Mangrove inter-species classification based on ZY-3 image in Leizhou Peninsula, Guangdong Province

doi:10.6046/gtzyyg.2019.03.25

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(3790 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Mapping the distribution pattern of mangrove species in regional scales with remote sensing technology is of great significance in the investigation, utilization and protection of mangrove resources. In this study, the authors mapped and analyzed the mangrove species distribution based on the spectrum characteristics of mangroves,vegetation index, texture information and shape parameters calculated from ZY-3 high-resolution multispectral images, in conjunction with the mangrove species sample points, which were collected by the unmanned aerial vehicle (UAV). The authors used object-oriented classification method,decision tree and support vector machine (SVM). The total area of mangrove forests in Leizhou Peninsula in 2014 was estimated at 5 949.3 hm ², much less than the area reported in most previous studies. For each of the districts in Leizhou Peninsula, mangrove forests covered 1 556.0 hm ² in Lianjiang City, 1 466.1 hm ² in Leizhou City, 1 168.0 hm ² in Zhanjiang Municipal City, 734.7 hm ² in Suixi County, 479.8 hm ² in Xuwen County and 544.7 hm ² in Wuchuan City, respectively. Zonal distribution of native mangrove species is significant from sea to land, with Avicennia marina dominated in the low tide level, followed by Aegiceras corniculatum, Kandelia obovata, Rhizophora stylosa and Brugueria gymnorrhiza dominated from middle to high tide level; the exotic mangrove species Sonneratia apetala is mainly distributed on the land side of Avicennia marina in its introduction area. The proportions of each dominate species are Avicennia marina (41.9%),Sonneratia apetala (23.4%), Aegiceras corniculatum (20.9%),Kandelia obovata(5.4%),Rhizophora stylosa(4.8%) and Brugueria gymnorrhiza (3.6%), respectively. The results show that Sonneratia apetala planting in Leizhou City and Zhanjiang Municipal City has achieved remarkable success in the past several years; however, the risk of its invasive and distribution expansion should also be taken into consideration.

Keywords mangroves inter-species classification high-resolwution imagery object-oriented

TP79

Corresponding Authors: Guanghui LIN E-mail: lingh@tsinghua.edu.cn

Issue Date: 30 August 2019

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Yi ZHENG
	Yiqiong LIN
	Jian ZHOU
	Weixiu GAN
	Guangxuan LIN
	Fanghong XU
	Guanghui LIN

Cite this article:

Yi ZHENG,Yiqiong LIN,Jian ZHOU, et al. Mangrove inter-species classification based on ZY-3 image in Leizhou Peninsula, Guangdong Province[J]. Remote Sensing for Land & Resources, 2019, 31(3): 201-208.

URL:

https://www.gtzyyg.com/EN/10.6046/gtzyyg.2019.03.25 OR https://www.gtzyyg.com/EN/Y2019/V31/I3/201

Fig.1 Location of Leizhou Peninsula and the imagery of two key study areas

Tab.1 Photography sample points for training and accuracy assessment

Fig.2 Rules of decision tree

特征变量		变量描述
原始单波段		B1—B4
波段组合	B2,B3		B2+B3
	B1,B4		B1+B4
	B1,B2,B3		B1+B2+B3
	B2,B3,B4		B2+B3+B4
植被指数	NDVI		$NDVI = B 4 - B 3 B 4 + B 3$
	NDWI		$NDWI = B 4 - B 2 B 4 + B 2$
	简单比值植被指数		$RVI = B 4 B 3$
	增强型植被指数		$EVI = 2.5 B 4 - B 3 B 4 + 6 B 3 - 7.5 B 1 + 1$
纹理参数	均值		$ME = ∑ i, j = 1 N i · P i, j$
	方差		$VAR = ∑ i, j = 1 N P i, j (i - ME) 2$
	均匀度		$HOM = ∑ i, j = 1 N P i, j 1 + │i - j│$
	对比度		$CON = ∑ i, j = 1 N (i - j) 2 · P i, j$
	相异性		$DIS = ∑ i, j = 1 N P i, j │i - j│$
	信息熵		$EN = ∑ i, j = 1 N P i, j (- ln P i, j)$
	二阶矩		$SM = ∑ i, j = 1 N P i, j 2$
	相关度		$COR = ∑ i, j = 1 N (i - ME) (j - ME) P i, j 2 VAR$

Tab.2 Features of remote sensing imagery used in mangrove inner-species classification

Tab.3 Confusion matrix for mangrove inter-species classification

Fig.3 Spatial distribution pattern of mangrove forests in Leizhou Peninsula

Tab.4 Statistic results for the inner-species classification of mangroves in Leizhou Peninsula

Tab.5 Comparison in the mangrove area for Leizhou Peninsula among different studies

Fig.4 Comparison in the results of mangrove inter-species classification for Leizhou Peninsula among different studies

[1]	Chen L Z, Wang W Q, Zhang Y H , et al. Recent progresses in mangrove conservation,restoration and research in China[J]. Journal of Plant Ecology, 2009,2(2):45-54.
[2]	贾明明 . 1973—2013年中国红树林动态变化遥感分析[D]. 北京:中国科学院大学, 2014.
[2]	Jia M M , Remote Sensing Analysis of China’s Mangrove Forests Dynamics During 1973 to 2013[D]. Beijing:University of Chinese Academy of Sciences, 2014.
[3]	但新球, 廖宝文, 吴照柏 , 等. 中国红树林湿地资源、保护现状和主要威胁[J]. 生态环境学报, 2016,25(7):1237-1243.
[3]	Dan X Q, Liao B W, Wu Z B , et al. Resources,conservation status and main threats of mangrove wetlands in China[J]. Ecology and Environmental Sciences, 2016,25(7):1237-1243.
[4]	Chen B Q, Xiao X M, Li X P , et al. A mangrove forest map of China in 2015:Analysis of time series Landsat 7/8 and Sentinel-1A imagery in Google Earth Engine cloud computing platform[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017,131:104-120.
[5]	Kuenzer C, Bluemel A, Gebhardt S , et al. Remote sensing of mangrove ecosystems:A review[J]. Remote Sensing, 2011,3(5):878-928.
[6]	唐焕丽, 刘凯, 朱远辉 , 等. 基于WorldView-2数据和支持向量机的红树林群落分类研究[J]. 中山大学学报(自然科学版), 2015,54(4):102-111.
[6]	Tang H L, Liu K, Zhu Y H , et al. Mangrove community classification based on WorldView-2 image and SVM method[J]. Acta Scientiarum Naturalium Universitatis Sunyatseni, 2015,54(4):102-111.
[7]	肖海燕, 曾辉, 昝启杰 , 等. 基于高光谱数据和专家决策法提取红树林群落类型信息[J]. 遥感学报, 2007,11(4):531-537. doi: 10.11834/jrs.20070473
[7]	Xiao H Y, Zeng H, Zan Q J , et al. Decision tree model in extraction of mangrove community information using hyperspectral image data[J]. Journal of Remote Sensing, 2007,11(4):531-537.
[8]	Wang T, Zhang H, Lin H , et al. Textural-spectral feature-based species classification of mangroves in Mai Po Nature Reserve from WorldView-3 imagery[J]. Remote Sensing, 2016,8(1):241-255.
[9]	Leempoel K, Satyaranayana B, Bourgeois C , et al. Dynamics in mangroves assessed by high-resolution and multi-temporal satellite data:A case study in Zhanjiang Mangrove National Nature Reserve (ZMNNR),P.R.China[J]. Biogeosciences, 2013,10(8):5681-5689.
[10]	苏岫, 赵冬至, 王祥 , 等. 基于SPOT5的红树林遥感分类[J]. 热带海洋学报, 2012,31(6):128-134. doi: 10.3969/j.issn.1009-5470.2012.06.020
[10]	Su X, Zhao D Z, Wang X , et al. Remote sensing classification of mangrove based on SPOT5 image[J]. Journal of Tropical Oceanography, 2012,31(6):128-134.
[11]	廖宝文, 张乔民 . 中国红树林的分布、面积和树种组成[J], 湿地科学, 2014,12(4):435-440.
[11]	Liao B W, Zhang Q M . Area,distribution and species composition of mangroves in China[J]. Wetland Science, 2014,12(4):435-440.
[12]	赵玉灵 . 广东省海岸线与红树林现状遥感调查与保护建议[J]. 国土资源遥感, 2017,29(s1):114-120.doi: 10.6046/gtzyyg.2017.s1.19.
[12]	Zhao Y L . Remote sensing survey and proposal for protection of the shoreline and the mangrove wetland in Guangdong Province[J]. Remote Sensing for Land and Recourses, 2017,29(s1):114-120.doi: 10.6046/gtzyyg.2017.s1.19.
[13]	刘静, 马克明, 曲来叶 . 广东湛江红树林国家级自然保护区优势乔木群落的物种组成及结构特征[J]. 生态科学, 2016,35(3):1-7.
[13]	Liu J, Ma K M, Qu L Y . Species composition and community structure of dominant mangrove forests in Zhanjiang Mangrove National Nature Reserve,Guangdong Province[J]. Ecological Science, 2016,35(3):1-7.
[14]	吴培强, 马毅, 李晓敏 , 等. 广东省红树林资源变化遥感监测[J]. 海洋学研究, 2011,29(4):16-24.
[14]	Wu P Q, Ma Y, Li X M , et al. Remote sensing monitoring of the mangrove forests resources of Guangdong Province[J]. Journal of Marine Sciences, 2011,29(4):16-24.
[15]	韩维栋, 高秀梅, 卢昌义 , 等. 雷州半岛的红树林植物组成与群落生态[J]. 广西植物, 2003,23(2):127-132.
[15]	Han W D, Gao X M, Lu C Y , et al. Mangrove flora and associations of Leizhou Peninsula[J]. Guihaia, 2003,23(2):127-132.
[16]	吕婷婷, 周翔, 刘闯 , 等.东南亚地区红树林空间分布数据集(Mangrov_SEAsia_2015)[Z].全球变化科学研究数据出版系统, 2015.
[16]	Lyu T T, Zhou X, Liu C , et al. Data set of mangrove spatial distribution in Southeast Asia(Mangrov_SEAsia_2015)[Z].Global Change Research Date Publish and Repository, 2015.
[17]	吴培强 . 近20年来我国红树林资源变化遥感监测与分析[D]. 国家海洋局第一海洋研究所, 2012.
[17]	Wu P Q . Remote Sensing Monitoring and Analysis of the Changes of Mangrove Forests Resources in China in the Past 20 Years[D].The First Institute of Oceanography, SOA, 2012.
[18]	缪绅裕 . 广东湛江红树林保护区植物群落生态研究[J]. 广州师院学报(自然科学版), 2000,21(3):65-69.
[18]	Miao S Y . Ecological study on the mangrove forest in Zhanjiang Nature Reserve,Guangdong[J]. Journal of Guangzhou Normal University(Natural Science Edition), 2000,21(3):65-69.
[19]	梁士楚, 王伯荪 . 广西英罗港红树林区木榄群落土壤粒径分布的分形特征[J]. 热带海洋学报, 2003,22(1):17-22.
[19]	Liang S C, Wang B S . Fractal characteristics of soil particle-size distribution of Bruguiera gymnorrhiza community in mangrove area of Yingluo Bay,Guangxi Province[J], Journal of Tropical Oceanography, 2003,22(1):17-22.

[1]	FAN Yinglin, LOU Debo, ZHANG Changqing, WEI Yingjuan, JIA Fudong. Information extraction technologies of iron mine tailings based on object-oriented classification: A case study of Beijing-2 remote sensing images of the Qianxi Area, Hebei Province[J]. Remote Sensing for Natural Resources, 2021, 33(4): 153-161.
[2]	CAI Xiang, LI Qi, LUO Yan, QI Jiandong. Surface features extraction of mining area image based on object-oriented and deep-learning method[J]. Remote Sensing for Land & Resources, 2021, 33(1): 63-71.
[3]	Jisheng XIA, Mengying MA, Zhongren FU. Extraction of mechanical damage surface using GF-2 remote sensing data[J]. Remote Sensing for Land & Resources, 2020, 32(2): 26-32.
[4]	Linyan FENG, Bingxiang TAN, Xiaohui WANG, Xinyun CHEN, Weisheng ZENG, Zhao QI. Object-oriented rapid forest change detection based on distribution function[J]. Remote Sensing for Land & Resources, 2020, 32(2): 73-80.
[5]	Liping YANG, Meng MA, Wei XIE, Xueping PAN. Fusion algorithm evaluation of Landsat 8 panchromatic and multispetral images in arid regions[J]. Remote Sensing for Land & Resources, 2019, 31(4): 11-19.
[6]	Hui HUANG, Xiongwei ZHENG, Genyun SUN, Yanling HAO, Aizhu ZHANG, Jun RONG, Hongzhang MA. Seismic image classification based on gravitational self-organizing map[J]. Remote Sensing for Land & Resources, 2019, 31(3): 95-103.
[7]	Feng FU, Xinjie WANG, Jin WANG, Na WANG, Jihong TONG. Tree species and age groups classification based on GF-2 image[J]. Remote Sensing for Land & Resources, 2019, 31(2): 118-124.
[8]	Zhen CHEN, Yunshi ZHANG, Yuanyu ZHANG, Lingling SANG. A study of remote sensing monitoring methods for the high standard farmland[J]. Remote Sensing for Land & Resources, 2019, 31(2): 125-130.
[9]	Linlin LIANG, Liming JIANG, Zhiwei ZHOU, Yuxing CHEN, Yafei SUN. Object-oriented classification of unmanned aerial vehicle image for thermal erosion gully boundary extraction[J]. Remote Sensing for Land & Resources, 2019, 31(2): 180-186.
[10]	Yueru WANG, Pengpeng HAN, Shujing GUAN, Yu HAN, Lin YI, Tinggang ZHOU, Jinsong CHEN. Information extraction of Dracaena sanderiana planting area based on Landsat8 OLI data[J]. Remote Sensing for Land & Resources, 2019, 31(1): 133-140.
[11]	Chao MA, Fei YANG, Xuecheng WANG. Extracting tea plantations in southern hilly and mountainous region based on mesoscale spectrum and temporal phenological features[J]. Remote Sensing for Land & Resources, 2019, 31(1): 141-148.
[12]	Wei LI, Weinan LIU, Yueping JIA, Hongyang LIU, Yong TANG. Information extraction of the Ebinur Lake artemia based on object - oriented method[J]. Remote Sensing for Land & Resources, 2018, 30(4): 176-181.
[13]	Xue HE, Zhengrong ZOU, Yunsheng ZHANG, Shouji DU, Te ZHENG. Object-oriented classification method for oblique photogrammetric point clouds[J]. Remote Sensing for Land & Resources, 2018, 30(2): 87-92.
[14]	Yongtao JIN, Xiufeng YANG, Tao GAO, Huimin GUO, Shimeng LIU. The typical object extraction method based on object-oriented and deep learning[J]. Remote Sensing for Land & Resources, 2018, 30(1): 22-29.
[15]	LI Chungan, Liang Wenhai. Forest change detection using remote sensing image based on object-oriented change vector analysis[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(3): 77-84.

Viewed

Full text

Abstract

Cited

Shared

Discussed