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

doi:10.11978/2022096

热带海洋学报 ›› 2023, Vol. 42 ›› Issue (2): 153-168.doi: 10.11978/2022096CSTR: 32234.14.2022096

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.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:2023-03-10 发布日期:2022-07-11
通讯作者: 吴培强。email: wu1416@163.com
作者简介:
张程飞(1998—), 男, 硕士研究生, 主要从事红树林遥感监测研究。email: zcf199828@163.com
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项目(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)项目(41-Y30F07-9001-20/22)

Mangrove species classification in the 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. 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:2023-03-10 Published:2022-07-11
Contact: WU Peiqiang. email: wu1416@163.com
Supported by:
National Natural Science Foundation of China(42106179); Natural Resources Satellite Remote Sensing Operational Service System(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/Abstract

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, 基于高分三号(GF-3)全极化合成孔径雷达(synthetic aperture radar, SAR)和高分六号(GF-6)多光谱遥感数据, 本文提取了35个红树林遥感特征, 利用极端梯度提升树(eXtreme gradient boosting, XGBoost)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, 将其与传统的支持向量机(support vector machine, SVM)、随机森林(random forest, RF)机器学习算法进行精度比较, 并基于XGBoost算法进行了3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个优选特征(绿光波段反射率G、蓝光波段反射率B、Yamaguchi面散射分量Y_s、近红外波段反射率NIR、增强型植被指数EVI、比值植被指数RVI、归一化植被指数NDVI、Freeman面散射分量F_s)即可达到较高分类精度。2) 对于八门湾红树林湿地, XGBoost算法的红树种间分类总体精度最高, 为86.16%, 卡帕系数为0.836, 比SVM和RF算法高3% ~ 8%; 优选特征的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%。

关键词: 红树林, 种间分类, 多光谱, 全极化SAR, XGBoost

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 the Hainan Bamen bay, based on GF-3 fully polarimetric Synthetic Aperture Radar (SAR) 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 eXtreme Gradient Bo3osting (XGBoost) algorithm. The accuracy of XGBoost was compared with the traditional Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms, and the classification accuracy of three feature combination methods (preferred feature, multispectral feature and full polarization SAR feature) is compared based on the XGBoost algorithm.The purpose is to explore the applicability of XGBoost to mangrove interspecific classification and the ability of optical and fully polarized SAR data for mangrove interspecific 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, Y_s, NIR, EVI, RVI, NDVI, F_s) 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 used multispectral or fully polarimetric SAR alone. 3) The total area of mangroves in the Bamen bay was 797.58 hm², 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 the 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, interspecific classification, multispectral, fully polarimetric SAR, XGBoost

张程飞, 任广波, 吴培强, 胡亚斌, 马毅, 阎宇, 张菁锐. 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[J]. 热带海洋学报, 2023, 42(2): 153-168.

ZHANG Chengfei, REN Guangbo, WU Peiqiang, HU Yabin, MA Yi, YAN Yu, ZHANG Jingrui. Mangrove species classification in the Hainan Bamen Bay based on GF optics and fully polarimetric SAR[J]. Journal of Tropical Oceanography, 2023, 42(2): 153-168.

图/表 13

图1

表1

表2

红树林类型及遥感影像解译描述"

红树种类	现场照片	GF-6影像	GF-3影像	红树属性及影像特征
白骨壤(Avicennia marina)				小叶、耐盐、耐淹、常绿灌木或小乔木、常分布于淡水注入较少的海湾区域。影像纹理略粗糙, 色调较均一, GF-6影像为暗红色, GF-3影像为紫色
海莲(Bruguiera sexangula)				木榄属乔木或灌木, 生于滨海盐滩或潮水到达的沼泽地。影像纹理较平滑, 色调较均一, GF-6影像为亮红色, GF-3影像为白色
红海榄(Rhizophora stylosa Griff)				支柱根、常绿乔木或灌木、较耐盐、多分布于河口外侧盐度较高的红树林内滩。影像纹理粗糙, 色调略杂乱, GF-6影像为暗红色, GF-3影像为紫色
杯萼海桑(Sonneratia alba Sm)				海桑属灌木或乔木, 生于滨海泥滩和河流两侧而潮水到达的红树林群落中。影像纹理粗糙, 色调较均一, GF-6影像为暗红色中掺杂白色斑点, GF-3影像为灰绿色
角果木(Ceriops tagal)				灌木或乔木, 耐盐性较强, 生于潮涨时仅淹没树干基部的泥滩和海湾内的沼泽地。影像纹理平滑细腻, 色调均一, GF-6影像为暗红色, GF-3影像浅红色
木榄(Bruguiera gymnorrhiza)				常绿乔木或灌木, 耐淹能力较差、多分布于红树林内滩。影像纹理略粗糙, 色调较均一, GF-6影像为亮红色, GF-3影像为灰绿色
榄李(Lumnitzera racemosa Willd)				使君子科、榄李属常绿灌木或小乔木, 喜生于中潮滩或高潮滩。影像纹理较平滑, 色调均一, GF-6影像为暗红色, GF-3影像为浅紫色
正红树(Rhizophora apiculata Bl)				常绿小乔木或灌木, 分布于海浪平静、淤泥松软的浅海盐滩或海湾内的沼泽地。影像纹理平滑, 色调均一, GF-6影像为深红色, GF-3影像为蓝色
海漆(Excoecaria agallocha Linn)				大戟科海漆属植物, 常绿乔木, 生于海陆交错区的高潮带或超高潮带的盐碱地上。影像纹理略粗糙, 色调较均一, GF-6影像为浅红色, GF-3影像为蓝绿色

表2

图2

图 3

表3

GF-6多光谱特征"

遥感特征	名称	公式	出处
光谱波段反射率	B1 ~ B4	$ρ R / ρ G / ρ B / ρ NIR$	—
植被指数	归一化植被指数(NDVI)	$ρ NIR − ρ R ρ NIR + ρ R$	Rouse等(1974)
	增强型植被指数(enhanced vegetation index, EVI)	$2.5 (ρ NIR − ρ R ρ NIR + 6 ρ R − 7.5 ρ B + 1)$	Liu等(1995)
	比值植被指数(ratio vegetation index, RVI)	$ρ NIR ρ R$	Pearson等(1972)
纹理参数	相关性(correlation)	$∑ i, j = 1 N (i − M E) (j − M E) P i, j 2 V ar$	Haralick等(1973)
	同质性(homogeneity)	$∑ i, j = 1 N P i, j 1 + i − j$
	对比度(contrast)	$∑ i, j = 1 N (i − j) 2 ⋅ P i, j$
	标准偏差(standard deviation)	$∑ i 2 p i, j − M E 2$
	二阶矩阵(second moment)	$∑ i, j = 1 N P i, j 2$
	相异性(dissimilarity)	$∑ i, j = 1 N P i, j ⋅ i − j$
	均值(mean)	$∑ i, j = 1 N i ⋅ P i, j$
	信息熵(entropy)	$∑ i, j = 1 N P i, j (− ln P i, j)$

表3

表4

GF-3全极化SAR特征"

遥感特征		名称	公式	出处
极化图像波段特征		HH/HV/VH/VV	$S HH$ / $S HH$ / $S HH$ / $S HH$	Souyris等(1995)
极化相关特征		共极化相干因子(polcoe)	$C 11 C 33 C 13$	Henderson等(1998)
		HH与HV相关系数 (ρ_HH-HV)	$S HH S HV * S HH S HH * S HH S HV *$	Souyris等(1995)
		VV与HV相关系数 (ρ_VV-HV)	$S VV S HV * S VV S VV * S HH S HV *$	Souyris等(1995)
		归一化圆极化基相关系数(NCCC)	$1 + 4 Re S HV * S HH − S VV 2 2 S HH − S VV 2 2 − S HV 2 2 1 / 2 ⋅ 1 − 4 Im S HV * S HH − S VV 2 2 S HH − S VV 2 2 + S HV 2 2 − 1 / 2$	杨杰等(2012)
极化分解特征	Freeman分解	体散射分量 (Freeman_vol, F_v)	$3 S VV 2$	Freeman等(1998)
		二次散射分量(Freeman_dbl, F_d)	$β S VV 2 − S HH S ∗ VV β − α$
		面散射分量 (Freeman_surf, F_s)	$α S VV 2 − S HH S ∗ VV α − β$
		雷达植被指数(RVI_Freeman)	$F v F s + F d + F v$
	Yamaguchi分解	体散射分量(Yamaguchi_vol, Y_v)	$154 2 S HV 2 − I m S ∗ HV (S HH − S VV)$	Yamaguchi等(2011)
		二次散射分量(Yamaguchi_dbl, Y_d)	$1 + α 2 β S VV 2 − S HH S ∗ VV β − α$
		面散射分量(Yamaguchi_surf, Y_s)	$1 + β 2 α S VV 2 − S HH S ∗ VV α − β$
		螺旋散射分量(Yamaguchi_cir, Y_c)	$2 I m S ∗ HV (S HH − S VV)$
	H/A/ $α -$ 分解	极化熵H (entropy)	$− ∑ i = 1 2 (λ i λ 1 + λ 2 log 2 λ i λ 1 + λ 2)$	Cloude等(1996)
		极化各向异性A (anisotropy)	$∑ i = 1 2 (λ i λ 1 + λ 2 cos − 1 (e i))$
		极化散射角 $α -$ (alpha)	$λ 1 − λ 2 λ 1 + λ 2$
		Van雷达植被指数(RVI_Van)	$4 λ 3 λ 1 + λ 2 + λ 3$	Zyl等(2016)

表4

图4

图5

图6

表5

表6

图7

参考文献 54

[1]	杜云艳, 周成虎, 1998. 水体的遥感信息自动提取方法[J]. 遥感学报, (4): 264-269.
	DU YUNYAN, ZHOU CHENGHU, 1998. Automatically extracting remote sensing information for Water Bodies[J]. Journal of Remote Seneing, (4): 264-269. (in Chinese with English abstract)
[2]	范航清, 张云兰, 邹绿柳, 等, 2022. 中国红树林基准价值及其单株价值分配研究[J]. 生态学报, 42(4): 1262-1275.
	FAN HANG QING, ZHANG YUNLAN, ZOU LVLIU, et al, 2022. A study on the baseline value of the Chinese mangrove services and allocation of the value to individual tree[J]. ActaEcologica Sinica, 42(4): 1262-1275. (in Chinese with English abstract)
[3]	何海军, 温家声, 张锦炜, 等, 2015. 海南红树林湿地生态系统服务价值评估[J]. 生态经济, 31(4): 145-149.
	HE HAIJUN, WEN JIASHENG, ZHANG JINWEI, et al, 2015. Ecological functions assessment of mangrove wetland in Hainan Province[J]. Ecological Economy, 31(4): 145-149. (in Chinese with English abstract)
[4]	李森, 蔡厚才, 陈万东, 等, 2020. 海岸带生态恢复区不同林龄红树林对CH₄和CO₂排放通量的影响[J]. 生态环境学报, 29(12): 2414-2422. doi: 10.16258/j.cnki.1674-5906.2020.012.012
	LI SEN, CAI HOUCAI, CHEN WANDONG, et al, 2020. Analysis on CH₄ and CO₂ fluxes of mangroves with different ages in the coastal ecological restoration zone[J]. Ecology and Environmental Sciences, 29(12): 2414-2422. (in Chinese with English abstract)
[5]	林鹏, 2001. 中国红树林研究进展[J]. 厦门大学学报(自然科学版), (2): 592-603.
	LIN PENG, 2001. A review on the mangrove research in China[J]. Journal of Xiamen University (Natural Science), (2): 592-603. (in Chinese with English abstract)
[6]	马云梅, 吴培强, 任广波, 等, 2019. 基于国产高分遥感的人工种植红树林种间分类方法研究——以广西茅尾海红树林为例[J]. 海洋技术学报, 38(4): 1-8.
	MA YUNMEI, WU PEIQIANG, REN GUANGBO, et al, 2019. Pixel-based and object-based comparative analysis of classification among mangrove species in Maoweihai[J]. Journal of Ocean Technology, 38(4): 1-8. (in Chinese with English abstract)
[7]	马云梅, 吴培强, 任广波, 2021. 基于高分影像光谱特征的广西海岸带红树林精细分类与制图[J]. 地球信息科学学报, 23(12): 2292-2304. doi: 10.12082/dqxxkx.2021.210494
	MA YUNMEI, WU PEIQIANG, REN GUANGBO, 2021. Fine classification and mapping of mangroves in Guangxi coastal zone based on spectral characteristics of GF images[J]. Journal of Geo-information Science, 23(12): 2292-2304. (in Chinese with English abstract)
[8]	农寿千, 杨小波, 李东海, 等, 2011. 清澜港红树林保护区植物特点研究[J]. 植物科学学报, 1(4): 459-466.
	NONG SHOUQIAN, YANG XIAOBO, LI DONGHAI, et al, 2011. Vegetation composition in the mangrove forest nature protection area of Qinglan, China[J]. Plant Science Journal, 1(4): 459-466. (in Chinese with English abstract)
[9]	任广波, 周莉, 梁建, 等, 2021. “高分五号”高光谱互花米草遥感识别与制图研究[J]. 海洋科学进展, 39(2): 312-326.
	REN GUANGBO, ZHOU LI, LIANG JIAN, et al, 2021. Monitoring the invasion of spartina alterniflora using hyperspectral remote sensing image of GF-5[J]. Advances In Marine Science, 39(2): 312-326. (in Chinese with English abstract)
[10]	邵永社, 韩阳, 吕倩利, 等, 2011. 4分量模型和散射参数的全极化雷达图像分类[J]. 同济大学学报(自然科学版), 39(9): 1345-1349.
	SHAO YONGSHE, HAN YANG, LYU QIANLI, et al, 2011. Full polarimetric SAR classification based on four-component decomposition model and scattering parameters[J]. Journal of Tongji University (Natural Science), 39(9): 1345-1349. (in Chinese with English abstract)
[11]	苏岫, 赵冬至, 黄凤荣, 等, 2011. 基于高空间分辨率的红树林卫星遥感监测技术进展[J]. 热带海洋学报, 30(3): 38-45.
	SU XIU, ZHAO DONGZHI, HUANG FENGRONG, et al, 2011. Development of mangrove monitoring technology using high spatial-resolution satellite images[J]. Journal of Tropical Oceanography, 30(3): 38-45. (in Chinese with English abstract) doi: 10.11978/j.issn.1009-5470.2011.03.038
[12]	涂志刚, 吴瑞, 张光星, 等, 2015. 海南岛清澜港红树植物群落类型及其特征[J]. 热带农业科学, 35(11): 21-25.
	TU ZHIGANG, WU RUI, ZHANG GUANGXING, et al, 2015. Types and characteristics of mangrove plants of Qinglan harbour in Hainan Island[J]. Chinese Journal of Tropical Agriculture, 35(11): 21-25. (in Chinese with English abstract)
[13]	徐晓然, 谢跟踪, 邱彭华, 2018. 1964—2015年海南省八门湾红树林湿地及其周边土地景观动态分析[J]. 生态学报, 38(20): 7458-7468.
	XU XIAORAN, XIE GENZONG, QIU PENGHUA, 2018. Dynamic analysis of iandscape changes in bamen port and the surrounding lands of Hainan Province from 1964 to 2015[J]. Acta Ecologica Sinice, 38(20): 7458-7468. (in Chinese with English abstract)
[14]	杨杰, 赵伶俐, 李平湘, 等, 2012. 引入规范化圆极化相关系数的保持极化散射特性的分类算法[J]. 武汉大学学报(信息科学版), 37(8): 911-914.
	YANG JIE, ZHAO LINGLI, LI PINGXIANG, et al, 2012. Preserving polarimetric scattering characteristics classification by introducing normalized Circular-pol correlation coefficient[J]. Geomatics and Information Science of Wuhan University, 37(8): 911-914. (in Chinese with English abstract)
[15]	杨众养, 薛杨, 宿少锋, 等, 2017. 文昌市八门湾红树林区植物群落特征调查[J]. 热带农业科学, 37(1): 48-52, 59.
	YANG ZHONGYANG, XUE YANG, SU SHAOFENG, et al, 2017. The survey on plant community characteristics of bamenwan mangroves in Wenchang City[J]. Chinese Journal Of Tropical Agriculture, 37(1): 48-52, 59. (in Chinese with English abstract)
[16]	郑德璋, 廖宝文, 郑松发, 等, 1995. 海南岛清澜港红树树种适应生境能力与水平分布[J]. 林业科学研究, 8(1): 67-72.
	ZHENG DEZHANG, LIAO BAOWEN, ZHENG SONGFA, et al, 1995. Mangrove Plants’ adaptive ability to habitat and their horizontal distribution in Qinglan Harbour, Hainan Island[J]. Forest Research, (1): 67-72. (in Chinese with English abstract)
[17]	郑艺, 林懿琼, 周建, 等, 2019. 基于资源三号的雷州半岛红树林种间分类研究[J]. 国土资源遥感, 31(3): 201-208.
	ZHENG YI, LIN YIQIONG, ZHOU JIAN, et al, 2019. Mangrove inter-species classification based on ZY-3 image in Leizhou Peninsula, Guangdong Province[J]. Remote Sensing for Land and Resources, 31(3): 201-208. (in Chinese with English abstract)
[18]	邹斌, 张腊梅, 孙德明, 等, 2009. PolSAR图像信息提取技术及应用的发展[J]. 遥感技术与应用, 24(3): 263-273.
	ZOU BIN, ZHANG LAMEI, SUN DEMING, et al, 2009. Development and application of information extraction using polarimetric SAR Data[J]. Remote Sensing Technology And Application, 24(3): 263-273. (in Chinese with English abstract)
[19]	ABDULLAHI S, KUGLER F, PRETZSCH H, 2016. Prediction of stem volume in complex temperate forest stands using TanDEM-X SAR data[J]. Remote Sensing of Environment, 174: 197-211. doi: 10.1016/j.rse.2015.12.012
[20]	BRYAN-BROWN D N, CONNOLLU R M, RICHARDS D R, et al, 2020. Global trends in mangrove forest fragmentation[J]. Scientific reports, 10(1): 7117. doi: 10.1038/s41598-020-63880-1
[21]	CHAN C W, PAELINCKX D, 2008. Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery[J]. Remote Sensing of Environment, 112(6): 2999-3011. doi: 10.1016/j.rse.2008.02.011
[22]	CHEN LUZHEN, WANG WENQING, ZHANG YIHUI, et al, 2009. Recent progresses in mangrove conservation, restoration and research in China[J]. Journal of Plant Ecology, 2(2): 45-54. doi: 10.1093/jpe/rtp009
[23]	CHEN TIANQI, GUESTRIN C, 2016. ASSOC COMP MACHINERY. XGBoost: A scalable tree boosting system[C]// 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). San Francisco, CA: 785-794.
[24]	CLOUDE S R, POTTIER E, 1996. A review of target decomposition theorems in radar polarimetry[J]. IEEE Transactions on Geoscience & Remote Sensing, 34(2): 498-518.
[25]	DIAN YUANYONG, ZENG YUANLI, PANG YONG, 2015. Spectral and Texture Features Combined for Forest Tree species Classification with Airborne Hyperspectral Imagery[J]. Journal of the Indian Society of Remote Sensing, 43(1): 101-107. doi: 10.1007/s12524-014-0392-6
[26]	DUARTE C M, MIDDELBURG J J, CARACO N, 2004. Major role of marine vegetation on the oceanic carbon cycle[J]. Biogeosciences Discussions, 1: 659-679.
[27]	FERREIRA M P, WAGNER F H, ARAGO L, et al, 2019. Tree species classification in tropical forests using visible to shortwave infrared WorldView-3 images and texture analysis[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 149: 119-131. doi: 10.1016/j.isprsjprs.2019.01.019
[28]	FREEMAN A, DURDEN S L, 1998. A three-component scattering model for polarimetric SAR data[J]. IEEE Transactions on Geoscience & Remote Sensing, 36(3): 963-973.
[29]	FRIESS D A, ROGERS K, LOVELOCK C E, et al, 2019. The state of the World’s mangrove forests: Past, present, and future[J]. Annual Review of Environment and Resources, 44(1): 89-115. doi: 10.1146/energy.2019.44.issue-1
[30]	GUPTA S, MISHRA P, SINGH D, et al, 2017. An approach to classify tall vegetation and Urban using deoriented PALSAR Image[J]. IEEE Geoence & Remote Sensing Letters, 14(12): 2185-2189.
[31]	HARALICK R M, SHANMUGAM K, DINSTEIN I, 1973. Textural features for image classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, 3(6): 610-621.
[32]	HELD A, TICEHURST C, LYMBURNER L, et al, 2003. High resolution mapping of tropical mangrove ecosystems using hyperspectral and radar remote sensing[J]. International Journal of Remote Sensing, 24(13): 2739-2759. doi: 10.1080/0143116031000066323
[33]	HENDERSON F M, LEWIS A J, 1998. Principles and applications of imaging radar. Manual of remote sensing: Third edition, Volume 2[J]. Ecological Engineering.
[34]	JIANG YUFENG, ZHANG LI, YAN MIN, et al, 2021. High-Resolution mangrove forests classification with machine learning using Worldview and UAV Hyperspectral Data[J]. Remote Sensing, 13(8): 1529. doi: 10.3390/rs13081529
[35]	LI HUIYING, JIA MINGMING, ZHANG RONG, et al, 2019. Incorporating the plant phenological trajectory into mangrove species mapping with dense time series Sentinel-2 imagery and the Google Earth Engine Platform[J]. Remote Sensing, 11(21): 2479. doi: 10.3390/rs11212479
[36]	LI QIAOSI, WONG F, FUNG T, 2021. Mapping multi-layered mangroves from multispectral, hyperspectral, and LiDAR data[J]. Remote Sensing of Environment, 258(3): 112403. doi: 10.1016/j.rse.2021.112403
[37]	LIU HUIQING, HUETE A, 1995. A feedback based modification of the NDVI to minimize canopy background and atmospheric noise[J]. IEEE Transactions on Geoscience and Remote Sensing, 33(2): 457-465. doi: 10.1109/TGRS.36
[38]	LUO ZHONGKUI, SUN O, XU HUALIN, 2010. A comparison of species composition and stand structure between planted and natural mangrove forests in Shenzhen Bay, South China[J]. Journal of Plant Ecology, 3(3): 165-174. doi: 10.1093/jpe/rtq004
[39]	MANABU W, MASANOBU S, 2017. Polarimetric Calibration for a Ground-Based Radar, and comparison of the polarimetric parameters with Air-Borne SAR obtained from a forest[J]. Remote Sensing, 9(4): 342. doi: 10.3390/rs9040342
[40]	MEERA S P, BHATTACHARYYA M, NIZAM A, et al, 2021. A review on microplastic pollution in the mangrove wetlands and microbial strategies for its remediation[J]. Environmental Science and Pollution Research, 29(4): 4865-4879. doi: 10.1007/s11356-021-17451-0
[41]	PEARSON R L, MILLER D L, 1972. Remote mapping of standing crop biomass for estimation of the productivity of the Shortgrass Prairie[J]. Ann Arbor, Michigan, 1357-1381.
[42]	ROUSE J W, HAAS R W, SCHELL J A, et al, 1974. Monitoring the vernal advancement and retrogradation (green wave effect) of natural vegetation[D]. Greenbelt, MD: NASA/GSFC Type Ⅲ, Final Report.
[43]	SOUYRIS J C, Le TOAN T, HSU C C, et al, 1995. Inversion of Landes Forest biomass using SIR-C/X-SAR data: experiment and theory[C]// 1995 International Geoscience and Remote Sensing Symposium, IGARSS’95. Quantitative Remote Sensing for Science and Applications. IEEE, 2: 1201-1203.
[44]	VIENNOIS G, PROISY C, FERET J B, et al, 2016. Multitemporal analysis of High-Rpatial-Resolution optical satellite imagery for mangrove species mapping in Bali, Indonesia[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 9(8): 3680-3686.
[45]	WANG DEZHI, WAN BO, QIU PENGHUA, et al, 2018. Artificial mangrove species mapping using Pléiades-1: An evaluation of Pixel-Based and Object-Based classifications with selected machine learning algorithms[J]. Remote Sensing, 10(2): 294. doi: 10.3390/rs10020294
[46]	WANG DEZHI, WAN BO, QIU PENGHUA, et al, 2022. Mapping mangrove species using combined UAV-LiDAR and Sentinel-2 data: Feature selection and point density effects[J]. Advances in Space Research, 69(3): 1494-1512. doi: 10.1016/j.asr.2021.11.020
[47]	XIA JUNSHI, YOKOYA N, PHAM T D, 2020. Probabilistic mangrove species mapping with Multiple-Source Remote-Sensing datasets using label distribution learning in Xuan Thuy National Park, Vietnam[J]. Remote Sensing, 12(22): 3834. doi: 10.3390/rs12223834
[48]	YAMAGUCHI Y, SATO A, BOERNER W M, et al, 2011. Four-component scattering power decomposition with rotation of coherency matrix[J]. IEEE Transactions on Geoscience and Remote Sensing, 49(6): 2251-2258. doi: 10.1109/TGRS.2010.2099124
[49]	YU HAIFEI, WANG CHANGYING, SUI YI, et al, 2020. Automatic extraction of green tide using Dual polarization Chinese GF-3 SAR Images[J]. Journal of Coastal Research, 102(sp1): 318-325.
[50]	ZHANG HONGSHEN, WANG TING, LIU MINGFENG, et al, 2018. Potential of combining optical and dual polarimetric SAR data for improving mangrove species discrimination using rotation forest[J]. Remote Sensing, 10(3): 467. doi: 10.3390/rs10030467
[51]	ZHANG RONG, JIA MINGMING, WANG ZONGMING, et al, 2021. A Comparison of Gaofen-2 and Sentinel-2 imagery for mapping mangrove forests using Object-Oriented analysis and random forest[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 4185-4193. doi: 10.1109/JSTARS.2021.3070810
[52]	ZHEN JIANING, LIAO JINGJUN, SHEN GUOZHUANG, 2018. Mapping mangrove forests of Dongzhaigang nature reserve in China using landsat 8 and Radarsat-2 Polarimetric SAR Data[J]. Sensors, 18(11): 4012. doi: 10.3390/s18114012
[53]	ZULFA A W, NORIZAH K, HAMDAN O, et al, 2021. Spectral signature analysis to determine mangrove species delineation structured by anthropogenic effects[J]. Ecological Indicators, 130: 108148. doi: 10.1016/j.ecolind.2021.108148
[54]	ZYL J J, 2016. An overview of the analysis of multi-frequency polarimetric SAR data[C]// 6th European Conference on Synthetic Aperture Radar (EUSAR 2006).

卫星	传感器	成像时间	波段信息	空间分辨率/m	幅宽/km
高分六号	全色/多光谱相机	2021年5月21日	红(0.63 ~ 0.69μm)/绿(0.52 ~ 0.60μm)/蓝(0.45 ~ 0.52μm)/近红外(0.76 ~ 0.90μm)	8	>90
高分六号	全色/多光谱相机	2021年5月21日	全色(0.45 ~ 0.90μm)	2	>90
高分三号	合成孔径雷达	2021年3月23日	水平发射水平接收/水平发射垂直接收/垂直发射水平接收/垂直发射垂直接收	8	30

	支持向量机		随机森林		极端梯度提升树
	优选特征		优选特征		优选特征		多光谱特征		全极化SAR特征
	PA/%	UA/%	PA/%	UA/%	PA/%	UA/%	PA/%	UA/%	PA/%	UA/%
白骨壤	76.47	65.00	100.00	83.33	94.74	90.00	66.67	50.00	85.71	85.71
海莲	84.93	69.66	86.25	75.82	82.47	89.89	87.38	63.22	79.01	74.42
红海榄	64.86	63.16	83.33	65.79	84.38	71.05	76.67	50.00	71.05	62.79
杯萼海桑	85.71	80.95	86.51	85.83	90.60	84.13	83.78	80.17	64.23	69.91
角果木	82.19	88.24	95.00	98.70	95.59	95.59	88.16	89.33	83.16	90.80
榄李	72.73	74.32	80.55	83.82	85.48	86.89	68.06	77.84	74.25	76.54
木榄	72.67	78.99	72.39	82.27	77.30	78.99	67.84	81.69	69.28	65.84
正红树	90.20	97.87	94.87	90.24	94.00	100.00	91.67	89.80	90.00	91.84
海漆	81.08	85.71	76.66	74.19	88.24	85.71	73.33	64.71	81.82	69.23
总体精度/%	78.23		83.04		86.16		76.22		74.77
Kappa系数	0.7417		0.9800		0.8359		0.7174		0.7033

实验组别	算法参数
SVM+优选特征	Kernel Type: 'RBF' Penalty=185; gamma=0.0001
RF+优选特征	n_estimators=120; max_depth=15; max_features=8
XGBoost+优选特征	learning_rate=0.06; n_estimators=252; max_depth=5; gamma=0.2
XGBoost+多光谱特征	learning_rate=0.09; n_estimators=10; max_depth=5; gamma=0.8
XGBoost+全极化SAR特征	learning_rate=0.09; n_estimators=10; max_depth=6; gamma=0.9

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

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

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 54

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	吴鸿博, 罗锋, 陈治澎, 朱飞, 曾靖伟, 张弛, 李瑞杰. 红树林生态重建效果预测研究新模式[J]. 热带海洋学报, 2024, 43(4): 86-97.
[2]	郑法, 黄福林, 陈泽恒, 丁伟品. 基于LUCC和景观格局变化的广西山口红树林湿地动态研究[J]. 热带海洋学报, 2024, 43(4): 165-173.
[3]	周治刚, 岳文, 李辉权, 林阳阳. 树种类型和潮滩高程对广东湛江高桥红树林碳储量的影响[J]. 热带海洋学报, 2024, 43(2): 108-120.
[4]	申键, 简焯锴, 欧阳雪敏, 艾彬. 结合潮位校正的雷州半岛红树林湿地动态变迁遥感监测[J]. 热带海洋学报, 2024, 43(1): 137-153.
[5]	耿婉璐, 邢永泽, 张秋丰, 管卫兵. 广西北海红树林宜林滩涂大型底栖动物群落结构特征[J]. 热带海洋学报, 2024, 43(1): 107-115.
[6]	董俊德, 黄小芳, 龙爱民, 王友绍, 凌娟, 杨清松. 红树林固氮微生物及其生态功能研究进展[J]. 热带海洋学报, 2023, 42(4): 1-11.
[7]	梁寒峭, 陈文凤, 范益铠, 朱子冬, 马国需, 陈德力, 田婧. 红树林来源曲霉属和木霉属内生真菌次生代谢产物及活性研究进展[J]. 热带海洋学报, 2023, 42(4): 12-24.
[8]	周月月, 王友绍. 广东沿海红树林区水质变化特征与富营养状态评估[J]. 热带海洋学报, 2022, 41(6): 1-11.
[9]	吴伟志, 赵志霞, 杨升, 梁立成, 陈秋夏, 卢翔, 刘星, 张小伟. 浙江省红树林分布和造林成效分析[J]. 热带海洋学报, 2022, 41(6): 67-74.
[10]	郝露露, 柯明思, 朱奕秀, 许燕敏, 张颖, 郑春芳. 低温胁迫下红榄李(Lumnitzera littorea)DEAD-box RNA解旋酶基因的表达分析[J]. 热带海洋学报, 2022, 41(6): 44-55.
[11]	李华薇, 徐向荣. 中国典型红树林沉积物中多溴联苯醚和替代型溴系阻燃剂污染特征[J]. 热带海洋学报, 2022, 41(1): 117-130.
[12]	王友绍. 全球气候变化对红树林生态系统的影响、挑战与机遇[J]. 热带海洋学报, 2021, 40(3): 1-14.
[13]	戴志军, 周晓妍, 王杰, 胡宝清. 红树林潮滩沉积动力研究进展与展望[J]. 热带海洋学报, 2021, 40(3): 69-75.
[14]	董迪, 曾纪胜, 魏征, 严金辉. 联合星载光学和SAR影像的漳江口红树林与互花米草遥感监测[J]. 热带海洋学报, 2020, 39(2): 107-117.
[15]	李小维, 黄子眉, 陈剑锋, 王欣, 韦江玲. 基于VSD模型的铁山港湾红树林生态系统脆弱性初步评价[J]. 热带海洋学报, 2018, 37(2): 47-54.