热带海洋学报

• •    

基于高分光学与全极化SAR的海南八门湾红树林种间分类方法

张程飞1,2, 任广波2, 吴培强2*, 胡亚斌2, 马毅2, 阎宇3, 张菁锐4   

  1. 1.山东科技大学测绘与空间信息学院, 山东 青岛 266590

    2.自然资源部第一海洋研究所, 山东 青岛 266061

    3.国家卫星海洋应用中心, 北京 100081;

    4.中国石油大学(华东)海洋与空间信息学院, 山东 青岛 266580

  • 收稿日期:2022-05-03 修回日期:2022-07-05 出版日期:2022-07-11 发布日期:2022-07-11
  • 通讯作者: 吴培强
  • 基金资助:
    国家自然科学基金项目(42106179);自然资源卫星遥感业务支持服务体系(编号:121168000000190033);高分海洋资源环境遥感信息处理与业务应用示范系统(二期)(41-Y30F07-9001-20/22)

Mangrove species classification in Hainan bamen Bay based on GF optics and fully polarimetric SAR

ZHANG Chengfei1,2, REN Guangbo2, WU Peiqiang2*, HU Yabin2, MA Yi2, YAN Yu3, ZHANG Jingrui4   

  1. 1. College of Geodesy and Geomatics, Shandong University of science and technology, Qingdao 266590, China;

    2. The first Institute of Oceanography, Ministry of natural resources, Qingdao 266061, China;

    3. National satellite marine application center, Beijing 100081, China; 4. College of Oceanography and Space Informatics, China University of petroleum, Qingdao 266580, China

  • Received:2022-05-03 Revised:2022-07-05 Online:2022-07-11 Published:2022-07-11
  • Contact: wu
  • Supported by:
    National Natural Science Foundation of China (41876207); Natural resources satellite remote sensing operational service system (No. 121168000000190033); High resolution marine resources and environment remote sensing information processing and business application demonstration system (phase Ⅱ) (41-Y30F07-9001-20 / 22)

摘要: 摘要:合理的红树种间组成结构是有效发挥红树林湿地生态价值的前提,明确的红树林种间分布信息是开展红树林生态系统治理和规划工作的有效依据。针对海南八门湾红树林湿地,基于GF-3全极化SAR(Synthetic Aperture Radar)和GF-6 多光谱遥感数据,本文提取了35个红树林遥感特征,利用XGBoost(eXtreme Gradient Boosting)算法开展了特征重要性排序、特征筛选和红树林种间分类实验,将其与传统的SVM(Support Vector Machine)、RF(Random Forest)机器学习算法进行精度比较,并进行了三种特征组合方式(优选特征、多光谱特征、全极化SAR特征)的分类精度比较,旨在探索XGBoost对红树林种间分类的适用性和光学与全极化SAR数据对红树林种间分类的能力。结果表明:(1)识别红树林种类的优势特征依次为多光谱的光谱波段、极化分解参数、光谱植被指数,且仅利用前8个(G、B、Ys、NIR、EVI、RVI、NDVI、Fs)优选特征即可达到较高分类精度。(2)XGBoost总体分类精度最高,为86.16%,Kappa为0.836,该算法的分类精度比SVM和RF高3%~8%;多光谱与全极化SAR结合的优选特征红树林种间分类精度比单独的多光谱特征或全极化SAR特征高10%~12%。(3)八门湾红树林总面积约为797.58hm2,共有白骨壤、海莲、红海榄、杯萼海桑、角果木、榄李、木榄、正红树、海漆9种优势真红树,杯萼海桑和木榄的面积较大,分别占全部红树林面积的45.46%、21.21%。本文基于高分光学与全极化SAR开展海南八门湾红树林种间分类研究,可为红树林生态系统的保护和治理提供数据支持和技术支撑。

关键词: 红树林, 树种分类, 多光谱, 全极化SAR, XGBoost, 特征筛选

Abstract: Abstract: A Reasonable interspecific composition structure of mangrove is the premise of effectively bringing into play the ecological value of mangrove wetland, and clear information of interspecific distribution of mangrove is an effective basis for mangrove ecosystem management and planning. For the mangrove wetland in Hainan Bamen bay, Based on GF-3 fully polarimetric SAR(Synthetic Aperture Radar) and GF-6 multi-spectral remote sensing data, 35 mangrove remote sensing features were extracted, and the importance ranking, feature screening and inter-species classification of mangrove were carried out using XGBoost (eXtreme Gradient Boosting)algorithm. The accuracy of XGBoost was compared with traditional SVM(Support Vector Machine)and RF(Random Forest)machine learning algorithms, and the classification accuracy was compared with three feature combinations (preferred feature, multispectral feature and fully polarimetric SAR feature), in order to explore the applicability of XGBoost to interspecific mangrove classification and the ability of optical and fully polarimetric SAR data to interspecific mangrove classification. The results showed that:(1) the dominant features of mangrove species identification were multi-spectral spectral bands, polarization decomposition parameters, spectral vegetation index, and only the first eight (G, B, Ys, NIR, EVI, RVI, NDVI, Fs) were used to achieve high classification accuracy. (2) XGBoost has the highest overall classification accuracy of 86.16%, and Kappa has 0.836. The classification accuracy of this algorithm is 3%-8% higher than SVM and RF. The accuracy of mangrove interspecific classification using multispectral and fully polarimetric SAR was 10%~12% higher than that using multispectral or fully polarimetric SAR alone. (3) The total area of mangroves in Bamen bay was 797.58hm2, and there were 9 dominant true mangrove species, Avicennia marina, Bruguiera sexangular, Rhizophora stylosa, Sonneratia alba, Rhizophoraceae, Bruguiera gymnorrhiza, Lumnitzera racemosa Willd, Rhizophora apiculate, and Excoecaria agallocha Linn. The area of Sonneratia alba and Lumnitzera racemosa Willd were larger, accounting for 45.46% and 21.21% of the total mangrove area respectively. In this paper, the interspecific classification of mangroves in Bamen bay, Hainan province was studied based on high-resolution optics and fully-polarimetric SAR, which can provide data support and technical support for the protection and management of mangrove ecosystem.

Key words: Mangrove, Classification of tree species, Multispectral, Fully polarimetric SAR, XGBoost, Feature selection

中图分类号: 

  • P237