Sponsored by Taylor Geospatial, the Global Fields of The World (FTW) dataset provides global-scale estimates of agricultural fields for 2024–2025. The dataset includes both model inputs (Sentinel-2–derived median composites in COG and Zarr v3 formats) and outputs (in Zarr, GeoParquet and PMTiles).
# Model entropy (500 m) — Fields of the World / PRUE
Mean Shannon entropy of the PRUE softmax outputs across the 10 m pixels in each 500 m cell, computed separately for the field and field-boundary classes. A model-internal uncertainty indicator (higher = less certain) used as a feature of the confidence model. See the Methods (Quality indicator computation) of [Robinson et al. 2026](https://arxiv.org/abs/2605.11055). Temporal basis inferred as 2025; pending author confirmation.
**Part of:** [FTW Global — Prediction Confidence & Quality Layers](../collection.json) · [Fields of the World](https://fieldsofthe.world)
**Paper:** [Robinson et al. 2026](https://arxiv.org/abs/2605.11055)
**License:** [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
**Temporal:** 2024-01-01 – 2025-12-31 (inferred 2025 from paper; pending author confirmation)
## How to access
Base URL: `https://data.source.coop/ftw/global-data/predictions/confidence/entropy/`
Common grid: EPSG:4326, 86400×34560 px, bbox [-180, -60, 180, 84], ~0.004167°/px (~500 m). All files are Cloud-Optimized GeoTIFFs (range-request friendly).
| Asset | File | CRS | Bands | Size |
|---|---|---|---|---|
| `data` | `prue_v1_entropy_500m.tif` | EPSG:4326 | 2 | 2.2 GB |
```python
import rasterio
url = "https://data.source.coop/ftw/global-data/predictions/confidence/entropy/prue_v1_entropy_500m.tif"
with rasterio.open(url) as ds: # COG: only the bytes you read are fetched
arr = ds.read(1, masked=True) # add window=... to subset by bbox
```
Browser preview (titiler): `https://titiler.xyz/cog/preview.png?url=https://data.source.coop/ftw/global-data/predictions/confidence/entropy/prue_v1_entropy_500m.tif&rescale=0,20&colormap_name=magma&bidx=1`
## Bands
| Asset | Band | dtype | nodata | range (min–max) | Meaning |
|---|---|---|---|---|---|
| `data` | `mean_entropy_field` | float32 | — | 0 – 251 | Mean per-pixel Shannon entropy of the field class within the cell |
| `data` | `mean_entropy_boundary` | float32 | — | 0 – 250 | Mean per-pixel Shannon entropy of the field-boundary class within the cell |
## Notes
- Stored values exceed the raw 3-class Shannon-entropy range (≈0–1.1), so treat the layer as a relative uncertainty indicator rather than entropy in nats; see the paper Methods.
## Related layers
- [Modeled confidence layer (500 m)](../confidence/confidence.json)
- [Field & boundary prediction density (500 m)](../field-density/field-density.json)
- [Cropland consensus count (500 m)](../crop-consensus/crop-consensus.json)
- [Precision & recall vs cropland agreement (500 m)](../precision-recall/precision-recall.json)
- Collection: [collection.json](../collection.json) · [README](../README.md)
## Cite
Robinson, C., Muhawenayo, G., Khanal, S., Fang, Z., Corley, I., Tárano, A. M., Estes, L., Marcus, J., Jacobs, N., Kerner, H., Becker-Reshef, I., & Lavista Ferres, J. M. (2026). The first global agricultural field boundary map at 10 m resolution. arXiv:2605.11055.