Unsupervised Mapping of Flood-prone Areas in Ghana Using Sentinel-1 Time-Series

Abstract

Abstract. Flooding is one of the most persistent natural hazards in Ghana, causing recurrent damage to infrastructure, livelihoods, and local economies. Despite its widespread impacts, most flood-related research has been concentrated on Accra, leaving many regions understudied. This paper addresses this spatial gap by integrating Earth Observation (EO) datasets to identify and characterise flood-prone areas across Ghana at a national scale. Precipitation patterns between 2015 and 2025 derived from the IMERG dataset showed a clear seasonal cycle, with major rainfall peaks from April to October, directly corresponding to observed flood events. This implies an associated annual seasonal cycle of flooding. Sentinel-1 Synthetic Aperture Radar (SAR) imagery was used for flood mapping using a change detection (ratio) approach on the backscatter coefficients. Results showed that flood is concentrated in the southern half of the country, particularly in Western, Western North and Eastern Regions, and hotspots around Kumasi in Ashanti and the Weija dam in Greater-Accra regions. Spatial patterns of the flood align closely with the national topography, with low elevation areas especially those beneath the Y-shaped mountain in the country more vulnerable. Technically, the study demonstrates the effectiveness of SAR-based change detection for flood mapping in data-sparse environments, while highlighting limitations relating to in-situ validation. The results underline the necessity of adopting engineering solutions to reduce flood impacts as a long term solution to the annual recurring flood observed in the country. From a policy perspective, the findings provide evidence to support flood risk management strategies.