gedi-subsetter/algorithm_config_cwl.yaml at main · MAAP-Project/gedi-subsetter · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
algorithm_name: gedi-subset
algorithm_version: 0.14.0
algorithm_description: >-
  Subset GEDI L1B, L2A, L2B, L4A, or L4C granules within an area of interest (AOI).
keywords: OGC, GEDI
code_repository: https://github.com/MAAP-Project/gedi-subsetter.git
citation: https://zenodo.org/records/15284245
author: MAAP
contributor: MAAP
license: https://github.com/MAAP-Project/gedi-subsetter/blob/main/LICENSE
release_notes: None
docker_container_url: mas.maap-project.org/root/maap-workspaces/custom_images/maap_base:v5.0.0
build_command: gedi-subsetter/bin/build.sh
run_command: gedi-subsetter/bin/subset.sh
ram_min: 8 # mebibytes
cores_min: 2
outdir_max: 20 # mebibytes

inputs:
  - name: aoi
    label: URL of file describing Area of Interest (AOI)
    type: File
    doc: >-
      URL of a file representing the Area of Interest (e.g., GeoJSON file)

  - name: doi
    label: Collection Identifier
    type: string
    doc: >-
      Either the Digital Object Identifier (DOI) or the Concept ID of the
      GEDI collection to subset.  For convenience, one of these logical
      names may be specified instead: L1B, L2A, L2B, L4A, L4C.

  - name: columns
    label: Columns
    type: string
    doc: >-
      One or more column names, separated by commas, to include in the
      output file, each naming a variable (dataset) from the collection.

  - name: query
    label: Query Expression
    type: string
    doc: >-
      Boolean query expression for subsetting the rows of data.  If not
      provided, all rows are included.  For details on query syntax, see
      https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.query.html.

  - name: lat
    label: Latitude Variable
    type: string
    default: lat_lowestmode
    doc: >-
      Name of the variable (dataset) containing latitude values.

  - name: lon
    label: Longitude Variable
    type: string
    default: lon_lowestmode
    doc: >-
      Name of the variable (dataset) containing longitude values.

  - name: temporal
    label: Temporal Range
    type: string
    # We are forced to supply a non-empty default due to MAAP Hub Job UI limitation.
    default: "2018-01-01T00:00:00Z/"
    doc: >-
      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.

  - name: beams
    label: Beams
    type: string
    default: all
    doc: >-
      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).

  - name: limit
    label: Limit
    type: int
    default: 100000
    doc: >-
      Maximum number of GEDI granules to subset, regardless of the number
      of granules within the spatio-temporal range.

  - name: output
    label: Output Filename
    type: string
    default: gedi-subset.parquet
    doc: >-
      Name of the output file produced by the algorithm.  Defaults to using
      the AOI filename (without the extension) with the suffix `_subset`
      and the extension `.gpkg`, resulting in a GeoPackage file format.

      For example, if the AOI were `https://host/path/to/my_aoi.geojson`,
      the default output filename would be `my_aoi_subset.gpkg`.

      When a filename is supplied, it must include a file extension in order
      to infer the output format.  Supported formats inferred from file
      extensions are as follows:

        - FlatGeobuf: `.fgb`
        - GPKG (GeoPackage): `.gpkg`
        - (Geo)Parquet: `.parquet`

      For example, if you prefer a Parquet file as output, you would specify
      a value such as `my_aoi.parquet` (where `my_aoi` can be whatever name
      you prefer).

  - name: tolerated-failure-percentage
    label: Tolerated Failure Percentage
    type: int
    default: 0
    doc: >-
      Integral percentage of individual granule subset failures tolerated
      before causing job failure.  For example, a value of 0 indicates that
      no individual granule failures are tolerated.  Thus, if an error is
      encountered during subsetting of any individual granule, the entire
      job will fail.

      Conversely, a value of 100 indicates that even if an error is
      encountered for every granule, the job will still succeed, resulting
      in an empty output file.

  - name: fsspec-kwargs
    label: "[Advanced] Keyword Arguments for fsspec configuration"
    type: string
    default: "{}"
    doc: >-
      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.

  - name: processes
    label: "[Advanced] Number of Processes"
    type: int
    default: 0
    doc: >-
      Number of processes to use for parallel processing.  If not provided, or
      a value less than 1 is provided, defaults to the number of CPUs available
      on the provisioned instance.

outputs:
  - name: output
    type: Directory