基于Sentinel-1和Sentinel-2影像的洪泽湖国家湿地公园水生植被信息提取

doi:10.12302/j.issn.1000-2006.202212016

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2024, Vol. 48 ›› Issue (2): 19-26.doi: 10.12302/j.issn.1000-2006.202212016

• 专题报道Ⅰ: 山水林田湖草沙一体化保护———湿地生态研究专题（执行主编张金池薛建辉） • 上一篇下一篇

基于Sentinel-1和Sentinel-2影像的洪泽湖国家湿地公园水生植被信息提取

韩森(), 阮仁宗^*(), 傅巧妮, 许捍卫, 衡雪彪

河海大学水文水资源学院,江苏南京 210098

收稿日期:2022-12-09 修回日期:2023-03-07 出版日期:2024-03-30 发布日期:2024-04-08
通讯作者: *阮仁宗(ruanrenzong@163.com),副教授。
作者简介:韩森(2902053779@qq.com)。
基金资助:
应急管理部国家减灾中心-中国人民财产保险股份有限公司联合实验室2020年度开放基金(NDRCCPICC202003)

Extraction of aquatic vegetation in Hongze Lake National Wetland Park based on Sentinel-1 and Sentinel-2 images

HAN Sen(), RUAN Renzong^*(), FU Qiaoni, XU Hanwei, HENG Xuebiao

College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China

Received:2022-12-09 Revised:2023-03-07 Online:2024-03-30 Published:2024-04-08

摘要/Abstract

摘要：

【目的】探索利用光学遥感和雷达遥感数据进行湖泊湿地水生植被信息提取方法。【方法】以洪泽湖国家湿地公园为研究区,基于Sentinel-1的SAR影像和Sentinel-2的MSI影像,利用面向对象影像分析技术,结合EVSI、NDVI、SR特征指数和对象之间的上下文特征,以及挺水植被高度的差异所对应SAR影像上的后向散射系数,在对象级的基础上建立决策树模型对湿地水生植被进行分类,分析洪泽湖国家湿地公园水生植被以及挺水植被的分布状况。【结果】研究区水生植被类群分类精度为89%,Kappa系数为0.85;挺水植被种群分类精度为85.2%,Kappa系数为0.76。与基于像元分析方法的结果相比,面向对象的影像分析方法具有更高的精度;湿地水生植被以沉水植被和挺水植被为主,其中挺水植被中以荷叶和芦苇为主。【结论】本研究提出的湖泊湿地水生植被信息提取方法具可行性,可为湿地管理与决策提供科学依据。

关键词: 水生植被, Sentinel-1, Sentinel-2, 决策树, 植被特征指数, 后向散射系数, 洪泽湖国家湿地公园

Abstract:

【Objective】 The objective of this study was to explore the extraction of spatio-temporal distribution of aquatic vegetation in lake wetlands using Sentinel-1 and Sentinel-2 data. 【Method】 Hongze Lake National Wetland Park was chosen as the research area. Based on the combination of Sentinel-2 MSI images and Sentinel-1 SAR images, the object-oriented image analysis was used. The feature set was constructed by using EVSI, NDVI, SR feature index and contextual features between objects, as well as differences in the backscatter coefficients of the SAR images corresponding to differences in the height of the emergent vegetation types. A decision-tree model was established at the object level to classify the wetland, and the spatio-temporal distribution of the aquatic vegetation and the emergent vegetation in the Hongze Lake National Wetland Park was acquired. 【Result】 The classification accuracy and the Kappa coefficient of aquatic vegetation were observed to be 89% and 0.85, respectively, and that of the emergent vegetation was 85.2% and 0.76, respectively. The results showed that, compared with the results of the pixel-based analysis method, the accuracy of object-based image analysis was higher. The wetland aquatic vegetation was dominated by submerged and emergent vegetation; among the emergent vegetation, lotus leaves and reeds were dominant. 【Conclusion】 The methods proposed in this study were feasible, and the results could provide a scientific basis for managers and planners of wetlands.

Key words: aquatic vegetation, Sentinel-1, Sentinel-2, decision tree, vegetation characteristic index, backscatter coefficient, Hongze Lake National Wetland Park

中图分类号:

S759
TP75

韩森,阮仁宗,傅巧妮,等. 基于Sentinel-1和Sentinel-2影像的洪泽湖国家湿地公园水生植被信息提取[J]. 南京林业大学学报（自然科学版）, 2024, 48(2): 19-26.

HAN Sen, RUAN Renzong, FU Qiaoni, XU Hanwei, HENG Xuebiao. Extraction of aquatic vegetation in Hongze Lake National Wetland Park based on Sentinel-1 and Sentinel-2 images[J].Journal of Nanjing Forestry University (Natural Science Edition), 2024, 48(2): 19-26.DOI: 10.12302/j.issn.1000-2006.202212016.

图/表 11

图1

图2

表1

特征指数选择"

项目 item	特征指数 characteristic index	公式 formula	备注 notes
自定义特征 custom feature	挺水植被指数EVSI(I_EVS)	I_EVS=(B_8a-B₄)/(B_8a+B₄)	B.波段值the band value;b(v,u).类型v、u的公共边界长度the common boundary length of types v and u;N_v(d).对象v在距离d处的相邻对象the adjacent object of object v at a distance of d;b_v.图像对象的边界长度the boundary length of the image object;^#P_u.包含在P_u中的像素总数the total number of pixels included in P_u
	归一化植被指数NDVI(I_NDV)	I_NDV=(B₈-B₄)/(B₈+B₄)
	沉水植被指数SR(R_S)	R_S=(B₄/B₈)×255
上下文关系 context relation	相邻某确定类别与图斑面积比R_{area to farm}	R_{area to farm}= $∑ u ∈ N v (d, m) # p u ∑ u ∈ N v (d) # p u$
上下文关系 context relation	相邻某确定类别与图斑共享的边界长度除以总边界长度R_{border to farm}	R_{border to farm}=[ $∑ u ∈ N v (d, m)$ b(v,u)]/b_v

表1

图3

图4

图5

图6

图7

表2

图8

表3

参考文献 32

[1]	MURPHY F, SCHMIEDER K, BAASTRUP-SPOHR L, et al. Five decades of dramatic changes in submerged vegetation in lake constance[J]. Aquat Bot, 2018, 144:31-37.DOI: 10.1016/j.aquabot.2017.10.006.
[2]	罗菊花, 杨井志成, 段洪涛, 等. 浅水湖泊水生植被遥感监测研究进展[J]. 遥感学报, 2022, 26(1):68-76.
	LUO J H, YANG J, DUAN H T, et al. Research progress of aquatic vegetation remote sensing in shallow lakes[J]. J Remote Sens, 2022, 26(1):68-76.
[3]	MASSICOTTE P, BERTOLO A, BRODEUR P, et al. Influence of the aquatic vegetation landscape on larval fish abundance[J]. J Gt Lakes Res, 2015, 41(3):873-880.DOI: 10.1016/j.jglr.2015.05.010.
[4]	RUAN R Z, ZHANG L. Changes of Hongze Lake wetlands in the past three decades[C]// 2010 6th International Conference on Wireless Communications Networking and Mobile Computing (WiCOM).Chengdu:IEEE, 2010:1-4.DOI: 10.1109/WICOM.2010.5601034.
[5]	夏双, 阮仁宗, 颜梅春, 等. 洪泽湖湿地类型变化分析[J]. 南京林业大学学报(自然科学版), 2012, 36(1):38-42.
	XIA S, RUAN R Z, YAN M C, et al. Analysis of long-term change in Hongze Lake wetlands[J]. J Nanjing For Univ (Nat Sci Ed), 2012, 36(1):38-42.DOI: 10.3969/j.issn.1000-2006.2012.01.008.
[6]	阮仁宗, 冯学智, 肖鹏峰, 等. 洪泽湖天然湿地的长期变化研究[J]. 南京林业大学学报(自然科学版), 2005, 29(4):57-60.
	RUAN R Z, FENG X Z, XIAO P F, et al. Long-term change of natural wetland of Hongze Lake[J]. J Nanjing For Univ, 2005, 29(4):57-60.DOI: 10.3969/j.issn.1000-2006.2005.04.014.
[7]	FÜLÖP G. Performance of Sentinel-2 data in unsupervised classification:a case study of statistical comparison with Landsat 8 OLI[J]. J Agric Inform, 2016, 7(1):1-12.DOI: 10.17700/jai.2016.7.1.280.
[8]	阮仁宗, 夏双, 陈远, 等. 1979—2006年洪泽湖西岸临淮镇附近湖泊变化研究[J]. 湿地科学, 2012, 10(3):344-349.
	RUAN R Z, XIA S, CHEN Y, et al. Change of lake nearby Linhuai Town in west bank of Hongze Lake during 1979-2006[J]. Wetl Sci, 2012, 10(3):344-349.DOI: 10.13248/j.cnki.wetlandsci.2012.03.014.
[9]	张殿岱, 王雪梅. 基于高分辨率遥感影像的植被分类方法比较[J]. 林业资源管理, 2021(3):108-113.
	ZHANG D D, WANG X M. Comparison of vegetation classification methods based on high resolution remote sensing image[J]. For Resour Manag, 2021(3):108-113.DOI: 10.13466/j.cnki.lyzygl.2021.03.017.
[10]	COLKESEN I, KAVZOGLU T. Ensemble-based canonical correlation forest (CCF) for land use and land cover classification using Sentinel-2 and Landsat OLI imagery[J]. Remote Sens Lett, 2017, 8(11):1082-1091.DOI: 10.1080/2150704X.2017.1354262.
[11]	PULETTI N, CHIANUCCI F, CASTALDI C. Use of Sentinel-2 for forest classification in Mediterranean environments[J]. 2017, 12(4):1463-1450.DOI:10.12899/ASR-1463.
[12]	WANG Y Q, MITCHELL B R, NUGRANAD-MARZILLI J, et al. Remote sensing of land-cover change and landscape context of the National Parks:a case study of the Northeast Temperate Network[J]. Remote Sens Environ, 2009, 113(7):1453-1461.DOI: 10.1016/j.rse.2008.09.017.
[13]	XUE B, LIN X H. Water system segmentation method of high resolution remote sensing image based on eCognition[J]. J Phys:Conf Ser, 2020, 1651(1):012162.DOI: 10.1088/1742-6596/1651/1/012162.
[14]	聂倩, 七珂珂, 赵艳福. 融入超像素分割的高分辨率影像面向对象分类[J]. 测绘通报, 2021(6):44-49.
	NIE Q, QI K K, ZHAO Y F. Object-oriented classification of high-resolution image combining super-pixel segmentation[J]. Bull Surv Mapp, 2021(6):44-49.DOI: 10.13474/j.cnki.11-2246.2021.0174.
[15]	STEINHAUSEN M J, WAGNER P D, NARASIMHAN B, et al. Combining Sentinel-1 and Sentinel-2 data for improved land use and land cover mapping of monsoon regions[J]. Int J Appl Earth Obs Geoinf, 2018, 73:595-604.DOI: 10.1016/j.jag.2018.08.011.
[16]	RUIZ L F C, GUASSELLI L A, SIMIONI J P D, et al. Object-based classification of vegetation species in a subtropical wetland using Sentinel-1 and Sentinel-2A images[J]. Sci Remote Sens, 2021, 3:100017.DOI: 10.1016/j.srs.2021.100017.
[17]	WHYTE A, FERENTINOS K P, PETROPOULOS G P. A new synergistic approach for monitoring wetlands using Sentinels-1 and 2 data with object-based machine learning algorithms[J]. Environ Model Softw, 2018, 104:40-54.DOI: 10.1016/j.envsoft.2018.01.023.
[18]	王靖, 吴见. 融入空间信息的湿地信息提取技术[J]. 南京林业大学学报(自然科学版), 2014, 38(4):19-22.
	WANG J, WU J. Wetland information extraction technology integrated by spatial information[J]. J Nanjing For Univ (Nat Sci Ed), 2014, 38(4):19-22.DOI: 10.3969/j.issn.1000-2006.2014.04.004.
[19]	刘瑞清, 李加林, 孙超, 等. 基于Sentinel-2遥感时间序列植被物候特征的盐城滨海湿地植被分类[J]. 地理学报, 2021, 76(7):1680-1692.
	LIU R Q, LI J L, SUN C, et al. Classification of Yancheng coastal wetland vegetation based on vegetation phenological characteristics derived from Sentinel-2 time-series[J]. Acta Geogr Sin, 2021, 76(7):1680-1692.DOI: 10.11821/dlxb202107008.
[20]	吴翼, 戴蓉, 徐勇峰, 等. 洪泽湖河湖交汇区土地利用时空动态[J]. 南京林业大学学报(自然科学版), 2016, 40(4):22-28.
	WU Y, DAI R, XU Y F, et al. Spatial and temporal changes in wetland use in the meeting place of Hung-tse Lake and Huaihe River[J]. J Nanjing For Univ (Nat Sci Ed), 2016, 40(4):22-28.DOI: 10.3969/j.issn.1000-2006.2016.04.004.
[21]	张楼香, 阮仁宗, 夏双. 洪泽湖湿地纹理特征参数分析[J]. 国土资源遥感, 2015, 27(1):75-80.
	ZHANG L X, RUAN R Z, XIA S. Parameter analysis of image texture of wetland in the Hongze Lake[J]. Remote Sens Land Resour, 2015, 27(1):75-80.DOI: 10.6046/gtzyyg.2015.01.12.
[22]	姚建平. 洪泽湖自然资源的开发和利用[J]. 自然资源, 1994, 16(5):25-30.
	YAO J P. The development and utilization of natural resources in Hongze Lake[J]. Nat Resour, 1994, 16(5):25-30.
[23]	杨斌, 李丹, 王磊, 等. 基于Sentinel-2A岷江上游地表生物量反演与植被特征分析[J]. 科技导报, 2017, 35(21):74-80.
	YANG B, LI D, WANG L, et al. Retrieval of surface vegetation biomass information and analysis of vegetation feature based on Sentinel-2A in the upper of Minjiang River[J]. Sci Technol Rev, 2017, 35(21):74-80.DOI: 10.3981/j.issn.1000-7857.2017.21.009.
[24]	DEFINIENTS IMAGE GMBH. eCognition User Guide[S]. Germany: Trimble, 2004.
[25]	BAATZ M, BENZ U, DEHGHANI S. eCognition Developer 8.0.1-User Guide[S]. Germany: Trimble, 2010.
[26]	DRǍGUŢ L, TIEDE D, LEVICK S R. ESP:a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data[J]. Int J Geogr Inf Sci, 2010, 24(6):859-871.DOI: 10.1080/13658810903174803.
[27]	国土资源部.TD/T 1063-1994 土地利用现状调查省级汇总技术规程[S]. 北京: 中国标准出版社,1994.
[28]	疏小舟, 尹球, 匡定波. 内陆水体藻类叶绿素浓度与反射光谱特征的关系[J]. 遥感学报, 2000, 4(1):41-45.
	SHU X Z, YIN Q, KUANG D B. Relationship between algal chlorophyll concentration and spectral reflectance of inland water[J]. J Remote Sens, 2000, 4(1):41-45.DOI: 10.3321/j.issn:1007-4619.2000.01.008.
[29]	FRIEDL M A, BRODLEY C E. Decision tree classification of land cover from remotely sensed data[J]. Remote Sens Environ, 1997, 61(3):399-409.DOI: 10.1016/s0034-4257(97)00049-7.
[30]	HANSEN M, DUBAYAH R, DEFRIES R. Classification trees:an alternative to traditional land cover classifiers[J]. Int J Remote Sens, 1996, 17(5):1075-1081.DOI: 10.1080/01431169608949069.
[31]	LUO J H, LI X C, MA R H, et al. Applying remote sensing techniques to monitoring seasonal and interannual changes of aquatic vegetation in Taihu Lake,China[J]. Ecol Indic, 2016, 60:503-513.DOI: 10.1016/j.ecolind.2015.07.029.
[32]	ZHU J G, HU W P, LIU X, et al. A review of the studies on the response of aquatic vegetation to hydrodynamic stress in lakes[J]. Acta Eco Sin, 2019, 39(2):454-459.DOI: 10.5846/stxb201801300245.

类别 class	敞水区 water area		浮水植被 floating plant		挺水植被 emergent plant		建筑 building		沉水植被 submerged plant		养殖场 farm		用户精度/% user accuracy
类别 class	OB	PB	OB	PB	OB	PB	OB	PB	OB	PB	OB	PB	OB	PB
敞水区water area	69 812	65	0	0	0	0	0	0	6 759	7	5 082	5	85.50	84.4
浮水植被floating plant	0	0	10 519	19	1 669	7	1 247	1	0	0	0	10	78.30	51.3
挺水植被emergent plant	0	0	420	6	14 810	101	0	0	1 207	1	1 127	15	84.32	82.1
建筑building	254	2	703	2	0	2	3 943	7	0	0	0	0	80.47	53.8
沉水植被submerged plant	6 516	7	0	0	0	4	0	2	114 273	87	4 370	30	91.30	66.9
养殖场farm	1 053	0	109	4	624	21	95	1	1 546	6	60 158	140	94.61	81.3
总计total	77 635	74	11 751	31	17 103	135	5 285	11	123 785	101	70 737	200
分类总精度/%total accuracy													89.00	75.90
Kappa系数Kappa coefficient													0.85	0.68

类别 class	荷叶N. nucifera
类别 class	OB	PB	OB	PB	OB	PB	OB	PB
荷叶N. nucifera	26 216	102	402	23	2 552	161	89.9	63.3
芦苇Ph. australis	1 339	11	43 396	81	1 247	16	94.3	75.0
菰Z. latifolia	1 686	4	682	10	9 397	97	79.8	87.4
总计total	29 241	117	44 480	114	13 166	149
分类总精度/% total accuracy							85.2	73.6
Kappa系数Kappa coefficient							0.76	0.61

基于Sentinel-1和Sentinel-2影像的洪泽湖国家湿地公园水生植被信息提取

Extraction of aquatic vegetation in Hongze Lake National Wetland Park based on Sentinel-1 and Sentinel-2 images

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 32

相关文章 9

编辑推荐

Metrics

本文评价

作者

读者

审稿

[1]	田春红, 李明阳, 李陶, 李登攀, 田雷. 基于Sentinel 1 & 2主被动遥感数据和冠层高度的森林净初级生产力估测[J]. 南京林业大学学报（自然科学版）, 2024, 48(4): 132-140.
[2]	王艳芳, 谭露, 郭红丽, 吴芳, 齐斐, 蒙雯婷, 徐雁南. 基于多源遥感数据的溧阳市林地植被覆盖度时空差异研究[J]. 南京林业大学学报（自然科学版）, 2023, 47(6): 183-191.
[3]	赵颖慧, 郭新龙, 甄贞. 基于光学-ALS变量组合和非参数模型的天然次生林地上生物量估算[J]. 南京林业大学学报（自然科学版）, 2021, 45(4): 49-57.
[4]	杨铭,王月婷,张晓丽. 基于双源遥感数据的杉木林分蓄积量估测模型研究[J]. 南京林业大学学报（自然科学版）, 2016, 40(05): 107-114.
[5]	柴颖,阮仁宗,傅巧妮. 高光谱数据湿地植被类型信息提取[J]. 南京林业大学学报（自然科学版）, 2015, 39(01): 181-184.
[6]	张慧春，郑加强，周宏平. 基于决策树技术的智能植保机械决策支持系统[J]. 南京林业大学学报（自然科学版）, 2011, 35(01): 95-98.
[7]	李明诗1，ChandraGiri2，朱智良3，吕恒4，潘洁1，温卫松5，徐达5，刘安兴5. 基于支持向量机的MERIS土地覆盖制图及其空间一致性分析[J]. 南京林业大学学报（自然科学版）, 2008, 32(06): 73-78.
[8]	王闻1,佘光辉2*. 决策树C4.5算法在森林资源二类调查中的应用[J]. 南京林业大学学报（自然科学版）, 2007, 31(03): 115-118.
[9]	熊文愈;薛建辉. 江苏省里下河滩地开发利用模式的综合评价[J]. 南京林业大学学报（自然科学版）, 1991, 15(03): 1-5.