The first global agricultural field boundary map at 10m resolution

2026-05-11

AI Summary

This study addresses the critical gap in global agricultural monitoring by producing the first 10-meter resolution cropland boundary map for 2024–2025, covering 241 countries and territories. Leveraging cloud-free Sentinel-2 imagery and a U-Net semantic segmentation model, the work delineates 3.17 billion field-level polygons and provides an accompanying 500-meter confidence layer to quantify prediction reliability. Validation across 24 countries demonstrates strong performance, with an average pixel-level recall of 0.85 and F1 scores reaching 0.89 in Austria, 0.88 in Latvia, and 0.74 in Finland. Released in three open-access mapping formats, this dataset establishes a foundational resource for field-scale global cropland mapping, overcoming the limitations of existing pixel-based remote sensing products that lack consistent, high-resolution field boundaries.

Abstract

The agricultural field is the natural unit at which crops are planted, managed, regulated, and reported, yet most global remote-sensing products for agriculture are only available at the pixel level. While some high-quality field-level data products exist, they come from parcel registries covering only parts of Europe or from ML-derived products for individual countries. No openly available, globally consistent map of agricultural field boundaries exists to date. Here we present the first global field boundary dataset at 10\,m resolution for the years 2024 and 2025, comprising 3.17 billion remote-sensing field polygons (1.62 B in 2024 and 1.55 B in 2025) across 241 countries and territories, produced by applying a U-Net segmentation model trained on the Fields of The World dataset to cloud-free Sentinel-2 mosaics. Validated against ground-truth field boundaries in 24 countries, the map achieved a mean pixel-level recall of 0.85 with 14 countries exceeding 0.90. Evaluation against full-country ground-truth datasets in Austria, Latvia, and Finland yielded F1 scores of 0.89, 0.88, and 0.74, respectively. Because reference data for global validation is inherently incomplete, we accompanied the map with a 500 m confidence layer that identifies regions where predictions are reliable. We release the dataset openly as three global maps: the confidence-thresholded default field boundary dataset, the full unfiltered dataset, and the continuous-valued confidence raster. These maps provide the first globally consistent field-level unit of analysis for crop monitoring, food security, and downstream agricultural science.

Problem

• field boundary
• global agricultural map
• remote sensing
• crop monitoring
• food security

Innovation

• field boundary mapping
• U-Net segmentation
• global agricultural monitoring
• Sentinel-2
• confidence layer