Figure 7
From: Understanding deep learning in land use classification based on Sentinel-2 time series

Location of the study area (eastern Spain), and a corresponding Sentinel-2 RGB (B4, B3, B2) composite image acquired on September 13, 2017 with overlaid ground truth. For the sake of visualisation, parcels belonging to rice, fallow, barley, oat, wheat, sunflower, and triticale have been grouped and displayed as arable land (ARL). The maps were generated with the Arcmap v.10.5 software (https://desktop.arcgis.com/es/arcmap/).