Classification of land use areas using remote sensing data with machine learning

province of greater El Jadida is experiencing an immense movement of change, both in terms of the extension of the building and in agricultural activity. This creates a high demand for information on the land likely to build all the different types of infrastructures there, given the considerable demographic change. On the other hand, knowledge of vegetation areas with ecological high potential will allow decision-makers to make targeted and profitable investments. The work piloted in this study, entering in the field of data science, aims to apply the techniques of Machine Learning to the data extracted via remote sensing to make the machine learn how to differentiate between vegetation areas, built-up, or other land use. Learning will be carried out by applying algorithms to the indices calculated from Landsat 8, namely Normalized difference water index (NDWI), Dry built-up index (DBI), and Normalized difference vegetation (NDVI). This will likely help formulate beneficial decisions for stakeholders across the Greater El Jadida area.