基于GEE的地表覆盖与气候状态关联研究  

Research on the correlation between land cover and climatic status based on Google Earth Engine

作　　者：陈伟 刘湘媛 曾圣 张华平 毛志芳 CHEN Wei;LIU Xiangyuan;ZENG Sheng;ZHANG Huaping;MAO Zhifang(Jiangxi Provincial Bureau of Coal Geology Surveying and Mapping Team,Nanchang 330001,China)

机构地区：[1]江西省煤田地质局测绘大队,江西南昌330001

出　　处：《测绘通报》2021年第12期99-104,共6页Bulletin of Surveying and Mapping

摘　　要：为探究地表覆盖与气候状态间的关联性,本文选取2019年的Landsat影像数据,结合温度、降水量、PM_(2.5)浓度3种气候指标,利用GEE平台,结合NDVI、MNDWI、NDBI,采用SVM、RF、CART方法进行地表覆盖分类,探究气候指标与地表覆盖类型分布的关联性;提出了使用3种气候指标构建分类特征进行地表覆盖分类的方法,并通过消融试验分析了气候指标对地表覆盖分类精度的影响。结果表明:①RF有较好的分类结果,总体精度为96.0%;②3种气候指标均能提高地表覆盖分类精度,其中PM_(2.5)浓度效果最好;③温度与植被、水体关联性较大,PM_(2.5)浓度与城区、植被关联性较大,降水量与耕地关联性较大。In order to explore the correlation between surface cover and climate status, this paper selects Landsat image data in 2019 and three climate indicators using temperature, precipitation and PM_(2.5)concentration, by GEE platform, combined with NDVI, MNDWI and NDBI, and uses SVM, RF and cart methods to classify surface cover, so as to explore the correlation between climate indicators and surface cover type distribution. The method of using three climate indicators to construct classification features for land cover classification is proposed, and the influence of climate indicators on the accuracy of land cover classification is analyzed through ablation experiments. The results show that:①RF has good classification results, and the overall accuracy is 96.0%;②The three climate indexes can improve the accuracy of surface cover classification, and the concentration of PM_(2.5) is the best;③Temperature is closely related to vegetation and water body, PM_(2.5) concentration is highly correlated with urban area and vegetation, precipitation is closely related to cultivated land.

关 键 词：地表覆盖 气候 PM GEE 关联性 分类 

分 类 号：P237[天文地球—摄影测量与遥感]