Global Fields of The World (FTW)

Taylor Geospatial Engine Labs presents global estimates of agricultural fields for the years 2024 and 2025 built with RasterFlow (a Wherobots Inc. product). Raster results are provided in Zarr V3; vector results in GeoParquet and PMTiles format.

Current Versions

• features: alpha
• predictions: alpha using the PRUE Model on Hugging Face.

Features: COGs

Location: s3://us-west-2.opendata.source.coop/tge-labs/ftw-global-data/features/cogs/alpha/.

Inputs are defined by selecting DOY ranges (planting/harvest heuristics) and computing the median of valid pixels across ~5–10 scenes. See Appendix for additional information.

• s2med_harvest/*:

  • Contains bands ["B02", "B03", "B04", "B08", "N_VALID_PIXELS"]
  • Each band is the median over the respective sentinel2 scenes.
  • N_VALID_PIXELS is the number of valid scenes after quality-flag masking.

• s2med_planting/*:

  • Contains bands ["B02", "B03", "B04", "B08", "N_VALID_PIXELS"]
  • Each band is the median over the respective sentinel2 scenes.
  • N_VALID_PIXELS is the number of valid scenes after quality-flag masking.

• index.parquet:

  1import geopandas as gpd
  2
  3gpd.read_parquet("s3://data.source.coop/tge-labs/ftw-global-data/features/cogs/alpha/index.parquet")
  1import geopandas as gpd
  2
  3gpd.read_parquet("s3://data.source.coop/tge-labs/ftw-global-data/features/cogs/alpha/index.parquet")
  

  

Features: Zarr Mosaic

Location: s3://data.source.coop/tge-labs/ftw-global-data/features/zarr/alpha/global.zarr

We reproject and resample all feature COGs to EPSG:4326 at 8.983119e-5° (~10 m at the equator) using GDAL cubic resampling, producing a single Zarr mosaic with dimensions (time, band, y, x).

1import rasterix
2import xarray as xr
3
4features = xr.open_zarr(
5    "s3://data.source.coop/tge-labs/ftw-global-data/features/zarr/alpha/global.zarr"
6).pipe(rasterix.assign_index)
7features
1import rasterix
2import xarray as xr
3
4features = xr.open_zarr(
5    "s3://data.source.coop/tge-labs/ftw-global-data/features/zarr/alpha/global.zarr"
6).pipe(rasterix.assign_index)
7features

Predictions: Zarr Mosaic

Location: s3://data.source.coop/tge-labs/ftw-global-data/predictions/zarr/alpha/global.zarr

We run the PRUE model over features/zarr/alpha/global.zarr to generate a stackable Zarr dataset with bands ["non_field_background","field","field_boundaries"]. Note that the feature and predictions zarr datasets share the same grid and are "stackable".

1features = xr.open_zarr(
2    "s3://data.source.coop/tge-labs/ftw-global-data/predictions/zarr/alpha/global.zarr"
3).pipe(rasterix.assign_index)
4features
1features = xr.open_zarr(
2    "s3://data.source.coop/tge-labs/ftw-global-data/predictions/zarr/alpha/global.zarr"
3).pipe(rasterix.assign_index)
4features

Predictions: GeoParquet [WIP]

• Predictions as Vector data product

Predictions: PMTiles [WIP]

• Predictions as PMTiles data product

Future Work

Future work may include but is not limited to:

1. Adding Predictions as COGs (and corresponding index)
2. Creating Multiscale Prediction Zarr Mosaics for scalable visualization.
3. More robust gap filling for multi-scene median composites.
4. More robust planting and harvest season definitions.
5. STAC GeoParquet index(es) with data lineage showing exactly which scenes were used for median composition.

Appendix

Features: Season Heuristics (alpha)

We determine relevant Sentinel-2 scenes by acquisition dates according to the following functions:

1def tile_to_planting_season_heuristic_doy(point: Point) -> tuple[int, int]:
2    lat = point.y
3    abs_lat = abs(lat)
4    if abs_lat > 45:
5        start_doy, end_doy = (91, 151) if lat > 0 else (274, 334)  # Apr-May or Oct-Nov
6    elif 20 < abs_lat <= 45:
7        start_doy, end_doy = (60, 120) if lat > 0 else (244, 334)  # Mar-Apr or Sep-Nov
8    elif 5 < abs_lat <= 20:
9        start_doy, end_doy = (121, 212) if lat > 0 else (305, 365)  # May-Jul or Nov-Dec
10    else:  # Equatorial
11        start_doy, end_doy = (60, 121)  # Approx. Mar-Apr and Sep-Oct (simplified)
12    return start_doy, end_doy
13
14
15def tile_to_harvest_season_heuristic_doy(point: Point) -> tuple[int, int]:
16    lat = point.y
17    abs_lat = abs(lat)
18    if abs_lat > 45:
19        start_doy, end_doy = (244, 304) if lat > 0 else (60, 151)  # Sep-Oct or Mar-May
20    elif 20 < abs_lat <= 45:
21        start_doy, end_doy = (213, 304) if lat > 0 else (32, 120)  # Aug-Oct or Feb-Apr
22    elif 5 < abs_lat <= 20:
23        start_doy, end_doy = (274, 365) if lat > 0 else (91, 181)  # Oct-Dec or Apr-Jun
24    else:  # Equatorial
25        start_doy, end_doy = (182, 243)  # Approx. Jul-Aug and Jan-Feb (simplified)
26    return start_doy, end_doy
1def tile_to_planting_season_heuristic_doy(point: Point) -> tuple[int, int]:
2    lat = point.y
3    abs_lat = abs(lat)
4    if abs_lat > 45:
5        start_doy, end_doy = (91, 151) if lat > 0 else (274, 334)  # Apr-May or Oct-Nov
6    elif 20 < abs_lat <= 45:
7        start_doy, end_doy = (60, 120) if lat > 0 else (244, 334)  # Mar-Apr or Sep-Nov
8    elif 5 < abs_lat <= 20:
9        start_doy, end_doy = (121, 212) if lat > 0 else (305, 365)  # May-Jul or Nov-Dec
10    else:  # Equatorial
11        start_doy, end_doy = (60, 121)  # Approx. Mar-Apr and Sep-Oct (simplified)
12    return start_doy, end_doy
13
14
15def tile_to_harvest_season_heuristic_doy(point: Point) -> tuple[int, int]:
16    lat = point.y
17    abs_lat = abs(lat)
18    if abs_lat > 45:
19        start_doy, end_doy = (244, 304) if lat > 0 else (60, 151)  # Sep-Oct or Mar-May
20    elif 20 < abs_lat <= 45:
21        start_doy, end_doy = (213, 304) if lat > 0 else (32, 120)  # Aug-Oct or Feb-Apr
22    elif 5 < abs_lat <= 20:
23        start_doy, end_doy = (274, 365) if lat > 0 else (91, 181)  # Oct-Dec or Apr-Jun
24    else:  # Equatorial
25        start_doy, end_doy = (182, 243)  # Approx. Jul-Aug and Jan-Feb (simplified)
26    return start_doy, end_doy

Features: Sentinel-2 Source

All sentinel2 scenes were sourced from s3://sentinel-cogs/sentinel-s2-l2a-cogs.

Features: Sentinel-2 SCL Flags

We use the following quality flags to mark sentinel2 bands as invalid as provided in the SCL band:

• 0: No Data
• 1: Saturated Defective
• 3: Cloud Shadow
• 7: Cloud Low Probability / Unclassified
• 8: Cloud Medium Probability
• 9: Cloud High Probability
• 10: Thin Cirrus

Contact

Email: len@wherobots.com