A Novel Approach to Protect Environment by CO2 Emission Detection

The growing environmental impact of vehicle CO2 emissions highlights the pressing need for creative solutions to foresee and lessen their negative impacts. Modern methods must be used because traditional machine learning algorithms are unable to understand the complexity of emissions. Outperforming previous ML restrictions, Automated Machine Learning (AutoML) becomes a vital tool because of its automated composition, selection, and parameterization capabilities. Using a global dataset gathered from the World Data Bank platform, this study investigates the effectiveness of AutoML in predicting CO2 emissions from vehicles. While previous machine learning models found it difficult to reach suitable precision levels, AutoML shows noticeably more prediction capability. This research highlights the advantages of AutoML over conventional machine learning techniques in terms of efficacy, affordability, and accessibility when estimating CO2 emissions. This work adds to the global effort to reduce CO2 emissions and promotes environmental research by demonstrating how AutoML can speed up modelling procedures and improve prediction accuracy.