Asif Raihan
The integration of Digital Twin (DT) and Artificial Intelligence (AI) technologies has shown considerable potential for advancing sustainability in energy and environmental systems, yet existing literature remains fragmented across sectors. This study conducts a systematic literature review of peer-reviewed research published between 2015 and 2025, applying PRISMA-guided screening to identify and analyze 142 relevant studies. The review methodology, including database search, selection criteria, and thematic analysis, ensures reproducibility and comprehensive coverage. The paper makes three core contributions. First, it establishes a conceptual foundation for DT-AI convergence by clarifying the complementary roles of DT as a dynamic digital representation and AI as adaptive intelligence, thus grounding the integration theoretically. Second, it provides a cross-sectoral synthesis of DT-AI applications across energy infrastructures and environmental domains, revealing that integration is most mature where data richness and system controllability are high, such as in smart grids, renewable assets, and intelligent buildings. Third, the review identifies persistent limitations and research gaps, including challenges in scalability, interoperability, AI transparency, and standardized sustainability evaluation. The analysis shows that DT-AI systems significantly enhance predictive control, operational efficiency, and resilience in urban and cyber-physical systems, while environmental applications benefit from improved scenario analysis and decision support. However, constraints related to data sparsity, uncertainty propagation, and governance impede real-time optimization in some domains. By synthesizing evidence across fields and drawing integrative insights, this study advances understanding of DT-AI’s role in sustainable urban development and outlines research priorities necessary to translate technological promise into scalable, impactful solutions.