The first global agricultural field boundary map at 10m resolution

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Robinson, Caleb, Muhawenayo, Gedeon, Khanal, Subash, Fang, Zhanpei, Corley, Isaac, Tárano, Ana M., Estes, Lyndon, Marcus, Jennifer, Jacobs, Nathan, Kerner, Hannah, Becker-Reshef, Inbal, Ferres, Juan M. Lavista
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918494880137216
author Robinson, Caleb
Muhawenayo, Gedeon
Khanal, Subash
Fang, Zhanpei
Corley, Isaac
Tárano, Ana M.
Estes, Lyndon
Marcus, Jennifer
Jacobs, Nathan
Kerner, Hannah
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
author_facet Robinson, Caleb
Muhawenayo, Gedeon
Khanal, Subash
Fang, Zhanpei
Corley, Isaac
Tárano, Ana M.
Estes, Lyndon
Marcus, Jennifer
Jacobs, Nathan
Kerner, Hannah
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_11055
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The first global agricultural field boundary map at 10m resolution
Robinson, Caleb
Muhawenayo, Gedeon
Khanal, Subash
Fang, Zhanpei
Corley, Isaac
Tárano, Ana M.
Estes, Lyndon
Marcus, Jennifer
Jacobs, Nathan
Kerner, Hannah
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
Computer Vision and Pattern Recognition
Machine Learning
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.
title The first global agricultural field boundary map at 10m resolution
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.11055