Geospatial Artificial Intelligence for Urban Flood Risk Assessment and Resilience Planning
Abstract
Urban flooding is escalating because of climate change, rapid urbanization, land-use change, and inadequate drainage, demanding advanced spatial decision-support systems. Geospatial Artificial Intelligence (GeoAI), integrating GIS, remote sensing, and deep learning, has become a powerful approach for flood risk assessment and management. This study presents a systematic review and bibliometric analysis of 106 Scopus-indexed publications (2016–2026). Publication trends, Bradford's Law, Lotka's Law, keyword co-occurrence, thematic evolution, and strategic thematic mapping were used to examine the field's intellectual structure and research development. Results indicate rapid expansion after 2022 (25.89% annual growth rate), with risk assessment, flooding, vulnerability, and machine learning as dominant themes. The review synthesizes GeoAI applications in flood susceptibility mapping, and deep learning, and proposes an integrated GeoAI-based disaster intelligence framework while identifying future priorities in explainable AI, digital twins, and real-time flood management.
