浏览全部资源
扫码关注微信
纸质出版日期： 2023-06-07 ，
扫 描 看 全 文
张琍，罗文庭，张皓寰，殷秀琬，李斌.2023.时序Sentinel-1和Sentinel-2 数据支持下的鄱阳湖湿地草本植物群落制图分类.遥感学报，27（6）： 1362-1375
Zhang L，Luo W T，Zhang H H，Yin X W and Li B. 2023. Classification scheme for mapping wetland herbaceous plant communities using time series Sentinel-1 and Sentinel-2 data. National Remote Sensing Bulletin， 27（6）：1362-1375
植被是湿地的核心，易受人类活动和气候变化的影响，湿地植物群落分类与制图可以为湿地生态监测与评估提供科学数据支撑。本研究以鄱阳湖国家级湿地自然保护区为研究区，基于2019年月度Sentinel-1和Sentinel-2时序数据，通过提取影像的水体指数和植被指数、红边指数、纹理特征、光谱特征、雷达极化数据5类，共计240个特征指标，使用随机森林、支持向量机和深度神经网络算法进行分类，探寻一套湿地植被分类最优的特征组合和分类方案。（1）光学数据在湿地分类与制图提取中明显优于雷达数据，雷达数据可以在光学数据不足时，作为光学数据的补充。（2）对时序Sentinel-2的各特征变量进行重要性筛选，有助于提高分类精度，优选时间段主要分布在1月、5月、8月、9月、10月和12月份；（2）当对5组特征变量单独分类时，分类精度排序为红边指数组>水体—植被指数组>光谱特征组>雷达极化数据组>纹理特征组；（3）对比组合变量和单独特征变量，组合变量不一定有助于提高分类效果，分类精度排序为：红边指数分类组>水体—植被指数分类组>组合分类组，其中，红边指数组随机森林分类总体精度达0.81，Kappa系数为0.76；（4）对比3种分类方法，分类精度排序为：深度神经网络>随机森林>支持向量机，其中，深度学习方法并没有太大幅度的提高分类精度，相对随机森林算法仅仅提高了2%。故深度神经网络和随机森林算法都可以作为优选算法。本研究给出的分类方案是，使用Sentinel-2和Sentinel-1多时序数据对湿地植被进行精细化分类，时段选择建议1月、5月、8月、9月、10月和12月份的卫星数据更优，特征变量可选红边指数组或者水体—植被指数组产品，分类方法可根据需求选择深度神经网络或随机森林对湿地植物群落进行分类，可得出较优的分类结果。这个分类方案可以有效的提升鄱阳湖湿地植被制图精度，并为决策部门提供科学的技术方案。
Plant communities play an important role in wetland elements and are vulnerable to human activities and climate change. Wetland plant community classification and mapping provide scientific important data support for wetland ecological monitoring and evaluation. This study aims to develop a classification scheme suitable for the wetland plant communities in the Poyang Lake wetland.
Taking Poyang Lake National Nature Reserve as the research area and on the basis of the monthly Sentinel-1 and Sentinel-2 time-series data in 2019
this study extracts five types of image feature parameters
including water and vegetation index group
red edge index group
texture feature group
spectral feature group
and polarization radar backscatter group
with a total of 240 feature indexes
and uses Random Forest (RF)
Support Vector Machine (SVM)
and Deep Neural Network (DNN) algorithms for classification to explore a set of optimal feature combinations and a suitable classification scheme for wetland vegetation mapping in Poyang Lake.
In conclusion
A classification scheme for wetland plant communities in the Poyang Lake wetland was proposed in this study using multi time-series Sentinel-2 and Sentinel-1 data. The optimal acquisition time periods of satellite data are in January
April
August
September
October
and December. The optimal image feature group can be red edge index group or water and vegetation index group for feature selection. The classification algorithm can select deep learning or RF algorithm to classify wetland plant communities according to the requirements. This classification scheme can effectively improve the accuracy of wetland vegetation mapping in the Poyang Lake and provide scientific and technical solutions for decision-making departments.
Results show the following
2
(1) Compared with radar data
the extraction accuracy of optical data is remarkably better than that of radar data in wetland plant community classification and mapping. Radar data can be used as a supplement to optical data when optical data are insufficient. (2) Screening the importance of each image feature of Sentinel-2 helps improve the classification accuracy. The preferred time periods are mainly distributed in January
May
August
September
October
and December. (3) Five groups of unitary image features are selected to classify separately
and the classification accuracy is as follows: red edge index group > water and vegetation index group > spectral feature group > radar polarization data group > texture feature group. (4) Comparing the combined image feature groups with the unitary image feature groups reveals that the combined image feature group is not necessarily helpful to improve the classification accuracy. The classification accuracy is as follows: red edge index group > water vegetation index group > combined image feature group. Among them
the overall accuracy of the classification scheme using the red edge index group and random forest method is 0.81
and the Kappa coefficient is 0.76. (4) By comparing the three classification algorithms
the classification accuracy is ranked as follows: DNN > RF > SVM. The overall accuracy of the deep learning method does not greatly improve
that is
only 2% higher than the RF algorithm. Thus
the DNN and machine learning method (RF) can be used as optimization algorithms.
遥感鄱阳湖湿地植被制图特征变量随机森林深度神经网络多时相光学与雷达数据
remote sensingPoyang Lakewetland vegetation mappingimage features selectionrandom forest algorithmDeep Neural Networks (DNN)multi-temporal optical and SAR data
Adam E, Mutanga O and Rugege D. 2010. Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review. Wetlands Ecology and Management, 18(3): 281-296 [DOI: 10.1007/s11273-009-9169-zhttp://dx.doi.org/10.1007/s11273-009-9169-z]
Dahl T E. 2000. Status and Trends of Wetlands in the Conterminous United States 1986 to 1997. U.S. Department of the Interior, Fish and Wildlife Service
Davranche A, Lefebvre G and Poulin B. 2010. Wetland monitoring using classification trees and SPOT-5 seasonal time series. Remote Sensing of Environment, 114(3): 552-562 [DOI: 10.1016/j.rse.2009.10.009http://dx.doi.org/10.1016/j.rse.2009.10.009]
DeLancey E R, Simms J F, Mahdianpari M, Brisco B, Mahoney C and Kariyeva J. 2020. Comparing deep learning and shallow learning for large-scale wetland classification in Alberta, Canada. Remote Sensing, 12(1): 2 [DOI: 10.3390/rs12010002http://dx.doi.org/10.3390/rs12010002]
Dronova I, Gong P and Wang L. 2011. Object-based analysis and change detection of major wetland cover types and their classification uncertainty during the low water period at Poyang Lake, China. Remote Sensing of Environment, 115(12): 3220-3236 [DOI: 10.1016/j.rse.2011.07.006http://dx.doi.org/10.1016/j.rse.2011.07.006]
Du L, McCarty G W, Zhang X, Lang M W, Vanderhoof M K, Li X, Huang C Q, Lee S and Zou Z H. 2020. Mapping forested wetland inundation in the Delmarva Peninsula, USA using deep convolutional neural networks. Remote Sensing, 12(4): 644 [DOI: 10.3390/rs12040644http://dx.doi.org/10.3390/rs12040644]
Frampton W J, Dash J, Watmough G and Milton E J. 2013. Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation. ISPRS Journal of Photogrammetry and Remote Sensing, 82: 83-92 [DOI: 10.1016/j.isprsjprs.2013.04.007http://dx.doi.org/10.1016/j.isprsjprs.2013.04.007]
Gitelson A A, Gritz Y and Merzlyak M N. 2003. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves. Journal of Plant Physiology, 160(3): 271-282 [DOI: 10.1078/0176-1617-00887http://dx.doi.org/10.1078/0176-1617-00887]
Gitelson A A, Keydan G P and Merzlyak M N. 2006. Three-band model for noninvasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves. Geophysical Research Letters, 33(11): L11402 [DOI: 10.1029/2006GL026457http://dx.doi.org/10.1029/2006GL026457]
Gitelson A A and Merzlyak M N. 1994. Spectral reflectance changes associated with autumn senescence of Aesculus hippocastanum L. and Acer platanoides L. Leaves. Spectral features and relation to chlorophyll estimation. Journal of Plant Physiology, 143(3): 286-292 [DOI: 10.1016/S0176-1617(11)81633-0http://dx.doi.org/10.1016/S0176-1617(11)81633-0]
Han X X, Chen X L and Feng L. 2015. Four decades of winter wetland changes in Poyang Lake based on Landsat observations between 1973 and 2013. Remote Sensing of Environment, 156: 426-437 [DOI: 10.1016/j.rse.2014.10.003http://dx.doi.org/10.1016/j.rse.2014.10.003]
Han X X, Feng L, Hu C M and Chen X L. 2018. Wetland changes of China's largest freshwater lake and their linkage with the Three Gorges Dam. Remote Sensing of Environment, 204: 799-811 [DOI: 10.1016/j.rse.2017.09.023http://dx.doi.org/10.1016/j.rse.2017.09.023]
Hird J, DeLancey E, McDermid G and Kariyeva J. 2017. Google Earth Engine, open-access satellite data, and machine learning in support of large-area probabilistic wetland mapping. Remote Sensing, 9(12): 1315 [DOI: 10.3390/rs9121315http://dx.doi.org/10.3390/rs9121315]
Hu Z P, Ge G and Liu C L. 2015. Cause analysis and early warning for wetland vegetation degradation in Poyang Lake. Resources and Environment in the Yangtze Basin, 24(3): 381-386
胡振鹏, 葛刚, 刘成林. 2015. 鄱阳湖湿地植被退化原因分析及其预警. 长江流域资源与环境, 24(3): 381-386[DOI: 10.11870/cjlyzyyhj201503005http://dx.doi.org/10.11870/cjlyzyyhj201503005]
Hu Z P, Ge G, Liu C L, Chen F S and Li S. 2010. Structure of Poyang Lake wetland plants ecosystem and influence of lake water level for the structure. Resources and Environment in the Yangtze Basin, 19(6): 597-605
胡振鹏, 葛刚, 刘成林, 陈伏生, 李述. 2010. 鄱阳湖湿地植物生态系统结构及湖水位对其影响研究. 长江流域资源与环境, 19(6): 597-605
Hu Z P and Lin Y R. 2019. Analysis of evolution process and driving factors for aquatic vegetations of Poyang Lake in 30 years. Resources and Environment in the Yangtze Basin, 28(8): 1947-1955
胡振鹏, 林玉茹. 2019. 鄱阳湖水生植被30年演变及其驱动因素分析. 长江流域资源与环境, 28(8): 1947-1955[DOI: 10.11870/cjlyzyyhj201908018http://dx.doi.org/10.11870/cjlyzyyhj201908018]
Kanai Y, Ueta M, Germogenov N, Nagendran M, Mita N and Higuchi H. 2002. Migration routes and important resting areas of Siberian cranes (Grus leucogeranus) between northeastern Siberia and China as revealed by satellite tracking. Biological Conservation, 106(3): 339-346 [DOI: 10.1016/S0006-3207(01)00259-2http://dx.doi.org/10.1016/S0006-3207(01)00259-2]
Kayastha N, Thomas V, Galbraith J and Banskota A. 2012. Monitoring wetland change using inter-annual Landsat time-series data. Wetlands, 32(6): 1149-1162 [DOI: 10.1007/s13157-012-0345-1http://dx.doi.org/10.1007/s13157-012-0345-1]
Landmann T, Schramm M, Colditz R R, Dietz A and Dech S. 2010. Wide area wetland mapping in semi-arid Africa using 250-meter MODIS metrics and topographic variables. Remote Sensing, 2(7): 1751-1766 [DOI: 10.3390/rs2071751http://dx.doi.org/10.3390/rs2071751]
Li D C, Xu P P, Niu Z G and Zhang H Y. 2018. Automatic updating method for large-scale wetland mapping based on existing thematic map. Journal of Remote Sensing, 22(6): 1060-1075
李大冲, 许盼盼, 牛振国, 张海英. 2018. 历史专题图的大空间范围湿地专题图自动更新. 遥感学报, 22(6): 1060-1075 [DOI: 10.11834/jrs.20187458http://dx.doi.org/10.11834/jrs.20187458]
Li L Y, Chen Y, Xu T B, Liu R, Shi K F and Huang C. 2015. Super-resolution mapping of wetland inundation from remote sensing imagery based on integration of back-propagation neural network and genetic algorithm. Remote Sensing of Environment, 164: 142-154 [DOI: 10.1016/j.rse.2015.04.009http://dx.doi.org/10.1016/j.rse.2015.04.009]
Lu S L, Wu B F and Li F P. 2011. Wetland pattern change in Hai Basin. Journal of Remote Sensing, 15(2): 349-371
卢善龙, 吴炳方, 李发鹏. 2011. 海河流域湿地格局变化分析. 遥感学报, 15(2): 349-371 [DOI: 10.11834/jrs.20110292http://dx.doi.org/10.11834/jrs.20110292]
MacAlister C and Mahaxay M. 2009. Mapping wetlands in the Lower Mekong Basin for wetland resource and conservation management using Landsat ETM images and field survey data. Journal of Environmental Management, 90(7): 2130-2137 [DOI: 10.1016/j.jenvman.2007.06.031http://dx.doi.org/10.1016/j.jenvman.2007.06.031]
MacKay H, Finlayson C M, Fernández-Prieto D, Davidson N, Pritchard D and Rebelo L M. 2009. The role of Earth Observation (EO) technologies in supporting implementation of the Ramsar Convention on Wetlands. Journal of Environmental Management, 90(7): 2234-2242 [DOI: 10.1016/j.jenvman.2008.01.019http://dx.doi.org/10.1016/j.jenvman.2008.01.019]
Maltby E and Acreman M C. 2011. Ecosystem services of wetlands: pathfinder for a new paradigm. Hydrological Sciences Journal, 56(8): 1341-1359 [DOI: 10.1080/02626667.2011.631014http://dx.doi.org/10.1080/02626667.2011.631014]
Martins V S, Kaleita A L, Gelder B K, Nagel G W and Maciel D A. 2020. Deep neural network for complex open-water wetland mapping using high-resolution WorldView-3 and airborne LiDAR data. International Journal of Applied Earth Observation and Geoinformation, 93: 102215 [DOI: 10.1016/j.jag.2020.102215http://dx.doi.org/10.1016/j.jag.2020.102215]
Mitsch W J, Bernal B, Nahlik A M, Mander Ü, Zhang L, Anderson C J, Jørgensen S E and Brix H. 2013. Wetlands, carbon, and climate change. Landscape Ecology, 28(4): 583-597 [DOI: 10.1007/s10980-012-9758-8http://dx.doi.org/10.1007/s10980-012-9758-8]
Nielsen E M, Prince S D and Koeln G T. 2008. Wetland change mapping for the U.S. mid-Atlantic region using an outlier detection technique. Remote Sensing of Environment, 112(11): 4061-4074 [DOI: 10.1016/j.rse.2008.04.017http://dx.doi.org/10.1016/j.rse.2008.04.017]
Rezaee M, Mahdianpari M, Zhang Y and Salehi B. 2018. Deep convolutional neural network for complex wetland classification using optical remote sensing imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(9): 3030-3039 [DOI: 10.1109/JSTARS.2018.2846178http://dx.doi.org/10.1109/JSTARS.2018.2846178]
Shi S X, Chang Y, Li Y H, Hu Y M, Liu M, Ma J, Xiong Z P, Wen D, Li B L and Zhang T S. 2021. Using time series optical and SAR data to assess the impact of historical wetland change on current wetland in Zhenlai County, Jilin Province, China. Remote Sensing, 13(22): 4514 [DOI: 10.3390/rs13224514http://dx.doi.org/10.3390/rs13224514]
Slagter B, Tsendbazar N E, Vollrath A and Reiche J. 2020. Mapping wetland characteristics using temporally dense Sentinel-1 and Sentinel-2 data: a case study in the St. Lucia wetlands, South Africa. International Journal of Applied Earth Observation and Geoinformation, 86: 102009 [DOI: 10.1016/j.jag.2019.102009http://dx.doi.org/10.1016/j.jag.2019.102009]
Tana G, Letu H, Cheng Z K and Tateishi R. 2013. Wetlands mapping in North America by decision rule classification using MODIS and ancillary data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(6): 2391-2401 [DOI: 10.1109/JSTARS.2013.2249499http://dx.doi.org/10.1109/JSTARS.2013.2249499]
Tu C R, Li P, Li Z H, Wang H J, Yin S W, Li D H, Zhu Q T, Chang M X, Liu J and Wang G Y. 2021. Synergetic classification of coastal wetlands over the Yellow River delta with GF-3 full-polarization SAR and Zhuhai-1 OHS hyperspectral remote sensing. Remote Sensing, 13(21): 4444 [DOI: 10.3390/rs13214444http://dx.doi.org/10.3390/rs13214444]
Wang Y Q and Yésou H. 2018. Remote sensing of floodpath lakes and wetlands: a challenging frontier in the monitoring of changing environments. Remote Sensing, 10(12): 1955 [DOI: 10.3390/rs10121955http://dx.doi.org/10.3390/rs10121955]
Whyte A, Ferentinos K P and Petropoulos G P. 2018. A new synergistic approach for monitoring wetlands using Sentinels -1 and 2 data with object-based machine learning algorithms. Environmental Modelling and Software, 104: 40-54 [DOI: 10.1016/j.envsoft.2018.01.023http://dx.doi.org/10.1016/j.envsoft.2018.01.023]
Zhang L, Gong Z N, Wang Q W, Jin D D and Wang X. 2019. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images. Journal of Remote Sensing, 23(2): 313-326
张磊, 宫兆宁, 王启为, 金点点, 汪星. 2019. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取. 遥感学报, 23(2): 313-326 [DOI: 10.11834/jrs.20198083http://dx.doi.org/10.11834/jrs.20198083]
Zhang M, Zeng Y N and Zhu Y S. 2017. Wetland mapping of Donting Lake Basin based on time-series MODIS data and object-oriented method. Journal of Remote Sensing, 21(3): 479-492
张猛, 曾永年, 朱永森. 2017. 面向对象方法的时间序列MODIS数据湿地信息提取——以洞庭湖流域为例. 遥感学报, 21(3): 479-492[DOI: 10.11834/jrs.20176129http://dx.doi.org/10.11834/jrs.20176129]
Zhu J F, Zhou Y, Wang S X, Wang L T, Liu W L, Li H T and Mei J J. 2019. Analysis of changes of Baiyangdian wetland from 1975 to 2018 based on remote sensing. Journal of Remote Sensing, 23(5): 971-986
朱金峰, 周艺, 王世新, 王丽涛, 刘文亮, 李海涛, 梅军军. 2019. 1975年—2018年白洋淀湿地变化分析. 遥感学报, 23(5): 971-986 [DOI: 10.11834/jrs.20198379http://dx.doi.org/10.11834/jrs.20198379]
Zoffoli M L, Kandus P, Madanes N and Calvo D H. 2008. Seasonal and interannual analysis of wetlands in South America using NOAA-AVHRR NDVI time series: the case of the Parana Delta region. Landscape Ecology, 23(7): 833-848 [DOI: 10.1007/s10980-008-9240-9http://dx.doi.org/10.1007/s10980-008-9240-9]
相关作者
相关机构
京公网安备11010802024621