Classification layer accuracy and area report (for simple random sampling)

Estimates map accuracy and area proportions for (simple) random sampling. We use the formulas for the stratified random sampling described in Stehman (2014): https://doi.org/10.1080/01431161.2014.930207. Note that (simple) random sampling is a special case of stratified random sampling, with exactly one stratum. Observed and predicted categories are matched by name, if possible. Otherwise, categories are matched by order (in this case, a warning message is logged).

Parameters

Predicted classification layer [raster]

A classification layer that is to be assessed.

Observed categorized layer [layer]

A categorized layer representing a (ground truth) observation sample, that was aquired using a (simple) random sampling approach.

Open output report in webbrowser after running algorithm [boolean]

Whether to open the output report in the web browser.

Default: True

Outputs

Output report [fileDestination]

Report file destination.

Command-line usage

>qgis_process help enmapbox:ClassificationLayerAccuracyAndAreaReportForSimpleRandomSampling:

----------------
Arguments
----------------

classification: Predicted classification layer
    Argument type:  raster
    Acceptable values:
            - Path to a raster layer
reference: Observed categorized layer
    Argument type:  layer
    Acceptable values:
            - Path to a vector, raster or mesh layer
openReport: Open output report in webbrowser after running algorithm
    Default value:  true
    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
outClassificationPerformance: Output report
    Argument type:  fileDestination
    Acceptable values:
            - Path for new file

----------------
Outputs
----------------

outClassificationPerformance: <outputHtml>
    Output report