ARCHIVES

The use of private vehicles is a major cause of the intensification of global warming. When one gallon of gasoline is combusted in the engine of a vehicle, it releases about 24 pounds of greenhouse gases, which account for around 20% of overall emissions. The majority of these emissions, more than 19 pounds, are emitted directly from the vehicle's tailpipe as heat-trapping emissions. Nevertheless, amount of emissions generated through the process of extraction, production, and transportation of the fuel is comparatively insignificant. Utilizing the strength of Python programming and so-sophisticated machine learning algorithms, i.e., the Random Forest Classifier and the Decision Tree Classifier, this project provides an exhaustive analysis of automobile emissions. The dataset used for this project has vital data, such as fuel consumption ratings, CO2 emissions in grams per kilometer, etc. These information elements present an integrated view of the environmental performance across different models of vehicles, facilitating informed decision making by consumers and policy makers. Predictive models were constructed using Random Forest Classifier, a strong ensemble learner algorithm, and Decision Tree Classifier. The prediction models obtained stunning accuracy scores with 100% on the training dataset taset and an impressive 99% accuracy on the test dataset. Likewise, the Decision Tree Classifier displayed excellent performance with a 100% training accuracy and a 98% test accuracy. Through the integration of these sophisticated algorithms and a dense dataset, this project contributes to ecological transportation alternatives and enables consumers to make environmentally friendly choices when buying automobiles. The system of CO2 Emission Rating devised here is of great use tool to analyze the environmental footprint of various models of vehicles, in order to lower carbon emissions and slow down climate change. In brief, "CO2 Emission Rating by Vehicles Using Data Science" is an innovative initiative that proves that data science and machine learning can be used to solve some of the most serious environmental issues.ions in grams per kilometer, etc.