Use the Train Birch tool to train raster data for the unsupervised BIRCH classification algorithm.

For background on the algorithm used, see BIRCH Classification.

You can also write a script to train raster data for BIRCH classification using the TrainBirch task.

  1. From the Toolbox, select Machine Learning > Training > Unsupervised Classification > Train BIRCH. The Train BIRCH dialog appears.
  2. Select the Input Rasters to train, perform optional spatial and spectral subsetting and/or masking, then click OK.

  3. Optionally, enter a name for the model in the Model Name field. The default is BIRCH Unsupervised Classifier.

  4. Optionally, enter a description for the model.

  5. In the Normalize field, you can optionally apply normalization statistics to the rasters that will be used for training by specifying Min and Max data values that correspond to 0% and 100% reflectance.

  6. Enter the maximum number of clustering feature subclusters in each node in the Branching Factor field. The default is 50.
  7. Enter the Number of Classes to identify. The default is 3.
  8. In the Threshold field, enter the radius of the subcluster obtained by merging a new sample and the closest subcluster should be less than the threshold. The default is 0.5.
  9. In the Output Model field, enter a location and filename for the classifier model.

  10. To reuse these task settings in future ENVI sessions, save them to a file. Click the down arrow and select Save Parameter Values, then specify the location and filename to save to. Note that some parameter types, such as rasters, vectors, and ROIs, will not be saved with the file. To apply the saved task settings, click the down arrow and select Restore Parameter Values, then select the file where you previously stored your settings.

  11. To run the process on a local or remote ENVI Server, click the down arrow and select Run Task in the Background or Run Task on remote ENVI Server name. The ENVI Server Job Console will show the progress of the job and will provide a link to display the result when processing is complete. See the ENVI Servers topic in ENVI Help for more information.

  12. To see a model-based version of this tool that shows how the tool is constructed from individual tasks, click Open in Modeler.

  13. Click OK.

See Also

ENVI Machine Learning Algorithms Background, TrainBirch Task, BIRCH Classification Tool