Six soil properties- sand, silt, clay, cation exchange capacity, soil organic carbon, nitrogen- have been predicted using remote sensing data in the Dano Catchment (West Africa, Burkina Faso). The predictors topographical and sprectral (Landsat and RapidEye) data. These data are in support of the article entitled: "High resolution mapping of soil properties using remote sensing variables in south-western Burkina Faso: a comparison of machine learning and multiple linear regression models". The uploaded datasets include the following: (1) The dataset used for the present manuscript as well as the R code (2) The maps related to the topographical and climatic variables (3) The maps related to Landsat variables (4) the shapefile containing all data points for each soil property.