mar-koz22 / satelite_image_classification_over_time

The aim of this project was to create a land cover classification of the area near Surat in India for 3 timesteps (2015, 2018, 2022) using a Random Forest classifier to access the process of urbanization

Classifying Urban Areas Over Time: A Case Study of Surat, India

The goal of this study is to analyze changes in urban areas of the fast-developing city of Surat, India, based on classification of urban areas with the Random Forest model and then performing post-classification change detection across three time steps (2015, 2018, 2022).

More information about the data, methodology and results are on a poster, that is also in this repository. Satellite images are too big to include here, but can be downloaded from EartExplorer, which is open-source (you have to register)

satelite_image_classification_over_time's Issues

shape file preparation

Labels from the AOIs

aoi = gpd.read_file("polygons_2015/merged_polygons_new2.shp")
aoi['aoi_cat'] = pd.Categorical(aoi['category'])

der sir
how could you prepare the AOI.
If possible share the file plz.