In this paper we investigate a local implementation of Random Forest (RF), named Geographical Random Forest (GRF) to predict population density with Very-High-Resolution Remote Sensing (VHHRS) data. As an independent variable we use population density at the neighborhood level from the 2013 census of Dakar, while as explanatory features, the proportions of three different built-up types in each neighborhood derived from a VHHRS land cover classification. The results demonstrated, that by using an appropriate geographic scale to calibrate GRF, we can maximize prediction accuracy due to the incorporation of spatial heterogeneity in the estimates. Additionally, since GRF is an ensemble of local sub-models, the results can be mapped, highlighting local model performance and other interesting spatial variations. Consequently, GRF is suggested as an interesting exploratory and explanatory technique to model remotely-sensed spatially heterogeneous relationships.