Assessing Urban Flood Susceptibility Using Random Forest Machine Learning and Geospatial Technologies: Application to the Bonoumin-Palmeraie Watershed, Abidjan (Côte d’Ivoire)

Recurrent flooding poses a persistent and growing threat to West African watersheds facing rapid urbanization and climate change. Despite advances in machine learning and geospatial datasets, urban planning and flood prevention often rely on limited datasets and traditional analysis. This study addresses this research gap in the Bonoumin-Palmeraie watershed (Abidjan, Côte d’Ivoire) by developing an integrated approach leveraging remote sensing, Geographic Information Systems (GIS), and the Random Forest algorithm to assess and map flood susceptibility. Twelve conditioning factors related to topography, hydrology, land use, and climate were derived from Sentinel-1, ALOS PALSAR, and multi-source earth observation datasets. Historical flood extents were mapped in Google Earth Engine to train the Random Forest model in a Google Colab environment. The model demonstrated high discriminatory power, yielding an Area Under the Curve of 0.94 and Overall Accuracy of 0.83. Drainage density, rainfall, and altitude were identified as the primary explanatory drivers. The resulting flood susceptibility map indicates that 39% of the watershed exhibits medium to very high susceptibility, with critical hotspots in the neighborhoods of Palmeraie, Attoban, Akouedo, Djorogobité, and Riviera-Sogefiha. While limited by the exclusion of certain anthropogenic variables and ground truth constraints, the study provides a reproducible, data-driven framework for flood risk assessment in tropical urban environments. These findings offer essential scientific support for urban planners and decision-makers to enhance territorial planning and sustainable flood management in Abidjan.