# Fields of The World: A Field Guide for Extracting Agricultural Field Boundaries

arXiv: https://arxiv.org/abs/2602.08131 · HTML: https://mlsanity.com/paper/2602.08131/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery](https://mlsanity.com/paper/2010.08168/) (2020)
- [Deep learning on edge: extracting field boundaries from satellite images with a convolutional neural network](https://mlsanity.com/paper/1910.12023/) (2019)
- [Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation](https://mlsanity.com/paper/2409.16252/) (2024)
- [Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery](https://mlsanity.com/paper/2504.02534/) (2025)
- [A region-wide, multi-year set of crop field boundary labels for Africa](https://mlsanity.com/paper/2412.18483/) (2024)
- [Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions](https://mlsanity.com/paper/2312.08384/) (2023)

## Abstract (arXiv)

Field boundary maps are a building block for agricultural data products and support crop monitoring, yield estimation, and disease estimation. This tutorial presents the Fields of The World (FTW) ecosystem: a benchmark of 1.6M field polygons across 24 countries, pre-trained segmentation models, and command-line inference tools. We provide two notebooks that cover (1) local-scale field boundary extraction with crop classification and forest loss attribution, and (2) country-scale inference using cloud-optimized data. We use MOSAIKS random convolutional features and FTW derived field boundaries to map crop type at the field level and report macro F1 scores of 0.65--0.75 for crop type classification with limited labels. Finally, we show how to explore pre-computed predictions over five countries (4.76M kmtextsuperscript2), with median predicted field areas from 0.06 ha (Rwanda) to 0.28 ha (Switzerland).