Artificial Intelligence (AI) for Disaster-Resilient Urban Planning: A Comprehensive Data-Driven Review Framework

Abstract

Rapid urbanization and escalating climate-related risks have significantly heightened the disaster vulnerability of cities worldwide. Traditional urban planning methods, constrained by their reliance on static historical data and reactive strategies, are increasingly inadequate for addressing contemporary hazard complexities. Artificial Intelligence (AI) presents a transformative opportunity for disaster-resilient urban planning through data-driven insights and dynamic decision-making capabilities. This paper evaluates the role of AI in enhancing urban resilience and proposes a conceptual framework grounded in a systematic review of peer reviewed literature and comparative global case studies. The study employs a qualitative review methodology encompassing an examination of academic publications, policy reports, and case studies from disaster prone metropolitan areas. Secondary data were sourced from Scopus, Web of Science, institutional databases, and publicly accessible urban and climate datasets. Results indicate that AI-enabled approaches demonstrate superior capabilities in risk recognition, integrated data analytics, and the formulation of proactive, adaptive planning strategies compared to conventional methods. Comparative case study analysis of Chennai, Rotterdam, Tokyo, and Singapore reveals that the efficacy of AI applications is contingent upon data availability, technological infrastructure, and institutional governance capacity. The study concludes that while AI holds substantial potential to transform disaster-resilient urban design, its effective implementation necessitates robust institutional frameworks, ethical governance, and context-specific adaptation, particularly in developing regions.