The SNAP Graph Processing Tool (gpt)
Usage:
gpt <op>|<graph-file> [options] [<source-file-1> <source-file-2> ...]
Description:
This tool is used to execute SNAP raster data operators in batch-mode. The
operators can be used stand-alone or combined as a directed acyclic graph
(DAG). Processing graphs are represented using XML. More info about
processing graphs, the operator API, and the graph XML format can be found
in the SNAP documentation.
Arguments:
<op> Name of an operator. See below for the list of <op>s.
<graph-file> Operator graph file (XML format).
<source-file-i> The <i>th source product file. The actual number of source
file arguments is specified by <op>. May be optional for
operators which use the -S option.
Options:
-h Displays command usage. If <op> is given, the specific
operator usage is displayed.
-e Displays more detailed error messages. Displays a stack
trace, if an exception occurs.
-t <file> The target file. Default value is './target.dim'.
-f <format> Output file format, e.g. 'GeoTIFF', 'HDF5',
'BEAM-DIMAP'. If not specified, format will be derived
from the target filename extension, if any, otherwise the
default format is 'BEAM-DIMAP'. Ony used, if the graph
in <graph-file> does not specify its own 'Write' operator.
-p <file> A (Java Properties) file containing processing
parameters in the form <name>=<value> or a XML file
containing a a parameter DOM for the operator. Entries in this
file are overwritten by the -P<name>=<value> command-line
option (see below). The following variables are substituted in
the parameters file:
${gpt.operator} (given by the 'op' argument)
${gpt.graphFile} (given by the 'graph-file' argument)
${gpt.parametersFile} (given by the -p option)
${gpt.targetFile} (given by the -t option)
${gpt.targetFormat} (given by the -f option)
-c <cache-size> Sets the tile cache size in bytes. Value can be suffixed
with 'K', 'M' and 'G'. Must be less than maximum
available heap space. If equal to or less than zero, tile
caching will be completely disabled. The default tile
cache size is '512M'.
-q <parallelism> Sets the maximum parallelism used for the computation, i.e.
the maximum number of parallel (native) threads.
The default parallelism is '8'.
-x Clears the internal tile cache after writing a complete
row of tiles to the target product file. This option may
be useful if you run into memory problems.
-T<target>=<file> Defines a target product. Valid for graphs only. <target>
must be the identifier of a node in the graph. The node's
output will be written to <file>.
-S<source>=<file> Defines a source product. <source> is specified by the
operator or the graph. In an XML graph, all occurrences of
${<source>} will be replaced with references to a source
product located at <file>.
-P<name>=<value> Defines a processing parameter, <name> is specific for the
used operator or graph. In an XML graph, all occurrences of
${<name>} will be replaced with <value>. Overwrites
parameter values specified by the '-p' option.
-D<name>=<value> Defines a system property for this invocation.
-v <dir> A directory containing any number of Velocity templates.
Each template generates a text output file along with the
target product. This feature has been added to support a
flexible generation of metadata files.
See http://velocity.apache.org/ and option -m.
-m <file> A (Java Properties) file containing (constant) metadata
in the form <name>=<value> or any XML file. Its primary
usage is to provide an additional context to be used
from within the Velocity templates. See option -v.
--diag Displays version and diagnostic information.
Operators:
AddElevation Creates a DEM band
AddLandCover Creates a land cover band
BandMaths Create a product with one or more bands using mathematical expressions.
Binning Performs spatial and temporal aggregation of pixel values into cells ('bins') of a planetary grid
Collocate Collocates two products based on their geo-codings.
Convert-Datatype Convert product data type
EMClusterAnalysis Performs an expectation-maximization (EM) cluster analysis.
Fill-DEM-Hole Fill holes in given DEM product file.
Flip flips a product horizontal/vertical
GLCM Extract Texture Features
Image-Filter Common Image Processing Filters
Import-Vector Imports a shape file into a product
KDTree-KNN-Classifier KDTree KNN classifier
KMeansClusterAnalysis Performs a K-Means cluster analysis.
KNN-Classifier K-Nearest Neighbour classifier
Land-Cover-Mask Perform decision tree classification
Land-Sea-Mask Creates a bitmask defining land vs ocean.
LandWaterMask Operator creating a target product with a single band containing a land/water-mask.
LinearToFromdB Converts bands to/from dB
Maximum-Likelihood-Classifier Maximum Likelihood classifier
Merge Allows copying raster data from any number of source products to a specified 'master' product.
Minimum-Distance-Classifier Minimum Distance classifier
Mosaic Creates a mosaic out of a set of source products.
NdviOp The retrieves the Normalized Difference Vegetation Index (NDVI).
PCA Performs a Principal Component Analysis.
PixEx Extracts pixels from given locations and source products.
ProductSet-Reader Adds a list of sources
Random-Forest-Classifier Random Forest based classifier
Read Reads a data product from a given file location.
ReplaceMetadata Replace the metadata of the first product with that of the second
Reproject Reprojection of a source product to a target Coordinate Reference System.
Resample Resampling of a multi-size source product to a single-size target product.
StatisticsOp Computes statistics for an arbitrary number of source products.
Subset Create a spatial and/or spectral subset of a data product.
TemporalPercentile Computes percentiles over a given time period.
Terrain-Mask Terrain Mask Generation
ToolAdapterOp Tool Adapter Operator
Unmix Performs a linear spectral unmixing.
Write Writes a data product to a file.
