Land Use Mapping Using Machine Learning, Apurímac-Peru Region.

Abstract

The objective of the research is to develop a global land use / land cover map (LULC) of the Apurímac Region, from ESA Sentinel-2 images with a resolution of 10 m. to predict 10 soil type classes throughout the year in order to generate a representative snapshot of 2020. The methodology used in the analysis is the machine learning model, for the classification it was based on Artificial Intelligence (AI). For the processing, 6 bands of Sentinel-2 surface reflectance data were used: visible blue, green, red, near-infrared and two short-wave infrared bands, to create the final map, the model is run on multiple dates of images throughout the year on the Google Earth Engine (GEE) platform. The results of the study determine the total area is 2 111 415.29 ha, where the water represents 9 392.84 ha. (0.44%), on the other hand, snow/ice occupies 227.89 ha, representing 0.01%, while cultivated land occupies an area of 34 408.09 ha, (1.63%), bushes/shrubs occupy most of 1 740 486.69 ha, which represents 82.435% of the total area.

Keywords

• machine learning
• land cover
• google earth engine (gee)
• artificial intelligence (ai)