耦合WorldView-2和珠海一号影像的红树林物种分布

高常军; 蒋侠朋; 甄佳宁; 王俊杰; 邬国锋

doi:10.11834/jrs.20221487

红树林遥感 | 浏览量 : 0 下载量: 405 CSCD: 6 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

耦合WorldView-2和珠海一号影像的红树林物种分布
Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images
2022年26卷第6期页码：1155-1168
纸质出版日期： 2022-06-07 ，
DOI： 10.11834/jrs.20221487

扫描看全文

高常军，蒋侠朋，甄佳宁，王俊杰，邬国锋.2022.耦合WorldView-2和珠海一号影像的红树林物种分布.遥感学报，26（6）： 1155-1168

Gao C J，Jiang X P，Zhen J N，Wang J J，Wu G F. 2022. Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images. National Remote Sensing Bulletin， 26（6）：1155-1168
高常军，蒋侠朋，甄佳宁，王俊杰，邬国锋.2022.耦合WorldView-2和珠海一号影像的红树林物种分布.遥感学报，26（6）： 1155-1168 DOI： 10.11834/jrs.20221487.

Gao C J，Jiang X P，Zhen J N，Wang J J，Wu G F. 2022. Mangrove species classification with combination of WorldView-2 and Zhuhai-1 satellite images. National Remote Sensing Bulletin， 26（6）：1155-1168 DOI： 10.11834/jrs.20221487.

摘要

红树林物种遥感分类受影像分辨率、波段信息、分类策略、影像特征选择方法等因素影响。现有的红树林物种遥感分类研究大多关注于分类精度的比较，较少报道商业高分与国产高光谱卫星的结合在物种分类的应用。基于湛江高桥红树林保护区的高分（WorldView-2）和高光谱（珠海一号）卫星影像，本文旨在利用随机森林分类方法，比较不同特征选择算法（极端梯度提升（XGBoost）、极端随机树（ERT）、连续投影算法（SPA））和不同空间分辨率（WorldView-2影像从0.5 m的分辨率重采样为1 m、2 m、4 m、8 m、10 m）对红树林物种分类精度的影响，并耦合WorldView-2与珠海一号影像研究红树林物种空间分布格局及影响因素。每种空间分辨率的WorldView-2影像提取248个特征（52个光谱特征及196个纹理特征），珠海一号影像提取117个光谱特征。结果表明，XGBoost方法优于ERT和SPA，在影像特征选择中具有巨大优势；与其他空间分辨率相比，2 m分辨率的WorldView-2影像具有更高的分类精度；耦合WorldView-2和珠海一号影像的分类精度（分辨率：2 m，总体精度：88.98%，kappa系数：0.846）高于单一的WorldView-2影像（分辨率：2 m，总体精度：83.47%，kappa系数：0.768）和珠海一号影像（分辨率：10 m，总体精度：78.50%，kappa系数：0.703）；另外，林窗、高程、离岸距离一定程度上影响红树林物种分布格局。本文表明WorldView-2与珠海一号高光谱影像的结合在景观及区域尺度上精确提取红树林物种信息具有巨大潜力，有利于红树林生物多样性保护及科学管理。

Abstract

Remotely sensed classification of mangrove species is affected by image resolution

spectral information

classification strategy

and image feature selection methods. The present studies of mangrove species classification using remote sensing mostly focus on comparison of classification accuracy

and few of them discuss the spatial pattern of species distribution and the corresponding influencing factors. The combination of high-resolution and hyperspectral satellite images in species classification of mangrove forest has received less attention. With WorldView-2 and Zhuhai-1 images in Gaoqiao mangrove Reserve

this study aims to compare the effects of different feature selection methods (XGBoost

eXtreme gradient boosting; ERT

extremely randomized trees; SPA

successive projections algorithm) and different image resolutions (the WorldView-2 image with a resolution of 0.5 m was resampled to 1

and 10 m) on the classification accuracy of mangrove species based on random forest classification model and to explore the spatial pattern of mangrove distribution and the corresponding influencing factors based on the coupling of WorldView-2 and Zhuhai-1 images.

With each spatial resolution of WorldView-2 image

248 features were extracted

including 52 spectral features (eight spectral bands

38 vegetation indices

three principal component bands

and three tasseled cap transformation bands) and 196 texture features (seven windows of 3×3

5×5

7×7

9×9

11×11

and 15×15; for each window

28 texture features were extracted). With Zhuhai-1 hyperspectral image

117 spectral features (32 original spectral bands

32 first derivative bands

47 vegetation indices

three principal component bands

and three tasseled cap transformation bands) were extracted.

Results showed that XGBoost was superior to ERT and SPA

which had great advantage in image feature selection. Among the six types of WorldView-2 image resolution

the 2 m resolution was optimal for species classification

and the red edge band (705—745 nm) played an important role in species classification. The coupling of WorldView-2 and Zhuhai-1 images (resolution: 2 m

overall accuracy: 88.98%

kappa coefficient: 0.846) had better performance than using single WorldView resolution: 2 m

overall accuracy: 83.47%

kappa coefficient: 0.768 and Zhuhai-1 image (resolution: 10 m

overall accuracy: 78.50%

kappa coefficient: 0.703). The classification map based on the coupled image features illustrated that the area of

Aegiceras corniculatum

accounted for the largest proportion (33.77 % )

followed by

Bruguiera gymnorrhiza

(30.44%)

Avicennia marina

(26.96%)

Bruguiera gymnorrhiza

(6.08%)

Sonneratia apetala

(2.72%)

and

Kandelia candel

(0.02%). Moreover

to some extent

forest gap

surface elevation

and offshore distance greatly affected the spatial distribution pattern of mangrove species.

This study demonstrated that the combination of WorldView-2 and Zhuhai-1 image had great potential in accurate mapping mangrove species at the landscape and regional scales

thereby facilitating biodiversity protection and scientific management of forest ecosystem and providing technical and data support for retrieval of ecosystem parameters (e.g.

carbon storage

net primary production

and leaf area index) and health evaluation of mangrove forests. Future research will focus on the fusion of WorldView-2 and Zhuhai-1 image to simultaneously achieve high spatial resolution and hyperspectral bands and the inclusion of canopy height and leaf trait information (e.g.

chlorophyll and water content) to the classification model.

关键词

遥感红树林WorldView-2影像珠海一号影像物种分类极端梯度提升极端随机树连续投影算法

Keywords

remote sensingmangroveWorldView-2 imageZhuhai-1 imagespecies classificationXGBoostextremely randomized treessuccessive projections algorithm

references

Araújo M C U, Saldanha T C B, Galvão R K H, Yoneyama T, Chame H C and Visani V. 2001. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems, 57(2): 65-73 [DOI: 10.1016/S0169-7439(01)00119-8http://dx.doi.org/10.1016/S0169-7439(01)00119-8]

Cao J J, Leng W C, Liu K, Liu L, He Z and Zhu Y H. 2018a. Object-based mangrove species classification using unmanned aerial vehicle hyperspectral images and digital surface models. Remote Sensing, 10(1): 89 [DOI: 10.3390/rs10010089http://dx.doi.org/10.3390/rs10010089]

Cao J J, Liu K, Liu L, Zhu Y H, Li J and He Z. 2018b. Identifying mangrove species using field close-range snapshot hyperspectral imaging and machine-learning techniques. Remote Sensing, 10(12): 2047 [DOI: 10.3390/rs10122047http://dx.doi.org/10.3390/rs10122047]

Chen T Q and Guestrin C. 2016. XGBoost: a scalable tree boosting system//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM: 785-794 [DOI: 10.1145/2939672.2939785http://dx.doi.org/10.1145/2939672.2939785]

George R, Padalia H, Sinha S K and Kumar A S. 2019. Evaluating sensitivity of hyperspectral indices for estimating mangrove chlorophyll in Middle Andaman Island, India. Environmental Monitoring and Assessment, 191(S3): 785 [DOI: 10.1007/s10661-019-7679-6http://dx.doi.org/10.1007/s10661-019-7679-6]

Geurts P, Ernst D and Wehenkel L. 2006. Extremely randomized trees. Machine Learning, 63(1): 3-42 [DOI: 10.1007/s10994-006-6226-1http://dx.doi.org/10.1007/s10994-006-6226-1]

Heenkenda M K, Joyce K E, Maier S W and Bartolo R. 2014. Mangrove species identification: comparing worldview-2 with aerial photographs. Remote Sensing, 6(7): 6064-6088 [DOI: 10.3390/rs6076064http://dx.doi.org/10.3390/rs6076064]

Hu L J, Xu N, Liang J, Li Z C, Chen L Z and Zhao F. 2020. Advancing the mapping of mangrove forests at national-scale using Sentinel-1 and Sentinel-2 time-series data with google Earth engine: a case study in China. Remote Sensing, 12(19): 3120 [DOI: 10.3390/rs12193120http://dx.doi.org/10.3390/rs12193120]

Huang J J, Liu S Q and Han W D. 2012. The analysis of mangrove inside zone gap feature in Gaoqiao, Leizhou peninsula. Forest Resources Management, (5): 46-50

黄剑坚, 刘素青, 韩维栋. 2012. 雷州半岛高桥红树林内带林窗特征分析——以湛江市廉江高桥红树林保护小区为例.林业资源管理, (5): 46-50 [DOI: 10.3969/j.issn.1002-6622.2012.05.009http://dx.doi.org/10.3969/j.issn.1002-6622.2012.05.009]

Jia M M, Wang Z M, Zhang Y Z, Mao D H and Wang C. 2018. Monitoring loss and recovery of mangrove forests during 42 years: the achievements of mangrove conservation in China. International Journal of Applied Earth Observation and Geoinformation, 73: 535-545 [DOI: 10.1016/j.jag.2018.07.025http://dx.doi.org/10.1016/j.jag.2018.07.025]

Jia M M, Zhang Y Z, Wang Z M, Song K S and Ren C Y. 2014. Mapping the distribution of mangrove species in the Core Zone of Mai Po Marshes Nature Reserve, Hong Kong, using hyperspectral data and high-resolution data. International Journal of Applied Earth Observation and Geoinformation, 33: 226-231 [DOI: 10.1016/j.jag.2014.06.006http://dx.doi.org/10.1016/j.jag.2014.06.006]

Jiang Y F, Zhang L, Yan M, Qi J G, Fu T M, Fan S X and Chen B W. 2021. High-resolution mangrove forests classification with machine learning using worldview and UAV hyperspectral data. Remote Sensing, 13(8): 1529 [DOI: 10.3390/rs13081529http://dx.doi.org/10.3390/rs13081529]

Kahaer Y, Tashpolat N, Shi Q D and Liu S H. 2020. Possibility of Zhuhai-1 hyperspectral imagery for monitoring salinized soil moisture content using fractional order differentially optimized spectral indices. Water, 12(12): 3360 [DOI: 10.3390/w12123360http://dx.doi.org/10.3390/w12123360]

Kamal M, Phinn S and Johansen K. 2014. Characterizing the spatial structure of mangrove features for optimizing image-based mangrove mapping. Remote Sensing, 6(2): 984-1006 [DOI: 10.3390/rs6020984http://dx.doi.org/10.3390/rs6020984]

Kamal M, Phinn S and Johansen K. 2015. Object-based approach for multi-scale mangrove composition mapping using multi-resolution image datasets. Remote Sensing, 7(4): 4753-4783 [DOI: 10.3390/rs70404753http://dx.doi.org/10.3390/rs70404753]

Kumar T, Mandal A, Dutta D, Nagaraja R and Dadhwal V K. 2019. Discrimination and classification of mangrove forests using EO-1 Hyperion data: a case study of Indian Sundarbans. Geocarto International, 34(4): 415-442 [DOI: 10.1080/10106049.2017.1408699http://dx.doi.org/10.1080/10106049.2017.1408699]

Leong R C, Friess D A, Crase B, Lee W K and Webb E L. 2018. High-resolution pattern of mangrove species distribution is controlled by surface elevation. Estuarine, Coastal and Shelf Science, 202: 185-192 [DOI: 10.1016/j.ecss.2017.12.015http://dx.doi.org/10.1016/j.ecss.2017.12.015]

Li H Y, Jia M M, Zhang R, Ren Y X and Wen X. 2019a. Incorporating the plant phenological trajectory into mangrove species mapping with dense time series Sentinel-2 imagery and the Google Earth Engine platform. Remote Sensing, 11(21): 2479 [DOI: 10.3390/rs11212479http://dx.doi.org/10.3390/rs11212479]

Li Q S, Wong F K K and Fung T. 2019b. Classification of mangrove species using combined wordview-3 and LiDAR data in Mai Po nature reserve, Hong Kong. Remote Sensing, 11(18): 2114 [DOI: 10.3390/rs11182114http://dx.doi.org/10.3390/rs11182114]

Li Y Q, Zuo X Q and Li H Z. 2020. Study on the separability measurement of mangrove population based on random forest——a case study of Shenzhen bay. Journal of Shaanxi University of Technology (Natural Science Edition), 36(2): 64-70, 92

李雨秦, 左小清, 李洪忠. 2020. 基于随机森林的红树林种群可分性度量研究——以深圳湾为例. 陕西理工大学学报(自然科学版), 36(2): 64-70, 92 [DOI: 10.3969/j.issn.1673-2944.2020.02.011http://dx.doi.org/10.3969/j.issn.1673-2944.2020.02.011]

Lu Y P, Xu W H, Zhang Z M, Zhang L, Xie S L, Zhang J J, Fan X Y and Ouyang Z Y. Gap analysis of mangrove ecosystem conservation in China. Acta Ecologica Sinica, 2019, 39(2): 684-691

卢元平, 徐卫华, 张志明, 张路, 谢世林, 张晶晶, 范馨悦, 欧阳志云. 中国红树林生态系统保护空缺分析. 生态学报, 2019, 39(2): 684-691 [DOI: 10.5846/stxb201804080794http://dx.doi.org/10.5846/stxb201804080794]

Ma C L, Ai B, Zhao J, Xu X P and Huang W. 2019. Change detection of mangrove forests in coastal Guangdong during the past three decades based on remote sensing data. Remote Sensing, 11(8): 921 [DOI: 10.3390/rs11080921http://dx.doi.org/10.3390/rs11080921]

Majdar R S and Ghassemian H. 2017. A probabilistic SVM approach for hyperspectral image classification using spectral and texture features. International Journal of Remote Sensing, 38(15): 4265-4284 [DOI: 10.1080/01431161.2017.1317941http://dx.doi.org/10.1080/01431161.2017.1317941]

Mallinis G, Koutsias N, Tsakiri-Strati M and Karteris M. 2008. Object-based classification using Quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site. ISPRS Journal of Photogrammetry and Remote Sensing, 63(2): 237-250 [DOI: 10.1016/j.isprsjprs.2007.08.007http://dx.doi.org/10.1016/j.isprsjprs.2007.08.007]

Peng L H, Liu K, Cao J J, Zhu Y H, Li F S and Liu L. 2020. Combining GF-2 and RapidEye satellite data for mapping mangrove species using ensemble machine-learning methods. International Journal of Remote Sensing, 41(3): 813-838 [DOI: 10.1080/01431161.2019.1648907http://dx.doi.org/10.1080/01431161.2019.1648907]

Pham T D, Yokoya N, Bui D T, Yoshino K and Friess D A. 2019. Remote sensing approaches for monitoring mangrove species, structure, and biomass: opportunities and challenges. Remote Sensing, 11(3): 230 [DOI: 10.3390/rs11030230http://dx.doi.org/10.3390/rs11030230]

Tian J Y, Wang L, Li X J, Gong H L, Shi C, Zhong R F and Liu X M. 2017. Comparison of UAV and WorldView-2 imagery for mapping leaf area index of mangrove forest. International Journal of Applied Earth Observation and Geoinformation, 61: 22-31 [DOI: 10.1016/j.jag.2017.05.002http://dx.doi.org/10.1016/j.jag.2017.05.002]

Toosi N B, Soffianian A R, Fakheran S, Pourmanafi S, Ginzler C and Waser L T. 2019. Comparing different classification algorithms for monitoring mangrove cover changes in southern Iran. Global Ecology and Conservation, 19: e00662 [DOI: 10.1016/j.gecco.2019.e00662http://dx.doi.org/10.1016/j.gecco.2019.e00662]

Valderrama-Landeros L, Flores-de-Santiago F, Kovacs J M and Flores-Verdugo F. 2018. An assessment of commonly employed satellite-based remote sensors for mapping mangrove species in Mexico using an NDVI-based classification scheme. Environmental Monitoring and Assessment, 190(1): 23 [DOI: 10.1007/s10661-017-6399-zhttp://dx.doi.org/10.1007/s10661-017-6399-z]

Wan L M, Lin Y Y, Zhang H S, Wang F, Liu M F and Lin H. 2020. GF-5 hyperspectral data for species mapping of mangrove in Mai Po, Hong Kong. Remote Sensing, 12(4): 656 [DOI: 10.3390/rs12040656http://dx.doi.org/10.3390/rs12040656]

Wang D Z, Wan B, Qiu P H, Su Y J, Guo Q H, Wang R, Sun F and Wu X C. 2018a. Evaluating the performance of sentinel-2, landsat 8 and pléiades-1 in mapping mangrove extent and species. Remote Sensing, 10(9): 1468 [DOI: 10.3390/rs10091468http://dx.doi.org/10.3390/rs10091468]

Wang D Z, Wan B, Qiu P H, Su Y J, Guo Q H and Wu X C. 2018b. Artificial mangrove species mapping using pléiades-1: an evaluation of pixel-based and object-based classifications with selected machine learning algorithms. Remote Sensing, 10(2): 294 [DOI: 10.3390/rs10020294http://dx.doi.org/10.3390/rs10020294]

Wang J J, Xu Y and Wu G F. 2020a. The integration of species information and soil properties for hyperspectral estimation of leaf biochemical parameters in mangrove forest. Ecological Indicators, 115: 106467 [DOI: 10.1016/j.ecolind.2020.106467http://dx.doi.org/10.1016/j.ecolind.2020.106467]

Wang W Q, Fu H F, Lee S Y, Fan H Q and Wang M. 2020b. Can strict protection stop the decline of mangrove ecosystems in China? From rapid destruction to rampant degradation. Forests, 11(1): 55 [DOI: 10.3390/f11010055http://dx.doi.org/10.3390/f11010055]

Wang X, Li H W, Qiu Z J, Yang H, Zhou G Y and Liao B W. 2009. Research on the difference of the structural feature of artificial sonneratia apetala-S. Caseolaris community and its affecting factor. Journal of Anhui Agricultural Sciences, 37(27): 13312-13316

王旭, 李洪旺, 邱志军, 杨怀, 周光益, 廖宝文. 2009. 不同离岸距离海桑+无瓣海桑红树群落的林分结构差异及其影响因子. 安徽农业科学, 37(27): 13312-13316

Watt A S. 1947. Pattern and process in the plant community. Journal of Ecology, 35(1/2): 1-22 [DOI: 10.2307/2256497http://dx.doi.org/10.2307/2256497]

Xu Y, Wang J J, Xia A Q, Zhang K Y, Dong X Y, Wu K P and Wu G F. 2019. Continuous wavelet analysis of leaf reflectance improves classification accuracy of mangrove species. Remote Sensing, 11(3): 254 [DOI: 10.3390/rs11030254http://dx.doi.org/10.3390/rs11030254]

Xu Y, Zhen J N, Jiang X P and Wang J J. 2021. Mangrove species classification with UAV-based remote sensing data and XGBoost. National Remote Sensing Bulletin, 25(3): 737-752

徐逸, 甄佳宁, 蒋侠朋, 王俊杰. 2021. 无人机遥感与XGBoost的红树林物种分类. 遥感学报, 25(3): 737-752 [DOI: 10.11834/jrs.20210281http://dx.doi.org/10.11834/jrs.20210281]

Zhang H S, Wang T, Liu M F, Jia M M, Lin H, Chu L M and Devlin A T. 2018. Potential of combining optical and dual polarimetric SAR data for improving mangrove species discrimination using rotation forest. Remote Sensing, 10(3): 467 [DOI: 10.3390/rs10030467http://dx.doi.org/10.3390/rs10030467]

Zhang X W, Zhang J C, Chen W Y, Liu W, Zhang Z J, Fan J W, Xiao C J and Wang R. 2021a. Semi-automated extraction of surface water based on ZhuHai-1 hyperspectral satellite images. Remote Sensing Letters, 12(8): 750-756 [DOI: 10.1080/2150704X.2021.1934593http://dx.doi.org/10.1080/2150704X.2021.1934593]

Zhang Y Y, Yang J and Du L. 2021b. Analyzing the effects of hyperspectral ZhuHai-1 band combinations on LAI estimation based on the PROSAIL model. Sensors, 21(5): 1869 [DOI: 10.3390/s21051869http://dx.doi.org/10.3390/s21051869]

Zhen J N, Jiang X P, Xu Y, Miao J, Zhao D M, Wang J J, Wang J Z and Wu G F. 2021. Mapping leaf chlorophyll content of mangrove forests with Sentinel-2 images of four periods. International Journal of Applied Earth Observation Geoinformation, 102: 102387 [DOI: 10.1016/j.jag.2021.102387http://dx.doi.org/10.1016/j.jag.2021.102387]

Zheng Y, Lin Y Q, Zhou J, Gan W X, Lin G X, Xu F H and Lin G H. 2019. Mangrove inter-species classification based on ZY-3 image in Leizhou Peninsula, Guangdong Province. Remote Sensing For Land & Resources, 31(3): 201-208

郑艺, 林懿琼, 周建, 甘伟修, 林广旋, 许方宏, 林光辉. 2019. 基于资源三号的雷州半岛红树林种间分类研究. 国土资源遥感, 31(3): 201-208 [DOI: 10.6046/gtzyyg.2019.03.25http://dx.doi.org/10.6046/gtzyyg.2019.03.25]

文章被引用时，请邮件提醒。

提交

1990年—2020年粤港澳大湾区红树林动态变化遥感监测

融合Landsat 8与Sentinel-2数据的红树林物候信息提取与分类

无人机多光谱和LiDAR的红树林精细识别与生物量估算

无人机遥感与XGBoost的红树林物种分类