2018-2019年欧盟10国主要农作物10m种植分布数据集

本数据集涵盖了2018-2019年欧盟10个国家冬麦、春麦、玉米和油菜的种植空间分布。基于哨兵2号(Sentinel-2) 遥感影像数据，利用英国和法国可公开获取的地面样本训练随机森林模型，并将模型迁移到欧盟其它缺乏地面样本的国家进行作物分类。基于2万多个LUCAS实地调查样本进行验证，10个国家的主要作物识别总体精度从89%到97%，生产者精度从72%到98%，用户精度从73%到98%。基于NUTS-2级统计面积进行验证，平均决定系数（R2）大于0.9。

This dataset provides spatial distribution data of winter wheat, spring wheat, maize, and oilseed rape cultivation across 10 European Union (EU) member states during 2018–2019. Based on Sentinel-2 remote sensing imagery, a random forest classifier was trained using publicly available ground reference samples from the United Kingdom and France, then deployed to other EU countries lacking ground reference data for crop classification. Validated against over 20,000 LUCAS field survey samples, the overall classification accuracy of major crops in the 10 countries ranges from 89% to 97%, with producer's accuracies spanning 72% to 98% and user's accuracies spanning 73% to 98%. Additional validation using NUTS-2 level statistical areas yielded an average coefficient of determination (R²) greater than 0.9.