A Synthesizing Land-cover Classification Method Based on Google Earth Engine: A Case Study in Nzhelele and Levhuvu Catchments, South Africa

作     者：ZENG Hongwei WU Bingfang WANG Shuai MUSAKWA Walter TIAN Fuyou MASHIMBYE Zama Eric POONA Nitesh SYNDEY Mavengahama ZENG Hongwei;WU Bingfang;WANG Shuai;MUSAKWA Walter;TIAN Fuyou;MASHIMBYE Zama Eric;POONA Nitesh;SYNDEY Mavengahama

作者机构：State Key Laboratory of Remote Sensing ScienceAerospace Information Research InstituteChinese Academy of SciencesBeijing 100101China University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Earth Surface Proc-esses and Resource EcologyFaculty of Geographical ScienceBeijing Normal UniversityBeijing 100875China Department of Town and Regional PlanningUniversity of JohannesburgJohannesburg 2028South Africa Department of Geography and Envi-ronmental StudiesStellenbosch UniversityStellenbosch 7600South Africa Department of Crop ScienceFaculty of Natural and Agricultural SciencesNorth West UniversityMmabatho 2745South Africa 

出 版 物：《Chinese Geographical Science》 (中国地理科学（英文版）)

年 卷 期：2020年第30卷第3期

页      面：397-409页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 0834[工学-风景园林学（可授工学、农学学位）] 

基　　金：Under the auspices of National Natural Science Foundation of China(No.4171101213,41561144013,41991232) National Key R&D Program of China(No.2016YFC0503401,2016YFA0600304) International Partnership Program of Chinese Academy of Sciences(No.121311KYSB20170004) 

主　　题：land-cover classification random forest percentile composite Landsat 8 Sentinel-1 Google Earth Engine(GEE) 

摘      要：This study designed an approach to derive land-cover in the South Africa with insufficient ground samples, and made a case demonstration in Nzhelele and Levhuvu catchments, South Africa. The method was developed based on an integration of Landsat 8, Sentinel-1, and Shuttle Radar Topography Mission(SRTM) Digital Elevation Model(DEM), and the Google Earth Engine(GEE) platform. Random forest classifier with 300 trees is employed as land-cover classification model. In order to overcome the defect of insufficient ground data, the stratified sampling method was used to generate the training and validation samples from the existing land-cover product. Likewise, in order to recognize different land-cover categories, the percentile and monthly median composites were employed to expand input metrics of random forest classifier. Results showed that the overall accuracy of the land-cover of Nzhelele and Levhuvu catchments, South Africa in 2017–2018 reached to 76.43%. Three important results can be drawn from our research. 1) The participation of Sentinel-1 data can slightly improve overall accuracy of land-cover while its contribution on land-cover classification varied with land types. 2) Under-fitting problem was observed in the training of non-dominant land-cover categories using the random sampling, the stratified sampling method is recommended to make sure the classification accuracy of non-dominant classes. 3) When related reflectance bands participated in the training process, individual Normalized Difference Vegetation index(NDVI), Enhanced Vegetation Index(EVI), Soil Adjusted Vegetation Index(SAVI), Normalized Difference Built-up Index(NDBI) have little effect on final land-cover classification result.