APPLICATION OF IOT AND AI FOR REAL-TIME FLOOD EARLY-WARNING AND RESILIENCE MANAGEMENT IN IBADAN METROPOLITAN AREA

Abstract

Urban flooding poses a persistent threat to lives, infrastructure, and economic activities in rapidly growing African cities, yet early-warning systems in many contexts remain reactive and data-poor. This study develops and empirically evaluates an integrated Internet of Things (IoT) and Artificial Intelligence (AI)–based flood early-warning prototype for the Ibadan metropolitan area, Southwest Nigeria. Real-time hydrological data were collected through strategically deployed rainfall and water-level sensors across flood-prone communities and integrated with historical datasets to train an artificial neural network model for flood prediction. Geospatial analysis was used to map flood-risk hotspots, while system performance was assessed using accuracy, precision, recall, and warning lead-time metrics. Results show that the integrated IoT–AI system achieved prediction accuracy exceeding 90% and increased average warning lead time by nearly threefold compared to conventional monitoring approaches. Stakeholder validation further confirmed high usability and operational relevance for disaster response agencies and local communities. The findings demonstrate that locally developed, low-cost smart technologies can substantially enhance urban flood preparedness and resilience. The study provides a scalable model for climate adaptation planning and supports evidence-based integration of smart early-warning systems into urban disaster risk management frameworks in Nigeria and similar developing-country contexts.