Leveraging the Potential of Convolutional Neural Network and Satellite Images to Map Informal Settlements in Urban Settings of the City of Kigali, Rwanda

Abstract

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.