科尔沁沙丘草甸相间地区土地利用与覆被识别  被引量:5

Land use and land cover classifications of Horqin Sandy Land dune-meadow areas

在线阅读下载全文

作  者:曹文梅[1] 刘廷玺[1] 王喜喜[2] 王冠丽[1] 李东方[1] 童新[1] CAO Wenmei;LIU Tingxi;WANG Xixi;WANG Guanli;LI Dongfang;TONG Xing(Water Conservancy and Civil Engineering College,Inner Mongolia Agricultural University,Inner Mongolia Water Resource Protection and Utilization Key Laboratory,Hohhot 010018,Inner Mongolia,China;Civil and Environmental Engineering,Old Dominion University,Norfolk 23529,Virginia,USA)

机构地区:[1]内蒙古农业大学水利与土木建筑工程学院,内蒙古自治区水资源保护与利用重点实验室,内蒙古呼和浩特010018 [2]美国欧道明大学,诺福克23529

出  处:《干旱区研究》2021年第2期526-535,共10页Arid Zone Research

基  金:国家自然科学基金重点国际(地区)合作研究项目和地区项目(51620105003,51769020);内蒙古自然科学基金重大项目、教育部创新团队发展计划项目(IRT_17R60);科技部重点领域科技创新团队(2015RA4013);内蒙古自治区草原英才产业创新创业人才团队资助。

摘  要:为了实现基于单独光学遥感数据对科尔沁沙丘草甸相间地区土地利用与覆被(LULC)类型的识别,选用2018年64景Sentinel-2影像,结合影像分割技术,利用植被物候信息和生境特征,建立了基于群落水平的LULC决策树识别规则,总体分类精度为0.91,Kappa系数为0.89。分类结果显示:研究区旱地分布面积最大,占33.79%,灌木群落次之,占25.03%,高多样性半灌木群落和乔木林相近,分别为14.54%和10%,低多样性半灌木群落、草甸地和流动沙地分别占5%左右,剩余类型的总占比小于5%。该方法不仅可以准确反映研究区覆被类型的空间分布情况,还能给出不同覆被类型的生长发育状况,可为该区域物质循环研究提供基础数据,同时为该区域历史LULC识别提供阈值参考。In this study,we determine land use/land cover(LULC)types using only optical remote sensing data in a dune-meadow area of Horqin Sandy Land in northeast China.We used 64 Sentinel-2 remote sensing images from 2018.An LULC decision tree recognition rule was established by combining image segmentation technology,vegetation phenology information,and habitat characteristics.The overall classification accuracy was 0.91,and the Kappa coefficient was 0.89.The classification results show that most of the study region was dryland area,accounting for 33.79%,followed by shrub communities at 25.03%.High-diversity semi-shrub communities and arbor forests accounted for 14.54% and 10%,respectively,while low-diversity semi-shrub communities,meadowlands,and mobile sand lands account for about 5% each.The total proportion of other LULC types was less than 5%.The results show that this interpretation method better reflects the spatial distribution of the LULC while also providing growth and development data for different cover types.These data can be used to study material cycles and provide threshold references for historical LULC identification of Horqin Sandy Land.

关 键 词:遥感 土地利用与覆被 多尺度分割 决策树 分类 哨兵2号卫星 多时相 科尔沁沙地 

分 类 号:Q948[生物学—植物学] P237[天文地球—摄影测量与遥感]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象