algorithm_config.yaml

algorithm_description: Subset GEDI L1B, L2A, L2B, L4A, or L4C granules within an area of interest (AOI)
algorithm_name: gedi-subset
algorithm_version: 0.9.0
repository_url: https://github.com/MAAP-Project/gedi-subsetter.git
docker_container_url: mas.maap-project.org/root/maap-workspaces/custom_images/maap_base:v4.1.0
disk_space: 20GB
queue: maap-dps-worker-32vcpu-64gb
build_command: gedi-subsetter/bin/build-dps
run_command: gedi-subsetter/bin/subset.sh
inputs:
  config: []
  file:
    - name: aoi
      description: URL of a file representing the Area of Interest (e.g., GeoJSON file)
      required: true
      default: ""
  positional:
    - name: doi
      description: "Digital Object Identifier (DOI) of the GEDI collection to subset,
        or one of these logical names: L1B, L2A, L2B, L4A"
      required: true
      default: ""
    - name: lat
      description: Name of the dataset containing latitude values
      required: true
      default: ""
    - name: lon
      description: Name of the dataset containing longitude values
      required: true
      default: ""
    - name: columns
      description: One or more column names, separated by commas, to include in the
        output file
      required: true
      default: ""
    - name: query
      description: Boolean query expression for subsetting the rows in the output file.
        If not provided, all rows are included.  See
        https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.query.html.
      required: false
      default: ""
    - name: temporal
      description: Temporal range to subset, formatted as an ISO 8601 Time Interval.
        For example, 2021-01-01T00:00:00Z/2021-12-31T23:59:59Z.  See
        https://en.wikipedia.org/wiki/ISO_8601#Time_intervals.  If not provided,
        the entire temporal range of the GEDI collection is used.
      required: false
      default: ""
    - name: beams
      description: "Which beams to include: all, coverage, power, or a comma-separated
        list of specific beam names, with or without the BEAM prefix (e.g.,
        BEAM0000,BEAM0001 or 0000,0001)"
      required: false
      default: all
    - name: limit
      description: Maximum number of GEDI granules to subset, regardless of the number
        of granules within the spatio-temporal range.
      required: false
      default: "100_000"
    - name: output
      description: Name of the output file produced by the algorithm.  Defaults to
        using the AOI file name (without the extension) with the suffix "_subset.gpkg".
      required: false
      default: ""
    - name: fsspec_kwargs
      description: "JSON object representing keyword arguments to pass to the
        fsspec.core.url_to_fs function when reading granule data files.  See
        https://filesystem-spec.readthedocs.io/en/latest/api.html#fsspec.core.url_to_fs."
      required: false
      default: '{"default_cache_type": "all", "default_block_size": 8388608}'
    - name: processes
      description: Number of processes to use for parallel processing.  If not provided,
        defaults to the number of available CPUs.
      required: false
      default: ""
    - name: scalene_args
      description: Arguments to pass to Scalene for memory and CPU profiling.  If not
        provided, Scalene will not be used.
      required: false
      default: ""