The first all-season sample set for mapping global land cover with Landsat-8 data

作     者：Congcong Li Peng Gong Jie Wang Zhiliang Zhu Gregory S. Biging Cui Yuan Tengyun Hu Haiying Zhang Qi Wang Xuecao Li Xiaoxuan Liu Yidi Xu Jing Guo Caixia Liu Kwame O. Hackman Meinan Zhang Yuqi Cheng Le Yu Jun Yang Huabing Huang Nicholas Clinton 

作者机构：Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Tsinghua University Beijing 100084 China Department of Environmental Science Policy and Management University of California Berkeley. CA 94720-3J 14 USA Joint Center for Global Change Studies Beijing 100875 China State Key Laboratory of Remote Sensing Science Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences Beijing 100101 China United States Geological Survey Restan VA 20192 USA Ministry of Education Key Laboratory for Geospatial Technology for the Middle and Lower Yellow River Regions College of Environment and Planning Henan University Kaifeng 475004 China Googie Inc. 1600 Amphitheatre Pkwy. Mountain View CA 94042 USA 

出 版 物：《Science Bulletin》 (科学通报（英文版）)

年 卷 期：2017年第62卷第7期

页      面：508-515页

核心收录：

学科分类：081603[工学-地图制图学与地理信息工程] 081802[工学-地球探测与信息技术] 07[理学] 08[工学] 070503[理学-地图学与地理信息系统] 0818[工学-地质资源与地质工程] 0705[理学-地理学] 0816[工学-测绘科学与技术] 

基　　金：partially supported by the National High Technology Program(2013AA122804) the Special Fund for Meteorology Scientific Research in the Public Welfare(GYHY201506023)of China Open Fund of State Key Laboratory of Remote Sensing Science(OFSLRSS201514) 

主　　题：Training sample Validation Latitudinal zones Anytime Anywhere 

摘      要：We report the world s first all-season training and validation sample sets for global land cover classification with Landsat-8 *** to this,such samples were only available at a single date primarily from the growing *** is unknown how much limitation such a single-date sample has to mapping global land cover in other seasons of the *** answer this question,we selected available Landsat-8 images from four seasons and collected training and validation samples from *** compared the performances of training samples in different seasons using Random Forest *** found that the use of training samples from any individual season would result in the best overall classification accuracy when validated by samples in the same *** global overall accuracy from combined best seasonal results was 67.2% when classifying the 11 Level-1 classes in the Finer Resolution Observation and Monitoring of Global Land Cover(FROM-GLC) classification *** use of training samples from all seasons(named all-season training sample set hereafter) produced an overall accuracy of 67.0%.We also tested classification within 10° latitude 60° longitude zones using all-season training subsample within each zone and obtained an overall accuracy of 70.2%.This indicates that properly grouped subsamples in space can help improve classification *** the results in this study seem to suggest that it is possible to use an all-season training sample set to reach global optimality with universal applicability in classifying images acquired at any time of a year for global land cover mapping.