当前位置: X-MOL 学术Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Validation of Visually Interpreted Corine Land Cover Classes with Spectral Values of Satellite Images and Machine Learning
Remote Sensing ( IF 4.2 ) Pub Date : 2021-02-25 , DOI: 10.3390/rs13050857
Orsolya Gyöngyi Varga , Zoltán Kovács , László Bekő , Péter Burai , Zsuzsanna Csatáriné Szabó , Imre Holb , Sarawut Ninsawat , Szilárd Szabó

We analyzed the Corine Land Cover 2018 (CLC2018) dataset to reveal the correspondence between land cover categories of the CLC and the spectral information of Landsat-8, Sentinel-2 and PlanetScope images. Level 1 categories of the CLC2018 were analyzed in a 25 km × 25 km study area in Hungary. Spectral data were summarized by land cover polygons, and the dataset was evaluated with statistical tests. We then performed Linear Discriminant Analysis (LDA) and Random Forest classifications to reveal if CLC L1 level categories were confirmed by spectral values. Wetlands and water bodies were the most likely to be confused with other categories. The least mixture was observed when we applied the median to quantify the pixel variance of CLC polygons. RF outperformed the LDA’s accuracy, and PlanetScope’s data were the most accurate. Analysis of class level accuracies showed that agricultural areas and wetlands had the most issues with misclassification. We proved the representativeness of the results with a repeated randomized test, and only PlanetScope seemed to be ungeneralizable. Results showed that CLC polygons, as basic units of land cover, can ensure 71.1–78.5% OAs for the three satellite sensors; higher geometric resolution resulted in better accuracy. These results justified CLC polygons, in spite of visual interpretation, can hold relevant information about land cover considering the surface reflectance values of satellites. However, using CLC as ground truth data for land cover classifications can be questionable, at least in the L1 nomenclature.

中文翻译:

用卫星图像和机器学习的光谱值验证视觉解释的Corine土地覆盖类别

我们分析了Corine Land Cover 2018(CLC2018)数据集,以揭示CLC的土地覆盖类别与Landsat-8,Sentinel-2和PlanetScope图像的光谱信息之间的对应关系。在匈牙利的25 km×25 km研究区域中分析了CLC2018的1级类别。光谱数据通过土地覆盖多边形进行了汇总,并通过统计测试对数据集进行了评估。然后,我们执行了线性判别分析(LDA)和随机森林分类,以揭示CLC L1水平类别是否已通过光谱值确认。湿地和水体最有可能与其他类别混淆。当我们应用中位数来量化CLC多边形的像素方差时,观察到的混合最少。RF的性能优于LDA的精度,PlanetScope的数据最为精确。对班级准确性的分析表明,农业地区和湿地存在分类错误的问题最多。我们通过重复的随机测试证明了结果的代表性,并且只有PlanetScope似乎无法概括。结果表明,CLC多边形作为土地覆盖的基本单位,可以确保三个卫星传感器的OA达到71.1–78.5%。更高的几何分辨率导致更好的精度。这些结果证明,尽管有直观的解释,但考虑到卫星的表面反射率值,CLC多边形仍可以保存有关土地覆盖的相关信息。但是,至少在L1术语中,将CLC用作土地覆盖分类的地面真相数据可能会令人怀疑。我们通过重复的随机测试证明了结果的代表性,并且只有PlanetScope似乎无法概括。结果表明,CLC多边形作为土地覆盖的基本单位,可以确保三个卫星传感器的OA达到71.1–78.5%。更高的几何分辨率导致更好的精度。这些结果证明,尽管有直观的解释,但考虑到卫星的表面反射率值,CLC多边形仍可以保存有关土地覆盖的相关信息。但是,至少在L1术语中,将CLC用作土地覆盖分类的地面真相数据可能会令人怀疑。我们通过重复的随机测试证明了结果的代表性,并且只有PlanetScope似乎无法概括。结果表明,CLC多边形作为土地覆盖的基本单位,可以确保三个卫星传感器的OA达到71.1–78.5%。更高的几何分辨率导致更好的精度。这些结果证明,尽管有直观的解释,但考虑到卫星的表面反射率值,CLC多边形仍可以保存有关土地覆盖的相关信息。但是,至少在L1术语中,将CLC用作土地覆盖分类的地面真相数据可能会令人怀疑。更高的几何分辨率导致更好的精度。这些结果证明,尽管有直观的解释,但考虑到卫星的表面反射率值,CLC多边形仍可以保存有关土地覆盖的相关信息。但是,至少在L1术语中,将CLC用作土地覆盖分类的地面真相数据可能会令人怀疑。更高的几何分辨率导致更好的精度。这些结果证明,尽管有直观的解释,但考虑到卫星的表面反射率值,CLC多边形仍可以保存有关土地覆盖的相关信息。但是,至少在L1术语中,将CLC用作土地覆盖分类的地面真相数据可能会令人怀疑。
更新日期:2021-02-25
down
wechat
bug