Several clustering methods are available in the EnMAP-Box. You can find them in the Processing Toolbox under Fit … algorithm first and then apply it to an image with Predict (unsupervised) classification layer.. The usual way to apply these methods is to use a
You can find all the available clustering algorithms here.
Open the test dataset
In the processing toolbox go to
- Under Output Clusterer specify an output file path and click Run
enmap_berlin.bsqas input Raster
- Under Clusterer click … and select the output
.pklfile from the Fit KMeans algorithm
- Specify an output filepath for the transformed raster under Clustering and click Run
8 clusters is the default of the kmeans algorithm here, if you want to change the number of clusters, run the
Fit Kmeans algorithm with a fewer number, by altering the
KMeans() function in the Code window to
This will reduce the amount of clusters to 4.