Classification of coastal wetlands in the Pearl River Estuary using Zhuhai-1 hyperspectral imagery and XGBoost algorithm

doi:10.13474/j.cnki.11-2246.2023.0373

Abstract

Abstract: Remote sensing classification of wetlands is still challenging due to the diversity of wetland types and complex composition. Taking the Pearl River Estuary as the study area, based on Zhuhai-1 hyperspectral imagery, we extracted the wetland type information with the spectral features, shape features, texture features, and spectral indices, using the eXtreme gradient boosting (XGBoost) algorithm, and compared with support vector machine (SVM) and random forest (RF). Results showed that Zhuhai-1 imagery can be used to identify wetland types accurately. Among three machine learning algorithms, the XGBoost gave the best wetland classification effect (OA=87.2%, Kappa coefficient=0.84). Moreover, the selected features gave higher classification accuracy, which verified the importance of feature selection for Zhuhai-1 imagery. This study proposed a new method suitable for large-area wetland classification, which can provide a practical technical reference for wetland resource investigation, protection, and development.

Key words: wetland classification, mangrove, remote sensing, XGBoost, Zhuhai-1, hyperspectral imagery

CLC Number:

P237

LIU Yanjun, LIU Kai, CAO Jingjing. Classification of coastal wetlands in the Pearl River Estuary using Zhuhai-1 hyperspectral imagery and XGBoost algorithm[J]. Bulletin of Surveying and Mapping, 2023, 0(12): 136-141.

References

[1] 李玉凤,刘红玉. 湿地分类和湿地景观分类研究进展[J]. 湿地科学,2014,12(1): 102-108.
[2] 牟晓杰,刘兴土,阎百兴,等. 中国滨海湿地分类系统[J]. 湿地科学,2015,13(1): 19-26.
[3] 杜文,国斯恩,刘津如,等. 基于Landsat8 OLI遥感数据的辽河口湿地分类与动态监测研究[J]. 沈阳农业大学学报,2022,53(4): 432-443.
[4] 程丽娜,钟才荣,李晓燕,等. Sentinel-2密集时间序列数据和Google Earth Engine的潮间带湿地快速自动分类[J]. 遥感学报,2022,26(2): 348-357.
[5] 黎丰收,刘凯,刘洋,等.基于WorldView-2数据的基塘系统遥感分类研究[J]. 湿地科学,2018,16(5): 587-596.
[6] XU Bing,GONG Peng. Noise estimation in a noise-adjusted principal component transformation and hyperspectral image restoration[J]. Canadian Journal of Remote Sensing,2008,34(3): 271-286.
[7] 张雅春,那晓东,臧淑英. 基于HJ-1A高光谱影像的湿地精细分类[J]. 地理科学进展,2018,37(12): 1705-1712.
[8] 李晓敏,张杰,马毅,等. 基于无人机高光谱的外来入侵种互花米草遥感监测方法研究: 以黄河三角洲为研究区[J]. 海洋科学,2017,41(4): 98-107.
[9] 谢静,王宗明,毛德华,等. 基于面向对象方法和多时相HJ-1影像的湿地遥感分类: 以完达山以北三江平原为例[J]. 湿地科学,2012,10(4): 429-438.
[10] YAN Dan,WERNERS S E,LUDWIG F,et al. Hydrological response to climate change: the Pearl River,China under different RCP scenarios[J]. Journal of Hydrology: Regional Studies,2015,4: 228-245.
[11] 莫利江,曹宇,胡远满,等. 面向对象的湿地景观遥感分类: 以杭州湾南岸地区为例[J]. 湿地科学,2012,10(2): 206-213.
[12] 吴庆双,汪明秀,申茜,等. Sentinel-2遥感图像的细小水体提取[J]. 遥感学报,2022,26(4): 781-794.
[13] 陈磊士,高霞霞,廖玉芳,等. 基于CART决策树的高分二号洞庭湖区湿地分类方法[J]. 测绘通报,2021(6): 12-15.
[14] 黄慧萍,吴炳方. 地物提取的多尺度特征遥感应用分析[J]. 遥感技术与应用,2003,18(5): 276-281.
[15] THOMAS N,HENDRIX C,CONGALTON R G. A comparison of urban mapping methods using high-resolution digital imagery[J]. Photogrammetric Engineering & Remote Sensing,2003,69(9): 963-972.
[16] DRǍGUŢ L,TIEDE D,LEVICK S R.ESP:a tool to estimate scale parameter for multiresolution image segmentation of remotely sensed data[J].International Journal of Geographical Information Science,2010,24(6):859-871.
[17] 姚博,张怀清,刘洋,等. 面向对象CART决策树方法的湿地遥感分类[J].林业科学研究,2019,32(5): 91-98.
[18] 孙宁青. 基于神经网络和CFS特征选择的网络入侵检测系统[J].计算机工程与科学,2010,32(6): 37-39.
[19] HALL M,SMITH L A. Feature subset selection: a correlation based filter approach[EB/OL]. [2023-02-02].https://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=1EAD7EDD7630EDF0CBD195FAC5906B23?doi=10.1.1.52.217&rep=rep1&type=pdf.
[20] CHEN Tianqi,GUESTRIN C. XGBoost: a scalable tree boosting system[EB/OL]. [2023-02-02].https://arxiv.org/abs/1603.02754.pdf.
[21] 叶倩怡,饶泓,姬名书. 基于Xgboost的商业销售预测[J]. 南昌大学学报(理科版),2017,41(3): 275-281.
[22] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报,2000,26(1): 32-42.
[23] 范怀刚,岳彩荣,王栋. 基于支持向量机的宜良县遥感分类与土地覆盖变化研究[J]. 林业调查规划,2014,39(2): 51-56.
[24] BREIMAN L. Random forests[J]. Machine Language,2001,45(1): 5-32.
[25] 方匡南,吴见彬,朱建平,等. 随机森林方法研究综述[J]. 统计与信息论坛,2011,26(3): 32-38.