基于Landsat影像USGS地表反射率产品的土地利用年际变化成因分析  

Analysis on the causes of inter-annual change of land use based on Landsat imaging USGS surface reflectance product

作　　者：刘安伟[1,2,3] 王红玲 韩立钦[1,2,3] 王利军 王颖洁 Liu Anwei;Wang Hongling;Han Liqin;Wang Lijun;Wang Yingjie(Gansu Industry Polytechnic College,Tianshui 741025,China;Gansu Engineering Research Center of Surveying and Mapping,Tianshui 741000,China;Tianshui City Sub-center,Major Projects for High-resolution Earth Observation Systems,Tianshui 741025,China;National Surveying and Mapping Bureau of Geographical Information,Third Airborne Remote Sensing Institute,Chengdu 610100,China)

机构地区：[1]甘肃工业职业技术学院,甘肃天水741025 [2]甘肃省测绘工程技术研究中心,甘肃天水741000 [3]高分专项甘肃中心天水分中心,甘肃天水741025 [4]国家测绘地理信息局第三航测遥感院,四川成都610100

出　　处：《矿山测量》2019年第4期47-51,共5页Mine Surveying

基　　金：甘肃省天水市科技局2017自然科学基金计划;2018基于中高分辨率遥感影像的生态环境监测平台建设项目;甘肃省教育厅科技成果转化项目(2017D-27)

摘　　要：应用支持向量机机器学习方法,对贵阳市及周边地区Landsat影像USGS地表反射率产品进行分类,通过比较2011~2015年五年区域地表覆盖分类结果图,结合区域工业和建筑业产值数据,分析该区域地表覆盖和土地利用年际变化成因,分析结果表明:(1)5年间随着经济社会的发展,呈现出林地和耕地的面积不断减少的土地利用变化格局;(2)研究区5景影像分类精度较高,总体精度范围91.14%~98.60%,Kappa系数范围0.93~0.98,分类结果真实的反应了研究区地表覆盖及其变化情况。从分析结果来看,优化城市发展空间格局,有序开展植被修复并进行持续遥感监测十分必要。By using the support vectormachine learning method, the Landsat imagery USGS surface reflectance products in the surrounding area of Guiyang were classified. By comparing the classification maps of regional land cover from 2011 to 2015, combining regional industrial and construction industry output data, the causes of the surface cover and the land use interannual variation in the region were analyzed. The results showed:(1) With the development of economy and society in 5 years, the pattern of land use change with declining area of the forest land and the cultivated land was presented;(2) The classification accuracy of 5 scenes was high in the study area, the overall accuracy range was 91.14%~98.60%, Kappa coefficient range was 0.93~0.98, the classification results truly reflected the surface coverage and the changes in the study area. From the analysis results, it was necessary to optimize the spatial pattern of urban development, orderly carry out the vegetation restoration and the continuous remote sensing monitoring.

关 键 词：Landsat影像 支持向量机 地表覆盖 精度分析 

分 类 号：TU4[建筑科学—土工工程]