<![CDATA[The rapid growth of urban populations presents significant challenges in infrastructure management, including increased maintenance costs, energy inefficiencies, and rising risks of structural failures. To address these issues, integrating Artificial Intelligence (AI) and Digital Twin technology has emerged as a promising approach for predictive infrastructure management. This study aims to evaluate the effectiveness of AI and Digital Twin integration in improving urban infrastructure resilience, optimizing maintenance strategies, and enhancing energy efficiency. A case study methodology was employed, utilizing real-time data from IoT sensors and historical maintenance records to develop AI-driven predictive models. The research applied machine learning algorithms, including Decision Tree, Random Forest, and Long Short-Term Memory (LSTM), for failure prediction, combined with Digital Twin simulations to optimize infrastructure management. The results indicate that the AI-based predictive failure model achieved an accuracy of 92%, significantly reducing the risk of infrastructure failure by 70%. Furthermore, the integration of AI and Digital Twin led to a 60% reduction in maintenance costs and a 35% improvement in energy efficiency, particularly in urban lighting and public facility management. These results demonstrate that the adoption of AI and Digital Twin technology can transform conventional infrastructure management by enabling proactive and cost-effective maintenance strategies. This study contributes to the growing body of knowledge on smart city infrastructure by providing empirical evidence on the benefits of AI-driven predictive analytics and Digital Twin simulations in enhancing urban sustainability and operational efficiency]]>
