pkannogr - classify vector dataset using Artificial Neural Network

pkannogr implements an artificial neural network (ANN) to solve a supervised classification problem.  The
       implementation  is  based  on  the open source C++ library ( fann ⟨http://leenissen.dk/fann/wp/⟩ ).  Both
       raster and vector files are supported as input.  The output will contain the classification  result,  ei‐
       ther  in  raster  or  vector format, corresponding to the format of the input.  A training sample must be
       provided as an OGR vector dataset that contains the class labels  and  the  features  for  each  training
       point.   The point locations are not considered in the training step.  You can use the same training sam‐
       ple for classifying different images, provided the number of bands of the images are identical.  Use  the
       utility  pkextract(1) to create a suitable training sample, based on a sample of points or polygons.  For
       raster output maps you can attach a color table using the option -ct.

       pkannogr - classify vector dataset using Artificial Neural Network

-ifilename, --inputfilename
              input image

       -tfilename, --trainingfilename
              training vector file.  A single vector file contains all training features (must be  set  as:  B0,
              B1,  B2,...)  for  all  classes (class numbers identified by label option).  Use multiple training
              files for bootstrap aggregation (alternative to the --bag and --bsize options, where a random sub‐
              set is taken from a single training file)

       -tlnlayer, --tlnlayer
              training layer name(s)

       -labelattribute, --labelattribute
              identifier for class label in training vector file.  (default: label)

       -priorvalue, --priorvalue
              prior probabilities for each class (e.g., -prior 0.3 -prior 0.3 -prior 0.2 )

       -cvvalue, --cvvalue
              n-fold cross validation mode (default: 0)

       -nnnumber, --nneuronnumber
              number of neurons in hidden layers in neural network (multiple hidden layers are set  by  defining
              multiple number of neurons: -nn 15 -nn 1, default is one hidden layer with 5 neurons)

       -mfilename, --maskfilename
              Only  classify  within specified mask (vector or raster).  For raster mask, set nodata values with
              the option --msknodata.

       -msknodatavalue, --msknodatavalue
              mask value(s) not to consider for classification.  Values will be taken over in classification im‐
              age.  Default is 0.

       -nodatavalue, --nodatavalue
              nodata value to put where image is masked as nodata (default: 0)

       -ofilename, --outputfilename
              output classification image

       -ottype, --otypetype
              Data type for output image ({Byte / Int16 / UInt16 / UInt32 / Int32 / Float32 / Float64 / CInt16 /
              CInt32 / CFloat32 / CFloat64}).  Empty string: inherit type from input image

       -ofGDALformat, --oformatGDALformat
              Output image format (see also gdal_translate(1)).  Empty string: inherit from input image

       -fOGRformat, --fOGRformat
              Output ogr format for active training sample (default: SQLite)

       -ctfilename, --ctfilename
              colour table in ASCII format having 5 columns: id R G B ALFA (0: transparent, 255: solid)

       -coNAME=VALUE, --coNAME=VALUE
              Creation option for output file.  Multiple options can be specified.

       -cname, --classname
              list of class names.

       -rvalue, --reclassvalue
              list of class values (use same order as in --class option).

       -v0|1|2, --verbose0|1|2
              set to: 0 (results only), 1 (confusion matrix), 2 (debug)

       Advanced options

       -balsize, --balancesize
              balance the input data to this number of samples for each class (default: 0)

       -minnumber, --minnumber
              if number of training pixels is less then min, do not take this class into  account  (0:  consider
              all classes)

       -bband, --bandband
              band index (starting from 0, either use --band option or use --start to --end)

       -sbandband, --startbandband
              start band sequence number (default: 0)

       -ebandband, --endbandband
              end band sequence number

       -offsetvalue, --offsetvalue
              offset value for each spectral band input features: refl[band]=(DN[band]-offset[band])/scale[band]

       -scalevalue, --scalevalue
              scale value for each spectral band input features: refl=(DN[band]-offset[band])/scale[band]

       -a1|2, --aggreg1|2
              how to combine aggregated classifiers, see also --rc option (1: sum rule, 2: max rule).

       --connection0|1
              connection rate (default: 1.0 for a fully connected network)

       -wweights, --weightsweights
              weights for neural network.  Apply to fully connected network only, starting from first input neu‐
              ron to last output neuron, including the bias neurons (last neuron in each but last layer)

       -lrate, --learningrate
              learning rate (default: 0.7)

       --maxitnumber
              number of maximum iterations (epoch) (default: 500)

       -combrule, --combrule
              how to combine bootstrap aggregation classifiers (0: sum rule, 1: product rule, 2: max rule).  Al‐
              so used to aggregate classes with --rc option.  Default is sum rule (0)

       -bagvalue, --bagvalue
              Number of bootstrap aggregations (default is no bagging: 1)

       -bsvalue, --bsizevalue
              Percentage  of  features used from available training features for each bootstrap aggregation (one
              size for all classes, or a different size for each class respectively. default: 100)

       -cbfilename, --classbagfilename
              output for each individual bootstrap aggregation (default is blank)

       --probfilename
              probability image.  Default is no probability image

       -nanumber, --nanumber
              number of active training points (default: 1)

                                                 01 January 2025                                     pkannogr(1)

pkannogr-ttraining [-iinput] [-ooutput] [-cvvalue] [options] [advancedoptions]