Artificial Intelligence for Net-Zero and Climate-Resilient Sustainable Cities: Technologies, Challenges, and Future Perspectives

Abstract

Urbanization, climate change, increasing energy demand, and rapid infrastructure development have created significant challenges for achieving sustainable and resilient cities. Artificial intelligence (AI) has emerged as a transformative technology that enables data-driven decision-making, intelligent automation, and efficient resource management, making it an important enabler of net-zero and climate-resilient urban systems. This narrative review examines AI applications relevant to urban climate mitigation and adaptation, drawing on literature identified through Google Scholar and ScienceDirect. The review examines the role of machine learning, deep learning, Internet of Things (IoT), big data analytics, cloud computing, digital twins, and generative AI in improving urban energy systems, sustainable transportation, environmental monitoring, infrastructure management, and smart governance. The study also discusses how these technologies contribute to carbon emission reduction, renewable energy integration, climate adaptation, disaster preparedness, and efficient urban planning. In addition, major challenges associated with AI implementation are critically analyzed, including data privacy, cybersecurity, algorithmic bias, lack of interoperability, high energy consumption of AI systems, digital inequality, and governance issues. Emerging research trends such as explainable AI, green AI, AI-enabled digital twins, federated learning, and human-centered smart governance are highlighted as important directions for future research. Based on the reviewed literature, the study proposes future research priorities that emphasize interdisciplinary collaboration, responsible AI governance, standardized urban data frameworks, and sustainable policy development. Overall, AI has the potential to accelerate the transition toward intelligent, low-carbon, and climate-resilient cities. The synthesis is qualitative and non-exhaustive, with limitations arising from unavailable original search and screening records and differences between study settings and outcome measures. However, the successful implementation of AI will depend on integrating technological innovation with ethical governance, public participation, and long-term sustainability planning to achieve the United Nations Sustainable Development Goals.