Predict (unsupervised) classification layer

Uses a fitted clusterer to predict an (unsupervised) classification layer from a raster layer with features.


Raster layer with features [raster]

A raster layer with bands used as features. Clusterer features and raster bands are matched by name to allow for clusterers trained on a subset of the raster bands. If raster bands and clusterer features are not matching by name, but overall number of bands and features do match, raster bands are used in original order.

Clusterer [file]

A fitted clusterer.

Match features and bands by name [boolean]

Whether to match raster bands and classifier features by name.

Default: False


Output classification layer [rasterDestination]

Raster file destination.

Command-line usage

>qgis_process help enmapbox:PredictUnsupervisedClassificationLayer:


raster: Raster layer with features
    Argument type:  raster
    Acceptable values:
            - Path to a raster layer
clusterer: Clusterer
    Argument type:  file
    Acceptable values:
            - Path to a file
matchByName: Match features and bands by name (optional)
    Default value:  false
    Argument type:  boolean
    Acceptable values:
            - 1 for true/yes
            - 0 for false/no
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
outputClassification: Output classification layer
    Argument type:  rasterDestination
    Acceptable values:
            - Path for new raster layer


outputClassification: <outputRaster>
    Output classification layer