Integrating Artificial Neural Networks for Predictive Life Cycle Assessment of Electric Vehicles in Sustainable Transportation

Sustainable transportation plays a critical role in combating climate change, with electric vehicles (EVs) offering a significant solution to reducing greenhouse gas emissions. This study integrates Life Cycle Assessment (LCA) and Artificial Neural Networks (ANN) to evaluate and predict the environmental impacts of EVs under various scenarios. While LCA provides a static analysis covering production, usage, and recycling phases, the ANN model overcomes the limitations of traditional methods by delivering dynamic scenario-based predictions. According to the analysis, increasing the renewable energy share in the electricity grid from 30% to 70% can reduce usage-phase emissions by approximately 17%, as listed in Table 2. Additionally, increasing battery recycling rates from 10% to 80% reduces life cycle emissions by up to 20%, emphasizing the importance of recycling technologies. Validated against LCA data, the ANN model demonstrated a 95% accuracy rate in reliably predicting environmental impacts under different conditions. This integrated approach highlights the critical role of energy policies and technological innovations in optimizing EV sustainability. By combining LCA's analytical precision with ANN's predictive capabilities, the framework is shown to be applicable for advancing renewable energy integration, enhancing recycling infrastructure, and developing sustainable production processes. The analysis reveals a strong alignment between LCA and ANN results, emphasizing their consistency and robustness in addressing environmental impacts. Keywords—life cycle assessment, artificial neural networks, electric vehicles, sustainable transportation, renewable energy, environmental impact analysis.