In many African cities, the accelerating forces of rapid urbanization and shifting climate patterns are intensifying the frequency and impact of climate shocks, including flash floods, heatwaves, droughts, and coastal surges. These hazards disproportionately affect informal settlements and critical infrastructure, challenges that are further compounded by fragmented data ecosystems, limited digital capacity, and inadequate real-time monitoring systems. This study presents a systematic review of 64 peer-reviewed articles published between 2015 and 2025, sourced from Scopus, Web of Science, and ScienceDirect, to evaluate the role of GeoAI (Geospatial Artificial Intelligence) in advancing urban climate resilience. The review focuses on five representative African cities—Lagos, Nairobi, Addis Ababa, Cape Town, and Dakar—selected for their diverse hazard profiles and varying institutional capacities. The study proposes a GeoAI-enabled framework that integrates Geographic Information Systems (GIS), remote sensing, and machine learning algorithms, including Random Forest, Support Vector Machines, Convolutional Neural Networks, and Long Short-Term Memory (LSTM) networks—to map spatial vulnerabilities, forecast climate hazards, and evaluate institutional readiness for proactive adaptation. Comparative analysis reveals persistent exposure hotspots in marginalized communities, with variations in predictive accuracy and hazard severity closely linked to data infrastructure maturity and governance capacity. Cape Town and Nairobi exhibit higher institutional readiness and successful integration of GeoAI into policy processes, while Lagos, Addis Ababa, and Dakar face obstacles related to data accessibility and inter-agency coordination. The study underscores the importance of embedding ethical principles, participatory mapping, and equity considerations into GeoAI systems to enhance both policy relevance and community resilience. The proposed framework offers a scalable, context-sensitive pathway for climate-smart urban governance in low- and middle-income settings, supporting the objectives of Sustainable Development Goals 11 (Sustainable Cities and Communities) and 13 (Climate Action).
Bello Hafisat Omodasola (Sat,) studied this question.