The FTW benchmark data includes all the chips and associated imagery to train field boundary models. This repo is starting as a demonstration of how to organize it, and will evolve to be alpha and beta releases of the 2.0 dataset. This catalog is a 'git-backed' Portolan catalog, backed by https://github.com/fieldsoftheworld/benchmark-data-catalog
Benchmark chips for Austria cut from the harmonized field boundary collection for Austria (edition 2025).
This collection holds 11,242 chips and 656,619 field polygons. Each chip is a square STAC item carrying the label masks rasterized from the field boundaries that fall inside it.
Chips per benchmark split:
How much of a chip is mapped field, as a distribution over the chips (field_coverage_pct):
Every chip carries these label rasters as STAC assets: instance_mask, semantic_2class_mask, semantic_3class_mask.
Crops are harmonized to the EuroCrops HCAT taxonomy. The classes covering most of this collection:
Ready-made map styles ship with the collection:
block3x3 strategy, random seed 42id, which carries the grid cell each chip was cut from.items.parquet mirrors every chip item, so the whole collection can be queried without walking the catalog:
See AGENTS.md for the schema, field notes and more queries.
Fields of the World 1.0 published austria with 6686 chips (5304 train / 637 val / 745 test) cut from 196101 parcels declared for 2021, under CC-BY-4.0. This collection has 11242 chips (9018/1153/1071) cut from 656619 fields declared for 2025.