构建全球农田边界数据集与工具链，支持精准农业分析。
Fields of The World: A Field Guide for Extracting Agricultural Field Boundaries
- 基于160万块农田数据构建跨24国基准测试集
- 实现有限标注下作物分类宏F1达0.65-0.75
- 提供云端推理工具，支持多国大范围农田分析
农田边界地图是农业数据产品的重要基础，支撑作物监测、产量估计和病害评估。本文介绍全球农田边界（Fields of The World, FTW）生态系统：包含24个国家共160万块农田多边形的基准数据集、预训练分割模型及命令行推理工具。提供两个Notebook：其一支持本地尺度农田边界提取并结合作物分类与森林损失归因；其二利用云优化数据实现国家尺度推理。采用MOSAIKS随机卷积特征与FTW提取的农田边界，在有限标注下实现田块级作物类型分类的宏F1分数为0.65–0.75。最后展示对五个国家（总面积476万平方公里）的预计算结果探索，各国家农田平均面积介于0.06公顷（卢旺达）至0.28公顷（瑞士）之间。
原文摘要 · Abstract (English)
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 km\textsuperscript{2}), with median predicted field areas from 0.06 ha (Rwanda) to 0.28 ha (Switzerland).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。