多源多特征集成的南美洲典型地区湿地制图
Wetlands mapping in typical regions of South America with multi-source and multi-feature integration
- 2023年27卷第6期 页码：1300-1319
纸质出版日期： 2023-06-07
DOI： 10.11834/jrs.20232265
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
南美洲湿地面积广且类型多样，但湿地制图相关研究匮乏，通过遥感手段可为南美洲全域湿地制图提供科学技术支撑。本研究依托GEE（Google Earth Engine）平台面向南美洲湿地提出一种多源多特征集成的湿地制图方法。研究选取南美洲典型湿地地区为研究区，首先利用已有土地覆盖数据集提出一种有效的湿地样本采集流程以保证样本质量，其次结合哨兵1号、哨兵2号和SRTM数据构建多源特征集合，并基于随机森林的递归特征消除算法（RF_RFE）进行特征优选，构建不同特征组合方案对比多源特征对湿地分类结果的影响，最后采用随机森林算法对研究区湿地进行分类提取。研究结果表明，设计样本采集方案可有效提高样本质量，多源特征集合能够提升湿地分类精度，特征优选能够减少特征冗余并提升分类精度。研究区分类总体精度为85.62%，Kappa系数为0.8333，其中湿地类别的精度最低为69.85%，最高为95.18%。
Abstract
Wetlands play an important role in maintaining ecological balance
conserving water resources
recharging groundwater
and controlling soil erosion. They are often called the “kidneys of the earth” because they help purify water by filtering out pollutants and sediments. South America has a vast area of wetlands
as well as a variety of wetlands types. While most of these wetlands were conserved in a relatively good condition until a few decades ago
pressures brought about by land use and climate change have threatened their integrity in recent years. However
no complete and uniform wetland map has provided adequate information on the location
distribution
size
and changing status of wetlands in South America. Remote sensing has been an effective tool for characterizing
mapping
and monitoring the complexity and dynamics of large areas of wetlands. Although fine wetland mapping may be done by combining data from many sources
the following two issues persist. On the one hand
given the complicated temporal dynamics and spectral heterogeneity of wetlands
large-scale wetland mapping remains a challenging task. On the other hand
supervised classification is a widely used technique for multi-category wetland mapping. However
selecting training samples is time consuming and labor intensive. Moreover
finer and more precise wetland information is currently unavailable for reference. In the study
we selected four study areas of typical wetlands in South America. First
an effective wetland sample collection process was proposed by using the existing land cover dataset to ensure the sample quality. Second
a multi-source feature set was constructed by combining Sentinel-1
Sentinel-2
and SRTM data. Then
feature selection is carried out on the basis of the random forest recursive feature elimination method (RF_RFE). We constructed a multi-feature combination scheme to compare the influence of multi-source features on wetlands classification. Finally
the random forest algorithm is used to classify wetlands in the study area. The research results show that the process facilitates the sample collection and improves the sample quality. The combination of Sentinel-1 and Sentinel-2 data can improve the accuracy of land cover mapping
and terrain features help greatly improve the overall classification accuracy and the accuracy of various types of objects. For wetland categories
the addition of multi-source data features can improve the separability of wetland categories. The feature selection based on RF_RFE can reduce the feature redundancy and improve the classification accuracy. The feature optimization results show that SAR polarization features and derived texture features can be used as an effective supplement to optical features. However
the dominant features account for less. The overall classification accuracy of the study area was 85.62%
and the Kappa coefficient was 0.8333. The study proposed an effective classification process and sample collection scheme to large-scale wetlands in South America. This study integrated Sentinel-1 synthetic aperture radar data
Sentinel-2 optical data
and terrain data to explore their importance to the extraction of different wetlands at a large scale. This work also verified the feasibility of feature selection based on random forest recursive feature elimination method. The research results reveal that the sample collection process facilitates sample collection and improves sample quality. The combination of Sentinel-1 and Sentinel-2 data can improve the accuracy of land cover mapping
and terrain features help greatly improve the overall classification accuracy and the accuracy of various types of objects. For wetland categories
the addition of multi-source data features can improve the separability of wetland categories. The feature selection based on RF_RFE can reduce the feature redundancy and improve the classification accuracy.
关键词
遥感哨兵1号（Sentinel-1）哨兵2号（Sentinel-2）Google Earth Engine湿地分类特征选择南美洲
Keywords
remote sensingSentinel-1Sentinel-2Google Earth Enginewetlands classificationfeature selectionSouth America
references
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]
Amani M, Brisco B, Afshar M, Mirmazloumi S M, Mahdavi S, Mirzadeh S M J, Huang W M and Granger J. 2019a. A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing. Big Earth Data, 3(4): 378-394 [DOI: 10.1080/20964471.2019.1690404http://dx.doi.org/10.1080/20964471.2019.1690404]
Amani M, Brisco B, Mahdavi S, Ghorbanian A, Moghimi A, DeLancey E R, Merchant M, Jahncke R, Fedorchuk L, Mui A, Fisette T, Kakooei M, Ahmadi S A, Leblon B and Larocque A. 2021. Evaluation of the landsat-based Canadian wetland inventory map using multiple sources: challenges of large-scale wetland classification using remote sensing. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 32-52 [DOI: 10.1109/jstars.2020.3036802http://dx.doi.org/10.1109/jstars.2020.3036802]
Amani M, Mahdavi S, Afshar M, Brisco B, Huang W M, Mirzadeh S M J, White L, Banks S, Montgomery J and Hopkinson C. 2019b. Canadian wetland inventory using google earth engine: the first map and preliminary results. Remote Sensing, 11(7): 842 [DOI: 10.3390/rs11070842http://dx.doi.org/10.3390/rs11070842]
Amani M, Salehi B, Mahdavi S, Granger J and Brisco B. 2017. Wetland classification in Newfoundland and Labrador using multi-source SAR and optical data integration. GIScience and Remote Sensing, 54(6): 779-796 [DOI: 10.1080/15481603.2017.1331510http://dx.doi.org/10.1080/15481603.2017.1331510]
Borges J, Higginbottom T P, Symeonakis E and Jones M. 2020. Sentinel-1 and Sentinel-2 Data for savannah land cover mapping: optimising the combination of sensors and seasons. Remote Sensing, 12(23): 3862 [DOI: 10.3390/rs12233862http://dx.doi.org/10.3390/rs12233862]
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32 [DOI: 10.1023/A:1010933404324http://dx.doi.org/10.1023/A:1010933404324]
Bunting P, Rosenqvist A, Lucas R M, Rebelo L M, Hilarides L, Thomas N, Hardy A, Itoh T, Shimada M and Finlayson C M. 2018. The global mangrove watch—a new 2010 global baseline of mangrove extent. Remote Sensing, 10(10): 1669 [DOI: 10.3390/rs10101669http://dx.doi.org/10.3390/rs10101669]
Cai Y T, Li X Y, Zhang M and Lin H. 2020. Mapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data. International Journal of Applied Earth Observation and Geoinformation, 92: 102164 [DOI: 10.1016/j.jag.2020.102164http://dx.doi.org/10.1016/j.jag.2020.102164]
Chang W T, Wang H, Ning X G and Zhang H C. 2020. Extraction of Zhalong wetlands information based on images of sentinel-2 red edge bands and Sentinel-1 radar bands. Wetland Science, 18(1): 10-19
常文涛, 王浩, 宁晓刚, 张翰超. 2020. 融合Sentinel-2红边波段和Sentinel-1雷达波段影像的扎龙湿地信息提取. 湿地科学, 18(1): 10-19 [DOI: 10.13248/j.cnki.wetlandsci.2020.01.002http://dx.doi.org/10.13248/j.cnki.wetlandsci.2020.01.002]
Chen J and Chen J. 2018. GlobeLand30: operational global land cover mapping and big-data analysis. Science China Earth Sciences, 61(10): 1533-1534 [DOI: 10.1007/s11430-018-9255-3http://dx.doi.org/10.1007/s11430-018-9255-3]
Deering D W. 1978. Rangeland Reflectance Characteristics Measured by Aircraft and Spacecraft Sensors. College Station, TX: Texas A and M University
Demarchi L, Kania A, Ciężkowski W, Piórkowski H, Oświecimska-Piasko Z and Chormański J. 2020. Recursive feature elimination and random forest classification of natura 2000 grasslands in Lowland River Valleys of Poland based on airborne hyperspectral and LiDAR data fusion. Remote Sensing, 12(11): 1842 [DOI: 10.3390/rs12111842http://dx.doi.org/10.3390/rs12111842]
Dong T F, Liu J G, Shang J L, Qian B D, Ma B L, Kovacs J M, Walters D, Jiao X F, Geng X Y and Shi Y C. 2019. Assessment of red-edge vegetation indices for crop leaf area index estimation. Remote Sensing of Environment, 222: 133-143 [DOI: 10.1016/j.rse.2018.12.032http://dx.doi.org/10.1016/j.rse.2018.12.032]
Fernández-Manso A, Fernández-Manso O and Quintano C. 2016. SENTINEL-2A red-edge spectral indices suitability for discriminating burn severity. International Journal of Applied Earth Observation and Geoinformation, 50: 170-175 [DOI: 10.1016/j.jag.2016.03.005http://dx.doi.org/10.1016/j.jag.2016.03.005]
Haralick R M, Shanmugam K and Dinstein I. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6): 610-621 [DOI: 10.1109/TSMC.1973.4309314http://dx.doi.org/10.1109/TSMC.1973.4309314]
Hu S J, Niu Z G, Chen Y F, Li L F and Zhang H Y. 2017. Global wetlands: potential distribution, wetland loss, and status. Science of the Total Environment, 586: 319-327 [DOI: 10.1016/j.scitotenv.2017.02.001http://dx.doi.org/10.1016/j.scitotenv.2017.02.001]
Junk W J. 1993. Wetlands of tropical South America//Whigham D F, Dykyjová D and Hejný S, eds. Wetlands of the World: Inventory, Ecology and Management Volume I. Dordrecht: Springer: 679-739 [DOI: 10.1007/978-94-015-8212-4_14http://dx.doi.org/10.1007/978-94-015-8212-4_14]
Junk W J, An S Q, Finlayson C M, Gopal B, Květ J, Mitchell S A, Mitsch W J and Robarts R D. 2013. Current state of knowledge regarding the world’s wetlands and their future under global climate change: a synthesis. Aquatic Sciences, 75(1): 151-167 [DOI: 10.1007/s00027-012-0278-zhttp://dx.doi.org/10.1007/s00027-012-0278-z]
Junk W J, Piedade M T F, Lourival R, Wittmann F, Kandus P, Lacerda L D, Bozelli R L, Esteves F A, Nunes Da cunha C, Maltchik L, Schöngart J, Schaeffer-Novelli Y and Agostinho A A. 2014. Brazilian wetlands: their definition, delineation, and classification for research, sustainable management, and protection. Aquatic Conservation: Marine and Freshwater Ecosystems, 24(1): 5-22 [DOI: 10.1002/aqc.2386http://dx.doi.org/10.1002/aqc.2386]
Kandus P, Minotti P G, Morandeira N S, Grimson R, Trilla G G, González E B, San Martín L and Gayol M P. 2018. Remote sensing of wetlands in South America: status and challenges. International Journal of Remote Sensing, 39(4): 993-1016 [DOI: 10.1080/01431161.2017.1395971http://dx.doi.org/10.1080/01431161.2017.1395971]
Lehner B and Döll P. 2004. Development and validation of a global database of lakes, reservoirs and wetlands. Journal of Hydrology, 296(1/4): 1-22 [DOI: 10.1016/j.jhydrol.2004.03.028http://dx.doi.org/10.1016/j.jhydrol.2004.03.028]
Li J H and Chen W J. 2005. A rule-based method for mapping Canada’s wetlands using optical, radar and DEM data. International Journal of Remote Sensing, 26(22): 5051-5069 [DOI: 10.1080/01431160500166516http://dx.doi.org/10.1080/01431160500166516]
Mahdavi S, Salehi B, Granger J, Amani M, Brisco B and Huang W M. 2018. Remote sensing for wetland classification: a comprehensive review. GIScience and Remote Sensing, 55(5): 623-658 [DOI: 10.1080/15481603.2017.1419602http://dx.doi.org/10.1080/15481603.2017.1419602]
Mahdianpari M, Brisco B, Granger J, Mohammadimanesh F, Salehi B, Homayouni S and Bourgeau-Chavez L. 2021. The third generation of pan-canadian wetland map at 10 m resolution using multisource earth observation data on cloud computing platform. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 8789-8803 [DOI: 10.1109/jstars.2021.3105645http://dx.doi.org/10.1109/jstars.2021.3105645]
Mao D H, Wang Z M, Du B J, Li L, Tian Y L, Jia M M, Zeng Y, Song K S, Jiang M and Wang Y Q. 2020. National wetland mapping in China: a new product resulting from object-based and hierarchical classification of Landsat 8 OLI images. ISPRS Journal of Photogrammetry and Remote Sensing, 164: 11-25 [DOI: 10.1016/j.isprsjprs.2020.03.020http://dx.doi.org/10.1016/j.isprsjprs.2020.03.020]
McFeeters S K. 1996. The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7): 1425-1432 [DOI: 10.1080/01431169608948714http://dx.doi.org/10.1080/01431169608948714]
Murray N J, Phinn S R, DeWitt M, Ferrari R, Johnston R, Lyons M B, Clinton N, Thau D and Fuller R A. 2019. The global distribution and trajectory of tidal flats. Nature, 565(7738): 222-225 [DOI: 10.1038/s41586-018-0805-8http://dx.doi.org/10.1038/s41586-018-0805-8]
Nembrini S, König I R and Wright M N. 2018. The revival of the Gini importance?. Bioinformatics, 34(21): 3711-3718 [DOI: 10.1093/bioinformatics/bty373http://dx.doi.org/10.1093/bioinformatics/bty373]
Rapinel S, Betbeder J, Denize J, Fabre E, Pottier É and Hubert-Moy L. 2020. SAR analysis of wetland ecosystems: effects of band frequency, polarization mode and acquisition dates. ISPRS Journal of Photogrammetry and Remote Sensing, 170: 103-113 [DOI: 10.1016/j.isprsjprs.2020.10.007http://dx.doi.org/10.1016/j.isprsjprs.2020.10.007]
Ruiz L F C, Guasselli L A, Simioni J P D, Belloli T F and Fernandes P C B. 2021. Object-based classification of vegetation species in a subtropical wetland using Sentinel-1 and Sentinel-2A images. Science of Remote Sensing, 3: 100017 [DOI: 10.1016/j.srs.2021.100017http://dx.doi.org/10.1016/j.srs.2021.100017]
Saah D, Johnson G, Ashmall B, Tondapu G, Tenneson K, Patterson M, Poortinga A, Markert K, Quyen N H, San Aung K, Schlichting L, Matin M, Uddin K, Aryal R R, Dilger J, Lee Ellenburg W, Flores-Anderson A I, Wiell D, Lindquist E, Goldstein J, Clinton N and Chishtie F. 2019. Collect Earth: an online tool for systematic reference data collection in land cover and use applications. Environmental Modelling and Software, 118: 166-171 [DOI: 10.1016/j.envsoft.2019.05.004http://dx.doi.org/10.1016/j.envsoft.2019.05.004]
Schratz P, Muenchow J, Iturritxa E, Cortés J, Bischl B and Brenning A. 2021. Monitoring forest health using hyperspectral imagery: does feature selection improve the performance of machine-learning techniques?. Remote Sensing, 13(23): 4832 [DOI: 10.3390/rs13234832http://dx.doi.org/10.3390/rs13234832]
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]
Tamiminia H, Salehi B, Mahdianpari M, Quackenbush L, Adeli S and Brisco B. 2020. Google Earth Engine for geo-big data applications: a meta-analysis and systematic review. ISPRS Journal of Photogrammetry and Remote Sensing, 164: 152-170 [DOI: 10.1016/j.isprsjprs.2020.04.001http://dx.doi.org/10.1016/j.isprsjprs.2020.04.001]
Wang J, Shang J, Brisco B and Brown R J. 1998. Evaluation of multidate ERS-1 and multispectral landsat imagery for wetland detection in Southern Ontario. Canadian Journal of Remote Sensing, 24(1): 60-68 [DOI: 10.1080/07038992.1998.10874692http://dx.doi.org/10.1080/07038992.1998.10874692]
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]
Wu N, Shi R H, Zhuo W, Zhang C, Zhou B C, Xia Z L, Tao Z, Gao W and Tian B. 2021. A classification of tidal flat wetland vegetation combining phenological features with Google earth engine. Remote Sensing, 13(3): 443 [DOI: 10.3390/rs13030443http://dx.doi.org/10.3390/rs13030443]
Xia Y, Li E H, Wang X L, Zhang Y Y, Yang J and Zhou R. 2021. Application of random forest algorithm based on feature optimization in wetland information extraction: a case study of Honghu Wetland Nature Reserve in Hubei Province. Journal of Central China Normal University (Natural Sciences), 55(4): 639-648, 660
夏盈, 厉恩华, 王学雷, 张莹莹, 杨娇, 周瑞. 2021. 基于特征优选的随机森林算法在湿地信息提取中的应用——以湖北洪湖湿地自然保护区为例. 华中师范大学学报(自然科学版), 55(4): 639-648, 660 [DOI: 10.19603/j.cnki.1000-1190.2021.04.019http://dx.doi.org/10.19603/j.cnki.1000-1190.2021.04.019]
Xu H Q. 2005. A study on information extraction of water body with the Modified Normalized Difference Water Index (MNDWI). Journal of Remote Sensing, 9(5): 589-595
徐涵秋. 2005. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究. 遥感学报, 9(5): 589-595 [DOI: 10.11834/jrs.20050586http://dx.doi.org/10.11834/jrs.20050586]
Yan X and Niu Z G. 2021. Reliability evaluation and migration of wetland samples. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 8089-8099 [DOI: 10.1109/jstars.2021.3102866http://dx.doi.org/10.1109/jstars.2021.3102866]
Yang J W, Zhang J S, Zhu X F and Yuan Z M Q. 2015. Random forest applied for dimension reduction and classification in hyperspectral data. Journal of Beijing Normal University (Natural Science), 51(S1): 82-88
杨珺雯, 张锦水, 朱秀芳, 谢登峰, 袁周米琪. 2015. 随机森林在高光谱遥感数据中降维与分类的应用. 北京师范大学学报(自然科学版), 51(S1): 82-88 [DOI: 10.16360/j.cnki.jbnuns.2015.s1.013http://dx.doi.org/10.16360/j.cnki.jbnuns.2015.s1.013]
Zha Y, Ni S X and Yang S. 2003. An effective approach to automatically extract urban land-use from TM imagery. Journal of Remote Sensing, 7(1): 37-40
查勇, 倪绍祥, 杨山. 2003. 一种利用TM图像自动提取城镇用地信息的有效方法. 遥感学报, 7(1): 37-40 [DOI: 10.11834/jrs.20030107http://dx.doi.org/10.11834/jrs.20030107]
Zhang H Y, Niu Z G, Xu P P, Chen Y F, Hu S J and Gong N. 2017. The boundaries and remote sensing classification datasets on large wetlands of international importance in 2001 and 2013. Journal of Global Change Data and Discovery, 1(2): 230-238
张海英, 牛振国, 许盼盼, 陈燕芬, 胡胜杰, 宫宁. 2017. 大型国际重要湿地边界及遥感分类数据集(2001、2013). 全球变化数据学报, 1(2): 230-238 [DOI: 10.3974/geodp.2017.02.15http://dx.doi.org/10.3974/geodp.2017.02.15]
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]
Zheng L L, Xu J Y and Wang X L. 2019. Application of random forests algorithm in researches on wetlands. Wetland Science, 17(1): 16-24
郑利林, 徐金英, 王晓龙. 2019. 随机森林算法在湿地研究中的应用. 湿地科学, 17(1): 16-24 [DOI: 10.13248/j.cnki.wetlandsci.2019.01.003http://dx.doi.org/10.13248/j.cnki.wetlandsci.2019.01.003]
Zhou X C, Zheng L and Huang H Y. 2021. Classification of forest stand based on multi-feature optimization of UAV visible light remote sensing. Scientia Silvae Sinicae, 57(6): 24-36
周小成, 郑磊, 黄洪宇. 2021. 基于多特征优选的无人机可见光遥感林分类型分类. 林业科学, 57(6): 24-36 [DOI: 10.11707/j.1001-7488.20210603http://dx.doi.org/10.11707/j.1001-7488.20210603]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
华中农业大学 资源与环境学院 宏观农业研究院
华中农业大学 植物科学技术学院
中国科学院空天信息创新研究院 遥感科学国家重点实验室
华中师范大学 城市与环境科学学院
广东省科学院广州地理研究所
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部