Machine learning can be applied to many fields as land cover classification from remote sensing imagery. The performance and accuracy of classification will depend on the number of raster bands, the image resolution, the land cover type and the algorithm used. This tutorial will perform an applied case of land cover classification from a panchromatic image in Python using the Naives Bayes algorithm implemented on the Scikit Learn package. The classification will cover four categories as: rivers, river beaches, woods and pastures; coding is performed under a Jupyter Notebook with Python running from a geospatial Conda environment. Some graphics and statistics about the classification precision are also included on the tutorial.

The processes of working with digital elevation models (DEMs) and watershed delineation are in constant change over time. Even though the elevation datasets date from 10 years ago; the web servers and tools for data processing have changed in recent years. With online tools such as Hatari Utils, the watershed delineation can be performed in a few steps with practical outputs as vector files and watershed statistics.

This tutorial covers the complete procedure to create a land cover change raster from a comparison of generated vegetation index (NDVI) rasters by the use of Python and the Numpy and Rasterio libraries. Results of the NDVI for given years and NDVI change are plotted on Jupyter Lab as color grid and contour grid.

Our current working conditions require access to spatial information in short periods of time. Work planning tasks or quoting of services require data of distances, areas, proximities, medium elevations, among others. The data can be given by clients, organizations or by field monitoring, but they may not be available at the required moment. The use of geoprocessng tools of satellite imagery reduces the required time to have this information. Since QGIS is open source and the Landsat, MODIS and Aster images are free, this type of geoprocessing is versatile, economic and friendly for any user with basic/intermediate QGIS knowledge.

This tutorial show the procedure to create contours from a raster file considering interval definition. The example is made from a NDVI raster file.

This tutorial show the procedure to cut a NDVI Raster File calculated from a Sentinel 2 Granule on QGIS.

This tutorial show the prodecure to calculate the NDVI from Sentinel 2 bands on QGIS.

False color images are used to enhance certain cover types as vegetation on the image representation. This tutorial show the procedure represent the bands of a False Color image from Sentinel 2 bands in QGIS. 

This tutorial show the procedure represent the bands of a Sentinel 2 Granule (Image) in QGIS. The representation of the image is True Color (Red, Green and Blue)

Sentinel-2 carries an innovative wide swath high-resolution multispectral imager with 13 spectral bands for a new perspective of our land and vegetation. The mission is based on a constellation of two identical satellites in the same orbit, 180° apart for optimal coverage and data delivery. Together they cover all Earth’s land surfaces, large islands, inland and coastal waters every five days at the equator (source ESA).

This tutorial show the procedure to download especific granules from a ESA Sentinel 2 Image using the website: https://scihub.copernicus.eu/