Mapping Socio-Economic Vulnerability to Natural Hazard in Urban Areas Using Machine Learning and Indicator-Based Approaches

Urbanization and climate change are increasing the risks of natural hazards, particularly in cities with significant socio-economic disparities. Existing hazard risk assessment frameworks often neglect socio-economic dimensions, limiting their utility in addressing community-level vulnerabilities. This study proposes an integrated machine learning and indicator-based framework for assessing flood susceptibility and socio-economic vulnerability, with a focus on data-scarce settings, using a case study of the City of Kigali. Socio-economic vulnerability was quantified through a composite index incorporating sensitivity and adaptive capacity. Multisource data were integrated and modeled using machine learning models, which included Multilayer Perceptron, Random Forest, Support Vector Machine, and XGBoost. In terms of model performance, the MLP has achieved high performance with an AUC score of 0.902 and F1-Score of 0.86. The results indicate intensified vulnerability in central and southern Kigali, with noticeable socio-economic disadvantages and high flood susceptibility. The resulting maps were validated using historical flood data, other socio-economic studies in the area, and local knowledge. The scalability of the framework was evaluated in Kampala, Uganda, and Dar es Salaam, Tanzania, demonstrating scalability with context-specific adaptations. This approach offers a robust methodology for integrating flood susceptibility and socio-economic vulnerability, enabling data-driven prioritization of interventions. The findings contribute to advancing urban resilience strategies, particularly in regions constrained by limited data availability.