高寒湿地分类的遥感特征优选研究  

Remote sensing feature selection for alpine wetland classification

作　　者：霍轩琳 牛振国 张波 刘林崧 李霞[3] HUO Xuanlin;NIU Zhenguo;ZHANG Bo;LIU Linsong;LI Xia(School of Earth Science and Resources,Chang’an University,Xi’an 710054,China;State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;School of Land Engineering,Chang’an University,Xi’an 710054,China)

机构地区：[1]长安大学地球科学与资源学院,西安710054 [2]中国科学院空天信息创新研究院遥感科学国家重点实验室,北京100094 [3]长安大学土地工程学院,西安710054

出　　处：《遥感学报》2023年第4期1045-1060,共16页NATIONAL REMOTE SENSING BULLETIN

基　　金：国家重点研发计划“政府间国际科技创新合作”重点专项(编号:2021YFE0194700);第二次青藏高原综合科学考察研究项目(编号:2019QZKK0106);国家自然科学基金(编号:41971390)。

摘　　要：高寒湿地是青藏高原重要的地表覆盖类型之一,对于水源涵养、调节气候、维护生物多样性等起着关键作用,准确及时获知高寒湿地的时空分布对于湿地的保护和管理十分必要。遥感分类特征优选对湿地制图具有关键性的作用。虽然像光谱特征、纹理特征、地形特征等均在已有研究中有涉及,但鲜有研究聚焦光谱指数特征,深入探讨其数理统计特征和特征优选方法。本研究以甘肃首曲高寒湿地保护区为研究区,基于Sentinel-2数据得到各分类特征(光谱、植被指数、红边指数和水体指数),采用Filter和Wrapper特征选择方法包括Jeffries-Matusita距离、光谱角距离(SAD)、欧氏距离(ED)、RF-RFE算法和Relief-F算法对上述特征进行优选,并利用Filter方法的Z检验进行量化评价。研究表明:(1)所有参与分类的类别中,河流与裸地最容易区分,其次为草原与沼泽,沼泽化草甸与草甸较为难分。对沼泽、沼泽化草甸、草甸、草原邻近两类可尝试MCARI2、NDWI、DVI、EVI、EWI、IRECI、MCARI、TCARI、UGWI指数进行区分;(2)就不同指数特征对湿地信息提取贡献程度而言,水体指数特征>植被指数特征>红边指数特征;(3)从特征优选方法角度看,Filter方法中的ED距离算法与Relief-F算法表现突出;(4)最终选出适于高寒湿地信息提取的指数有RDVI、NDVI、MSR、RVI、VIgreen、RNDWI、NDWI、NDWI_B、MNDWI、EWI、CIre;(5)从不同分类特征的数理统计指标看,中值特征的分类结果最好,其次是平均值特征。本研究为湿地信息提取在特征变量优选方面提供了一种可迁移且普适性高的方法和思路。Alpine wetlands are an important surface cover type on the Qinghai―Tibet Plateau because they play a key role in water conservation,climate regulation,and biodiversity maintenance.Accurate and timely knowledge of the temporal and spatial distribution of alpine wetlands is necessary for wetland protection and management.The selection of remote sensing classification features is crucial in wetland mapping.Although spectral,texture,and topographic features have been investigated,studies focusing on spectral index features and their mathematical statistical features and feature selection methods are limited.This study aims to classify alpine wetlands from the aspects of mathematical statistical features,alpine wetland types,feature selection methods,and selected feature sets combined with random forest classification algorithm using Sentinel-2 image data and taking the Shouqu Alpine Wetland Reserve as the research site.An in-depth and comprehensive analysis on the spectral index characteristics of alpine wetlands is performed to optimize the classification characteristics of alpine wetlands.The Gansu Shouqu Alpine Wetland Reserve was used as the research area,and classification characteristics(spectrum,vegetation index,red edge index,and water body index) were obtained on the basis of Sentinel-2 data.Filter and wrapper feature selection methods,including Jeffries – Matusita distance,Spectral Angular Distance(SAD),Euclidean Distance(ED),RF-RFE algorithm,and Relief-F algorithm are utilized to optimize these features.Meanwhile,Z test is applied for quantitative evaluation.The following conclusions can be drawn from this study.(1) Among the categories of alpine wetlands involved in the classification,rivers and bare land are the easiest to distinguish,followed by grasslands and swamps and then swampy meadows and meadows.MCARI2,NDWI,DVI,EVI,EWI,IRECI,MCARI,TCARI,and UGWI indices can be used to differentiate among adjacent swamps,swampy meadows,meadows,and grasslands.(2) The order of contribution of different index cha

关 键 词：遥感 湿地分类 高寒湿地 特征优选 青藏高原 Sentinel-2 

分 类 号：P2[天文地球—测绘科学与技术]