine learning is a niche area of the more general field of artificial intelligence that is responsible for the rapid development of technologies improving different aspects of human existence. The ability to make accurate and reliable predictions from large amounts of data brings significant benefits in such fields as healthcare, transportation, energy, and environmental conservation. This paper presents a machine learning model designed to estimate carbon dioxide emissions produced by the use of fossil fuel consuming vehicles. This study primarily aims to provide an advanced and scalable solution that is an alternative to established emission estimation tools. The main objective of the research was to make a carbon emission forecast by analyzing the characteristics of vehicles such as model year, make, model, type, engine displacement, number of cylinders, transmission type and fuel type. When it comes to analysis, the study used Linear Regression and Multiple Linear Regression algorithms. The data includes a large dataset with a total of 1068 rows with 200 individual models representing 39 car brands. This data set is derived from a number of vehicle methods employed in training the model. It entails several steps such as data preprocessing, feature selection, and assessment of the models' accuracy. The findings indicate that the machine learning-based models have a a high degree of accuracy in forecasting carbon emissions. The findings can be utilized to encourage environmental become informed and make knowledgeable choices for automobile manufacturers and decision makers. This study aims to be an excellent tool to promote environmental sustainability by providing a daily life-based method for emission estimation. By doing this, the study not only adds to the current academic literature but Additionally, it possesses the capacity to devise solutions for real-world challenges.

Keywords: Carbon Emissions, Machine Learning, Environmental Pollution, Fossil Fuel Vehicles, Sustainability

Pages: 144-156

WSEAS Transactions on