应用谷歌地球引擎和多维特征集构建的艾比湖流域长时序景观分类模型  

Long-Term Landscape Classification Model for the Ebi Lake Basin Constructed Using Google Earth Engine and Multidimensional Feature Sets

作　　者：雷焯越 蒲智[1] 周军[1] Lei Zhuoyue;Pu Zhi;Zhou Jun(Xinjiang Agricultural University,Urumqi 830000,P.R.China)

机构地区：[1]新疆农业大学,乌鲁木齐830000

出　　处：《东北林业大学学报》2025年第2期97-104,共8页Journal of Northeast Forestry University

基　　金：国家自然科学基金项目(62161048)。

摘　　要：以新疆艾比湖流域为研究区域,整合历史遥感影像数据与现场地表特征考察,将艾比湖流域景观类型划分为6类(耕地、林地、草地、水域、建设用地、未利用地);以谷歌地球引擎(GEE)平台提供的艾比湖流域2002—2023年(2002、2008、2013、2018、2023年)的陆地卫星(Landsat)影像为基础数据源,以艾比湖流域长时序景观分类为评价指标,光谱指数(归一化植被指数、增强植被指数、归一化水体指数、归一化建筑指数)、地形特征(海拔、坡度、坡向)、纹理特征(角二阶矩阵、对比度、相关性、熵、协方差、逆方差、总和平均值)为影响因素,从光谱指数、地形特征、纹理特征三个角度构建并筛选最优多维特征模型;分别运用分类回归树(CART)、随机森林(RF)、梯度提升树(GBT)、支持向量机(SVM)机器学习算法,对艾比湖流域长时序景观信息进行自动分类,对比4种机器学习算法的分类精度,遴选最适用于艾比湖流域的景观分类模型。结果表明:(1)应用谷歌地球引擎云计算平台,能够高效处理、分析及可视化研究区近22 a的景观分类结果。(2)3类特征重要性,由大到小依次为光谱指数(31.52%)、地形特征(17.18%)、纹理特征(3.83%)。地形特征在单一特征中分类精度最高;光谱特征联合纹理特征,在双特征配置中对提高研究区景观分类精度呈现出较好效果;而整合光谱指数、地形特征、纹理特征的模型,能够在任一特征组合的基础上有效提高研究区景观分类模型精度。(3)4种分类算法融合光谱、地形、纹理特征,分类精度由高到低依次为随机森林、梯度提升树、分类回归树、支持向量机;随机森林在5期(2002、2008、2013、2018、2023年)影像中的总体分类精度不低于93%,卡帕系数(Kappa)不低于0.92,最适用于艾比湖流域景观分类。The study focuses on the Ebi Lake Basin in Xinjiang,integrating historical remote sensing imagery data with field surface feature investigations.The landscape types of the Ebi Lake Basin were classified into six categories:cultivated land,forest land,grassland,water bodies,construction land,and unused land.Using Landsat imagery provided by the Google Earth Engine(GEE)platform for the years 2002,2008,2013,2018,and 2023 as the primary data source,we established landscape classification as an evaluation indicator.Spectral indices(normalized difference vegetation index,enhanced vegetation index,normalized water index,and normalized construction index),terrain features(elevation,slope,and aspect),and texture features(angular second moment,contrast,correlation,entropy,covariance,inverse difference,and mean of sum)were used as influencing factors to construct and optimize the multidimensional feature model from three perspectives:spectral indices,terrain features,and texture features.Four machine learning algorithms-classification and regression trees(CART),random forest(RF),gradient boosting trees(GBT),and support vector machines(SVM)-were employed to automatically classify long-term landscape information in the Ebi Lake Basin and to compare the classification accuracy of the four algorithms to identify the most suitable landscape classification model for the region.The results showed:(1)The Google Earth Engine cloud computing platform efficiently processed,analyzed,and visualized landscape classification results for nearly 22 years in the study area.(2)The importance of the three feature types ranked from highest to lowest was as follows:spectral indices(31.52%),terrain features(17.18%),and texture features(3.83%).Among individual features,terrain features exhibited the highest classification accuracy.The combination of spectral features and texture features showed improved classification accuracy for the study area.Meanwhile,models that integrated spectral indices,terrain features,and texture features could effective

关 键 词：景观分类 生态系统 生态环境 艾比湖流域 

分 类 号：X171.1[环境科学与工程—环境科学] P901[天文地球—自然地理学]