Testing Accuracy of Land Cover Classification Algorithms in the Qilian Mountains Based on GEE Cloud Platform
Testing Accuracy of Land Cover Classification Algorithms in the Qilian Mountains Based on GEE Cloud Platform
复制标题
基于GEE云平台的祁连山土地覆盖分类算法精度测试
DOI：
10.3390/rs13245064
复制
发表时间：
2021-12
期刊：
影响因子：
5
通讯作者：
Nawaz Zain
中科院分区：
文献类型：
--
作者：
Yang Yanpeng;Yang Dong;Wang Xufeng;Zhang Zhao;Nawaz Zain
祁连山是中国西部重要的生态屏障。高精度土地覆盖数据产品是准确检测和评价祁连山生态服务功能的基础数据。为了研究QLM中的土地覆盖以及不同遥感分类算法在基于Google Earth Engine（GEE）云平台的土地覆盖制图中的性能，采用了空间分辨率较高的Sentinel-1和Sentinel-2遥感影像、数字高程数据、遥感影像数据和遥感影像数据。支持向量机（SVM）、分类回归树（CART）、和随机森林（RF）算法，被用来执行监督分类的哨兵-2图像的QLM。在此基础上，对不同遥感分类算法和特征变量组合的分类结果进行了对比分析。结果表明：（1）不同遥感分类算法的分类精度不同，RF的分类精度最高，CART和SVM次之;（2）不同的特征变量组合对分类结果的总体精度（OA）和不同土地覆盖类型的识别分类性能有不同的影响;与现有的QLM土地覆盖产品相比，本研究获得的土地覆盖图具有更高的空间分辨率和整体精度。
The Qilian Mountains (QLM) are an important ecological barrier in western China. High-precision land cover data products are the basic data for accurately detecting and evaluating the ecological service functions of the QLM. In order to study the land cover in the QLM and performance of different remote sensing classification algorithms for land cover mapping based on the Google Earth Engine (GEE) cloud platform, the higher spatial resolution remote sensing images of Sentinel-1 and Sentinel-2; digital elevation data; and three remote sensing classification algorithms, including the support vector machine (SVM), the classification regression tree (CART), and the random forest (RF) algorithms, were used to perform supervised classification of Sentinel-2 images of the QLM. Furthermore, the results obtained from the classification process were compared and analyzed by using different remote sensing classification algorithms and feature-variable combinations. The results indicated that: (1) the accuracy of the classification results acquired by using different remote sensing classification algorithms were different, and the RF had the highest classification accuracy, followed by the CART and the SVM; (2) the different feature variable combinations had different effects on the overall accuracy (OA) of the classification results and the performance of the identification and classification of the different land cover types; and (3) compared with the existing land cover products for the QLM, the land cover maps obtained in this study had a higher spatial resolution and overall accuracy.
登录
查看更多内容
DOI：
10.3390/rs11091056
发表时间：
2019-05
期刊：
Remote. Sens.
影响因子：
--
作者：
Xiao Zhang;Liangyun Liu;Xidong Chen;Shuai Xie;Yuan Gao
通讯作者：
Xiao Zhang;Liangyun Liu;Xidong Chen;Shuai Xie;Yuan Gao
影响因子：
4
作者：
Abdel-Hamid, Ayman;Dubovyk, Olena;Greve, Klaus
通讯作者：
Greve, Klaus
影响因子：
13.5
作者：
Xiao, XM;Boles, S;Moore, B
通讯作者：
Moore, B
影响因子：
3.4
作者：
H. Zeng;Bingfang Wu;Shuai Wang;W. Musakwa;Fuyou Tian;Zama Eric Mashimbye;Nitesh K. Poona;Mavengahama Syndey
通讯作者：
H. Zeng;Bingfang Wu;Shuai Wang;W. Musakwa;Fuyou Tian;Zama Eric Mashimbye;Nitesh K. Poona;Mavengahama Syndey
DOI：
10.3390/rs13081596
发表时间：
2021-04
期刊：
Remote. Sens.
影响因子：
--
作者：
B. Zhong;A. Yang;Kunsheng Jue;Junjun Wu
通讯作者：
B. Zhong;A. Yang;Kunsheng Jue;Junjun Wu