Analysing significant automobile carbon dioxide (CO2) emission factors for eco-friendly automotive framework using descriptive analytics and artificial neural network (ANN) technology

The automotive industry's role in environmental sustainability has gained significant attention globally, with carbon dioxide (CO2) emissions being a primary concern. This study investigates the factors influencing CO2 emissions in automobiles within the context of eco-friendly frameworks. A comprehensive analysis is conducted using Partial Least Squares Structural Equation Modelling (PLS-SEM) and Artificial Neural Network (ANN) technology to understand the intricate relationships between various automotive factors and their impact on CO2 emissions. The study identifies critical variables, including engine CC, horsepower, fuel type, track width, weight, aerodynamics, car segment, official euro class, transmission, emotion, knowledge and driving behaviour, hypothesized to influence CO2 emissions. Adopting PLS-SEM, these variables' direct and indirect effects on emissions are examined, providing insights into their relative importance and interdependencies. Moreover, the ANN model is deployed to explore nonlinear relationships and predict CO2 emissions more accurately. Results indicate that engine efficiency and fuel type significantly affect CO2 emissions, with higher-efficiency engines and alternative fuels demonstrating a considerable reduction in emissions. Additionally, vehicle weight emerges as a crucial determinant, with lighter vehicles exhibiting lower emissions due to enhanced energy efficiency. Moreover, driving behaviour, encompassing factors such as speed patterns and acceleration rates, influences emissions, emphasizing the importance of ecoconscious driving habits. Integrating PLS-SEM and ANN technology enables a robust analysis of automotive factors contributing to CO2 emissions, offering valuable insights for ecofriendly automotive frameworks. By understanding these relationships, policymakers, manufacturers, and consumers can make informed decisions to mitigate emissions and promote sustainable transportation solutions. Future research could explore additional variables and refine modelling techniques to further enhance the understanding of CO2 emissions in the automotive sector and facilitate the transition towards a greener mobility landscape.