基于Sentinel-2数据多特征优选的农作物遥感识别研究

陈健, 李虎, 刘玉锋, 常竹, 韩伟杰, 刘赛赛

Crops identification based on Sentinel-2 data with multi-feature optimization

CHEN Jian, LI Hu, LIU Yufeng, CHANG Zhu, HAN Weijie, LIU Saisai

表6 RF_RFE特征优选下基于不同机器学习分类的农作物分类精度

Tab.6 RF_RFE characteristics are preferably based on different crop classification accuracy of machine learning algorithms

机器学习方法 RF SVM MDC 评价指标 PA/% UA/% PA/% UA/% PA/% UA/% 油菜 83.5 88.8 84.7 83.0 80.3 63.5 小麦 96.2 93.2 91.1 91.3 70.8 65.4 OA/% 91.7 91.0 61.2 Kappa 0.89 0.88 0.48