Rapid urbanization and climate change are increasing the risks associated with natural hazards, especially in cities where socio-economic disparities are significant. Current hazard risk assessment frameworks fail to consider socio-economic factors, which limits their ability to effectively address vulnerabilities at the community level. This study introduces a machine learning framework designed to assess flood susceptibility and socio-economic vulnerability, particularly in urban areas with limited data. Using Kigali, Rwanda, as a case study, we quantified socio-economic vulnerability through a composite index that includes indicators of sensitivity and adaptive capacity. We utilized a variety of data sources, such as demographic, environmental, and remotely sensing datasets, applying machine learning algorithms like Multilayer Perceptron (MLP), Random Forest, Support Vector Machine (SVM), and XGBoost. Among these, MLP achieved the best predictive performance, with an AUC score of 0.902 and an F1-score of 0.86. The findings indicate spatial differences in socio-economic vulnerability, with central and southern Kigali showing greater vulnerability due to a mix of socio-economic challenges and high flood risk. The vulnerability maps created were validated against historical flood records, socio-economic research, and expert insights, confirming their accuracy and relevance for urban risk assessment. Additionally, we tested the framework’s scalability and adaptability in Kampala, Uganda, and Dar es Salaam, Tanzania, showing that making context-specific adjustments to the model improves its transferability. This study offers a solid, data-driven approach for combining assessments of flood susceptibility and socio-economic vulnerability, filling important gaps in urban resilience planning. The results support the advancement of risk-informed decision-making, especially in areas with limited access to detailed socio-economic information.

The urban population is rapidly increasing and more than half of the world's population is currently living in cities. About 1 billion of city dwellers are living in slums and informal settlements. Addressing the issue of slums and informal settlements require information on these areas. This study explored the potential of Convolutional Neural Network (CNN) and Very-High Resolution satellite image to map the informal settlements in urban areas of the city of Kigali, Rwanda. The study applied modified U-Net model with MobileNetV2 model as the base model to discriminate areas with informal settlements from other areas. The model was obtained by modifying the original U-Net architecture to incorporate dilated convolutional operations at the beginning of the network. The findings demonstrate that based on the spatial characteristics of informal settlements, the model was able to detect informal settlements in urban areas with a recall of 0.862, a precision of 0.810 and an F1-Score of 0.809. Based on these results, the study can be a basis for finding relevant information about informal settlements that are of concern in the implementation of SDGs, especially goal 11 addressing the issues of safe and inclusive cities and human settlements.

Increasing tenure security is essential for promoting safe and inclusive urban development and achieving Sustainable Development Goals. However, assessment of tenure security relies on conventional census and survey statistics, which often fail to capture the dimension of perceived tenure insecurity. This perceived tenure insecurity is crucial as it influences local engagement and the effectiveness of policies. In many regions, particularly in the Global South, these conventional methods lack the necessary data to adequately measure perceived tenure insecurity. This study first used household survey data to derive variations in perceived tenure insecurity and then explored the potential of Very-High Resolution (VHR) satellite imagery and spatial data to assess these variations in urban deprived areas. Focusing on the city of Kigali, Rwanda, the study collected household survey data, which were analysed using Multiple Correspondence Analysis to capture variations of perceived tenure insecurity. In addition, VHR satellite imagery and spatial datasets were analysed to characterize urban deprivation. Finally, a Random Forest regression model was used to assess the relationship between variations of perceived tenure insecurity and the spatial characteristics of urban deprived areas. The findings highlight the potential of geospatial information to estimate variations in perceived tenure insecurity within urban deprived contexts. These insights can inform evidence-based decision-making by municipalities and stakeholders in urban development initiatives.

Urbanization significantly enhances socio-economic conditions, health, and well-being for many by improving access to services, education, and economic opportunities. However, socio-economic and public health disparities are also being exacerbated by urbanization. The reliable data required to monitor these conditions are often unavailable, outdated, or inconsistent. This study introduces a multimodal deep learning framework that integrates satellite imagery with street network datasets to predict urban socio-economic indicators and public health determinants at the sector level as a political administrative unit of public health planning in Rwanda. We extracted latent visual and topological embeddings of the urban built environment, using a Convolutional Neural Network (CNN) and Graph Neural Network (GNN). These embeddings were fused through an attentional mechanism to train a multi-task regression model that simultaneously predicts multiple socio-economic indicators and public health determinants. This framework was applied to the City of Kigali in Rwanda. Overall, the multimodal fusion model achieved the best average performance across targets, with an average correlation of 0.68 and MAE of 1.26 for socio-economic indicators, and 0.68 and 1.46 for public health determinants, demonstrating the benefit of integrating visual and topological information. The learned fused embedding space arranges socio-economic indicators and public health determinant deciles along a continuous morphological gradient from sparsely built rural settings to dense urban settings, demonstrating that the urban form encodes latent signals that capture socio-economic indicators and health determinants. Moreover, the study reveals a strong relationship between socio-economic indicators and the public health index, with education, cooking materials, and floor materials exhibiting a correlation above 0.96. This work demonstrates the utility of an integrated framework for socio-economic indicator profiling and public health planning in data-scarce urban contexts, offering a scalable approach for monitoring the indicators of Sustainable Development Goals in rapidly changing urban environments.

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.