利用Sentinel-2遥感影像分析水葫芦时空分布规律

doi:10.13474/j.cnki.11-2246.2023.0166

测绘通报 ›› 2023, Vol. 0 ›› Issue (6): 44-49.doi: 10.13474/j.cnki.11-2246.2023.0166

利用Sentinel-2遥感影像分析水葫芦时空分布规律

王冬梅¹, 吴勇锋¹, 石一凡¹, 梁文广¹, 王轶虹¹, 潘思远²

1. 江苏省水利科学研究院, 江苏南京 210017;
2. 河海大学农业科学与工程学院, 江苏南京 210024

收稿日期:2022-07-28 发布日期:2023-07-05
通讯作者: 吴勇锋。E-mail:yongfengwu1995@163.com
作者简介:王冬梅(1978-),女,硕士,研究员级高级工程师,主要从事河湖空间变化相关研究。E-mail:17290559@qq.com
基金资助:
江苏省水利科技项目(2021072;2020039;2019049);自主科研项目(2020z025;2022z031)

Analyzing the spatio-temporal distribution of Eichhornia crassipes based on Sentinel-2 remote sensing

WANG Dongmei¹, WU Yongfeng¹, SHI Yifan¹, LIANG Wenguang¹, WANG Yihong¹, PAN Siyuan²

1. Jiangsu Provincial Institute of Water Conservancy Sciences, Nanjing 210017, China;
2. School of Agricultural Science and Engineering, Hohai University, Nanjing 210024, China

Received:2022-07-28 Published:2023-07-05

摘要/Abstract

摘要： 水葫芦大面积暴发会对河湖防洪、供水安全,水生态造成重要影响。本文以江苏省里下河地区为研究区,采用Sentinel-2影像数据对比分析3种机器学习算法分类精度,利用最佳分类方法提取2017—2021年多期影像中的水葫芦,分析研究区水葫芦暴发年际特征及其扩散趋势。结果表明,基于支持向量机(SVM)的分类效果优于神经网络(NN)和随机森林(RF)(总体精度为84.81%～94.30%,Kappa系数为0.70～0.89);2017—2021年水葫芦面积整体呈先增后减趋势,其中,2019年水葫芦暴发达到峰值,暴发热点主要集中在阜宁县南部、宝应县中部及兴化市南部地区等行政交界和水网密集处。兴化、宝应、高邮、江都、阜宁五区县年均水葫芦面积在3 km²以上,其中兴化市年均水葫芦暴发最为频繁,面积达6.85 km²。

关键词: 遥感, 水葫芦, Sentinel-2, 支持向量机, 里下河地区, 时空分布

Abstract: The large-scale outbreak of Eichhornia crassipes dramatically influence river and lake flood control, water supply security, and water ecology. In this study, the Lixia River area of Jiangsu province is chosen as the research area. We applied the Sentinel-2 image data to filter the optimal classification method of Eichhornia crassipes by compare and analyze the classification accuracy of three machine learning algorithms. Then, analysis the inter-annual spatio-temporal (2017—2021) characteristics and their spreading trends of Eichhornia crassipes by inversion of remote sensing data. The results showed that, the classification performance based on support vector machine (SVM) (overall accuracy is 84.81%～94.30%, Kappa coefficient is 0.70～0.89) is better than neural network (NN) and random forest (RF), The annual outbreak area of Eichhornia crassipes showed a trend of “increase and then decrease” from 2017 to 2021, the outbreak area of Eichhornia crassipes reached its peak in 2019. The outbreak hotspots are mainly located in the junctions of administrative region and dense water networks,such as southern Funing county, central Baoying county, and southern Xinghua city. The average Eichhornia crassipes area during 2017—2021 in the five districts and counties of Xinghua, Baoying, Gaoyou, Jiangdu, and Funing is above 3 km². Especially, the annual average Eichhornia crassipes outbreak in Xinghua is the most frequent, with an area of 6.85 km².

Key words: remote sensing, Eichhornia crassipes, Sentinel-2, support vector machine, Lixia River area, spatio-temporal distribution

中图分类号:

P237

王冬梅, 吴勇锋, 石一凡, 梁文广, 王轶虹, 潘思远. 利用Sentinel-2遥感影像分析水葫芦时空分布规律[J]. 测绘通报, 2023, 0(6): 44-49.

WANG Dongmei, WU Yongfeng, SHI Yifan, LIANG Wenguang, WANG Yihong, PAN Siyuan. Analyzing the spatio-temporal distribution of Eichhornia crassipes based on Sentinel-2 remote sensing[J]. Bulletin of Surveying and Mapping, 2023, 0(6): 44-49.

参考文献

[1] HE C Y,LIU Z F,WU J G,et al. Future global urban water scarcity and potential solutions[J]. Nature Communications,2021,12(1):4667.
[2] DAI D,SUN M D,LÜ X B,et al. Comprehensive assessment of the water environment carrying capacity based on the spatial system dynamics model,a case study of Yongding River Basin in North China[J]. Journal of Cleaner Production,2022,344:131137.
[3] 蔡竟芳,孙凯,张羽,等. 凤眼莲入侵强度和水深对沉水植物生长及种间关系的影响[J]. 环境科学学报,2022,42(1):36-46.
[4] ALBRIGHT T P,MOORHOUSE T G,MCNABB T J. The rise and fall of Eichhornia crassipes in Lake Victoria and the Kagera River basin,1989-2001[J]. Journal of Aquatic Plant Management,2004,42(42):73-84.
[5] VERMA R,SINGH S P,RAJ K G. Assessment of changes in water-hyacinth coverage of water bodies in northern part of Bangalore city using temporal remote sensing data[J]. Current Science,2003,84:795-804.
[6] 蒋明,郭云开,朱佳明,等. 时序遥感影像滇池凤眼莲时空动态变化分析[J]. 遥感信息,2019,34(3):43-47.
[7] 杨静学,陈亮雄,李伟添,等. 多源卫星遥感数据和水色遥感技术在水库水葫芦覆盖监察中的应用[J]. 农业与技术,2019,39(3):5-7.
[8] 张覃雅基于Worldview影像的外来入侵植物提取方法对比及格局动态[D].北京:中国地质大学,2019.
[9] 秦雁,陈亮雄,杨静学,等. 东莞市水葫芦分布遥感动态监测分析[J]. 广东水利水电,2020(7):11-15.
[10] MUKARUGWIRO J A,NEWETE S W,ADAM E,et al. Mapping distribution of Eichhornia crassipes (Eichhornia crassipes) in Rwanda using multispectral remote sensing imagery[J]. African Journal of Aquatic Science,2019,44(4):339-348.
[11] SINGH G,REYNOLDS C,BYRNE M,et al.A remote sensing method to monitor water,aquatic vegetation,and invasive eichhornia crassipes at national extents[J]. Remote Sensing,2020,12(24):4021.
[12] 徐勇,郑志威,郭振东,等. 2000-2020年长江流域植被NDVI动态变化及影响因素探测[J].环境科学,2022,43(7):3730-3740.
[13] 宁津生.测绘工程专业和测绘学[J]. 测绘工程,2000,9(2):70-74.
[14] 李瑶,张立福,黄长平,等. 基于MODIS植被指数时间谱的太湖2001年-2013年蓝藻暴发监测[J]. 光谱学与光谱分析,2016,36(5):1406-1411.
[15] 张圳,张弥,肖薇,等. 太湖水生植被NDVI的时空变化特征分析[J]. 遥感学报,2018,22(2):324-334.
[16] 汪星,宫兆宁,井然,等. 基于连续统去除法的水生植物提取及其时空变化分析——以官厅水库库区为例[J]. 植物生态学报,2018,42(6):640-652.
[17] 张妮娜,张珂,李运平,等. 中国南方典型湿润山区植被类型的无人机多光谱遥感机器学习分类研究[J]. 遥感技术与应用,2022,37(4):816-825.
[18] NOI P T,KUCH V,LEHNERT L. Land cover classification using Google Earth Engine and random forest classifier-the role of image composition[J]. Remote Sensing,2020,12(15):2411.
[19] PRATICÒ S,SOLANO F,DI FAZIO S,et al. Machine learning classification of Mediterranean forest habitats in Google Earth Engine based on seasonal Sentinel-2 time-series and input image composition optimisation[J]. Remote Sensing,2021,13(4):586.
[20] YE N,JUSTIN M,XU C,et al. Improving neural network classification of indigenous forest in New Zealand with phenological features[J]. Journal of Environmental Management,2022,13(4):586.
[21] MAUNG W S,SASAKI J. Assessing the natural recovery of mangroves after human disturbance using neural network classification and Sentinel-2 imagery in wunbaik mangrove forest,Myanmar[J]. Remote Sensing,2020,13(1):52.
[22] ZHANG M L,QU H,XIE X R,et al. Supervised learning in spiking neural networks with noise-threshold[J]. Neurocomputing,2017,219:333-349.
[23] LIANG X,ZHU L,HUANG D S. Multi-task ranking SVM for image cosegmentation[J]. Neurocomputing,2017,247:126-136.
[24] CERVANTES J,GARCIA-LAMONT F,RODRÍGUEZ-MAZAHUA L,et al. A comprehensive survey on support vector machine classification:applications,challenges and trends[J]. Neurocomputing,2020,408:189-215.

利用Sentinel-2遥感影像分析水葫芦时空分布规律

Analyzing the spatio-temporal distribution of Eichhornia crassipes based on Sentinel-2 remote sensing

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李鹏, 周虹利, 林是聪, 王厚杰, 李振洪. 海洋塑料垃圾卫星遥感探测方法[J]. 测绘通报, 2023, 0(6): 20-26.
[2]	王俪璇, 叶成名, 眭天波, 魏瑞龙, 李洪富. 川藏交通廊道冰川和地表水遥感监测及耦合分析[J]. 测绘通报, 2023, 0(6): 50-55.
[3]	杨佳欣, 李佳田, 陆美, 胡明洪, 李文, 金维, 胡浩. 云南地区积雪遥感监测及气候响应分析[J]. 测绘通报, 2023, 0(6): 56-60.
[4]	张炎, 刘立龙, 何广焕, 徐勇, 蒙金龙. 改进哈里斯鹰优化算法在匹配地面点云孔洞修补中的应用[J]. 测绘通报, 2023, 0(6): 82-87.
[5]	沈鑫甦, 嵇灵. 面向遥感地类变化检测的U型深度学习神经网络改进方法[J]. 测绘通报, 2023, 0(6): 93-97,103.
[6]	范忻, 丁来中, 李莹, 王文杰, 程明, 宋会传, 高爽, 耿丽艳, 李春意. 黄河下游藕节形河道游荡趋势演变遥感分析[J]. 测绘通报, 2023, 0(6): 150-154.
[7]	陈杰, 邓敏, 侯东阳. 大数据智能时代遥感课程实践教学模式的改革与探索[J]. 测绘通报, 2023, 0(6): 176-179.
[8]	李心媛, 贺智, 楼桉君, 肖曼. 双线性图卷积网络的环南海地区湿地遥感分类[J]. 测绘通报, 2023, 0(5): 44-50.
[9]	张全旺, 郭辉. 采煤拉张裂隙区土壤有机质高光谱反演[J]. 测绘通报, 2023, 0(5): 78-83,134.
[10]	张适然, 陈明辉, 黄燕. 基于实景三维的东莞自建住宅提取与特征分析[J]. 测绘通报, 2023, 0(5): 120-124,163.
[11]	王菡, 刘宁, 薛岩, 孙贵芹, 魏潇, 徐艳东. 1975—2020年烟台芝罘湾海湾形态变化及驱动因素[J]. 测绘通报, 2023, 0(4): 10-15.
[12]	邓敏, 王晶, 唐建波, 丁晨, 杨学习, 刘慧敏, 刘宝举. 顾及纹理特征差异性的遥感影像数据分区域多密级加密方法[J]. 测绘通报, 2023, 0(4): 23-28.
[13]	赵宗泽, 方明源, 高钊, 王双亭. 融合高程信息的低空遥感影像SLIC分割和区域合并方法[J]. 测绘通报, 2023, 0(4): 35-40.
[14]	邢若芸, 冉树浩, 高贤君, 杨元维, 方军. 顾及多分辨率特征的复合字典城中村识别方法[J]. 测绘通报, 2023, 0(4): 41-48,48.
[15]	朱建伟, 李朝奎, 周新邵, 赵丁莹, 傅开鸿. 基于车载遥感影像的高速公路广告牌破损检测方法及应用[J]. 测绘通报, 2023, 0(4): 59-63,98.