多源30 m分辨率土地覆被数据在蒙古高原的一致性分析和精度评价  

Consistent Analysis and Accuracy Evaluation of Multisource Land Cover Datasets in 30 m Spatial Resolution over the Mongolian Plateau

作　　者：仝冉 杨雅萍[2,3,4] 陈晓娜 TONG Ran;YANG Yaping;CHEN Xiaona(College of Geography and Environment,Henan University,Kaifeng 475001,China;Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China;National Center for Earth System Science,Institute of Geographic Sciences and Natural Resources Research,Chinese Academy of Sciences,Beijing 100101,China;Collaborative Innovation Center for Development and Utilization of Geographic Information Resources of Jiangsu Province,Nanjing 210023,China)

机构地区：[1]河南大学地理与环境学院,开封475001 [2]中国科学院地理科学与资源研究所,北京100101 [3]国家地球系统科学数据中心,中国科学院地理科学与资源研究所,北京100101 [4]江苏省地理信息资源开发与利用协同创新中心,南京210023

出　　处：《地球信息科学学报》2022年第12期2420-2434,共15页Journal of Geo-information Science

基　　金：蒙古高原资源环境要素综合考察(2019FY102001);中国科学院网络安全和信息化专项(CAS-WX2021SF-0106-03);国家科技基础条件平台建设项目“地球系统科学数据共享网”(2005DKA32300);科学院数据中心(WX145XQ07-11)。

摘　　要：蒙古高原土地覆被的变化表征着区域内生态环境的变化,许多环境问题的研究依赖于准确的土地覆被信息。因此,评估当前全球土地覆被数据在区域尺度上的准确性非常重要。本文以蒙古高原为研究区,从构成相似性、类型混淆程度、空间一致性、绝对精度4个方面,分析了GlobeLand30、GLC_FCS30和FROM_GLC 3种30m高分辨率全球土地覆被数据的一致性和准确性。结果表明:(1) 3种土地覆被数据都显示,草地和裸地是蒙古高原的主要土地覆被类型,任意2种数据的面积序列相关系数都优于0.95;(2) 3种土地覆被数据中完全一致的区域占蒙古高原总面积的61.87%,主要集中在土地表面异质性低的区域;(3) GLC_FCS30数据的总体精度(78.33%)最高,GlobeLand30数据的总体精度(76.85%)次之,FROM_GLC数据的总体精度(75.86%)最低;林地、草地、水体和裸地在3种土地覆被数据中的精度较高(75%以上),灌丛、湿地等地类的精度较低(50%以下)。因此,对蒙古高原土地覆被进行全要素研究时,可以综合考虑选择总体精度最高的GLC_FCS30数据。对特定地类研究的用户,可参考3种土地覆被数据的分类精度有针对性的进行选择。本文可为蒙古高原相关研究选择合适的土地覆被数据提供参考。Land cover changes over the Mongolian Plateau is a key indicator of local ecological environment changes in the region. Numerous of environmental research relies on accurate land cover information. With the vigorous development of geographic information technology and remote sensing technology, a variety of land cover datasets of different resolutions at global scales have emerged, and the free and open sharing of these datasets provides a strong data support for scientific research on global change and regional sustainable development.Therefore, it is important to assess the accuracy of current global land cover datasets at a regional scale. In this study, we analyzed the consistent analysis and accuracy of three 30m global land cover datasets(GlobeLand30dataset, GLC_FCS30 dataset, and FROM_GLC dataset) from the similarity of composition type, the degree of type confusion, spatial consistency, and absolute accuracy. The results show that:(1) The consistent analysis of three land cover datasets show that grassland and bare land are the main land cover types over the Mongolian Plateau, and the area sequence correlation coefficient of any two datasets is better than 0.95.(2) the areas that are completely consistent among the three land cover datasets account for 61.87% of the total area of the Mongolian Plateau, mainly in areas with low land surface heterogeneity.(3) The overall accuracy of GLC_FCS30 dataset(78.33%) is the highest, the overall accuracy of GlobeLand30 dataset(76.85%) is the second, and the overall accuracy of FROM_GLC dataset(75.86%) is the lowest. The accuracy of forest, grassland, water area, and bare land in the three kinds of land cover datasets is generally higher(more than 75%), and the accuracy of shrubland,wetland and other land types is low(less than 50%). Therefore, GLC_FCS30 dataset with the highest overall accuracy can be comprehensively considered when studying the all types of land cover over the Mongolian Plateau. For users who have specific land type research needs, they can refer to

关 键 词：蒙古高原 土地覆被 全球土地覆被数据 土地覆被数据 空间一致性 精度评价 一致性分析 30 m分辨率 

分 类 号：P237[天文地球—摄影测量与遥感]