基于Sentinel-2影像的雄安新区2016—2019年土地利用分析

雄安新区是国家层面打造的又一个具有重要战略意义的新区,及时准确掌握该地区的土地利用详情具有重要意义。本文利用10 m分辨率的Sentinel-2影像对雄安新区2016—2019年的土地利用进行分类,进而分析该地区的土地利用时空演变。共测试了决策树、随机森林和支持向量机3种分类器,进而获得最高精度的土地分类结果图;同时,利用随机森林的特征排序功能分析了不同特征的重要性。结果表明,雄安新区的耕地、林地、水生植物面积总体均呈显著减少趋势,建设用地面积变化最为显著,表明雄安新区正在进行中、快速的城市化发展。本研究得到的10 m分辨率土地利用专题图和分析结果对于雄安新区的及时监测与规划有着重要参考意义。

Analysis of land use change in Xiong' an New Area from 2016 to 2019 based on the Sentinel-2 images

The Xiong'an New Area is another strategically important new area established at the national level. It is of great significance to grasp the details of land use in this area. In this study, the 10 m Sentinel-2 images were used to classify the land use from 2016 to 2019, and the spatio-temporal land use changes were then analyzed. This study first tested three popular classifiers including decision tree, random forest, and support vector machine to obtain the highest-accuracy land use map. Meanwhile, the importance of different features was analyzed. The results showed that in Xiong'an New Area, the land use types and areas have undergone significant changes. Among them, the area of arable land, woodland, and aquatic plants all showed a significant reduction trend, and the area of construction land has increased a lot, indicating that the Xiong'an New Area was undergoing rapid urbanization. The 10 m land use maps obtained in this study have important reference significance for the timely monitoring and planning of Xiong'an New Area.