Dynamic Monitoring of Spartina alterniflora in Xiangshan Harbor Based on GEE and Random Forest

doi:10.13466/j.cnki.lyzygl.2023.03.006

Abstract

Abstract:

The large-scale invasion of Spartina alterniflora has endangered the ecological security of China's coastal area.Therefore,studying a fast and accurate algorithm for identifying Spartina alterniflora is particularly important for achieving dynamic monitoring within the region.Taking Xiangshan harbor as a research zone in this study,151 Spartina alterniflora and 140 non-Spartina alterniflora land patches were used as the training data set on the GEE platform.The index of NDVI,EVI,NDWI and BSI were extracted from the Sentinel-2 remote sensing image band information,and these indices were added to the remote sensing image data.Machine learning methods such as Support Vector Machines and Random Forests were used for identification and classification.By identifying and classifying Sentinel-2 remote sensing images from 2017 to 2022,dynamic monitoring of Spartina alterniflora within the study area was achieved.The research results showed that compared with SVM,the RF method had higher recognition accuracy for identifying Spartina alterniflora,and the overall recognition accuracy in 2022 reached 99.03% with a Kappa coefficient of 0.978 7.At the same time,the experimental results showed that the area of Spartina alterniflora in Xiangshan harbor has gradually decreased since 2017,indicating that the artificial intervention measures taken during this period were very effective.The dynamic monitoring and status analysis of Spartina alterniflora in Xiangshan harbor provided quantitative scientific data for the management of Spartina alterniflora,and have important reference value for formulating relevant prevention and control measures.

Key words: Spartina alterniflora, Google Earth Engine, support vector machines, random forests, remote sensing image

CLC Number:

LIANG Licheng, FU Xiaoqiang, ZHANG Bin, CHENG Guxun, LI Zuohui. Dynamic Monitoring of Spartina alterniflora in Xiangshan Harbor Based on GEE and Random Forest[J]. FOREST RESOURCES WANAGEMENT, 2023, 0(3): 38-45.

Figures/Tables 9

Fig.1

Tab.1

Tab.2

Fig.2

Fig.3

Tab.3

Tab.4

Fig.4

Fig.5

References 14

[1]	Yang Renmin. Characterization of the salt marsh soils and visible-near-infrared spectroscopy along a chronosequence of spartina alterniflora invasion in a coastal wetland of eastern China[J]. Geoderma, 2020, 362:114138. doi: 10.1016/j.geoderma.2019.114138
[2]	沈永明, 杨劲松, 曾华, 等. 我国对外来物种互花米草的研究进展与展望[J]. 海洋环境科学, 2008, 27(4):391-396.
[3]	王卿, 安树青, 马志军, 等. 入侵植物互花米草——生物学、生态学及管理[J]. 植物分类学报, 2006, 44(5):559-588.
[4]	董小滋. 大米草“鸠占鹊巢”昔日滩涂成“海上草原”[N/OL]. 今日象山,2014-08-29(6).[2023-01-12]. http://dzb.cnxsg.cn/html/2014-08/29/content_6_1.htm.
[5]	陶艳成, 潘良浩, 范航清, 等. 广西海岸潮间带互花米草遥感监测[J]. 广西科学, 2017, 24(5):483-489.
[6]	费鲜芸, 何鑫坤, 谢宏璇, 等. 基于GF-1卫星影像的临洪河口湿地遥感分类[J]. 江苏海洋大学学报:自然科学版, 2021, 30(2):50-57.
[7]	郑浩, 陈星彤, 宋利杰, 等. 基于GEE的滨海湿地互花米草信息提取方法研究[J]. 赤峰学院学报:自然科学版, 2022, 38(10):1-6.
[8]	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. doi: 10.11821/dlxb202107008
[9]	李京, 刘亚静, 刘明月. 基于Sentinel-2A影像的互花米草信息提取研究[J]. 华北理工大学学报:自然科学版, 2021, 43(3):14-19.
[10]	中国海湾志编纂委员会. 中国海湾志(第五分册)[M]. 北京: 海洋出版社, 1992:166-206.
[11]	He Tao, Zhou Houkui, Xu Caiyao, et al. Deep learning in forest tree species classification using Sentinel-2 on Google Earth Engine:A case study of Qingyuan County[J]. Sustainability, 2023, 15(3):2741. doi: 10.3390/su15032741
[12]	Rabiei S, Jalilvand E, Tajrishy M. A method to estimate surface soil moisture and map the irrigated cropland area using Sentinel-1 and Sentinel-2 Data[J]. Sustainability, 2021, 13(20):11355. doi: 10.3390/su132011355
[13]	易俐娜, 张桂峰, 魏征, 等. 利用无人机高光谱影像的红树林群落物种分类[J]. 测绘通报, 2022(11):26-31. doi: 10.13474/j.cnki.11-2246.2022.0320
[14]	付雅晴, 印萍, 高飞, 等. 浙江省三门湾北部潮滩互花米草遥感研究[J]. 中国海洋大学学报, 2022, 52(1):134-144.

Sentinel-2 波段	波长/μm	分辨率/m
Band 1:coastal aerosol	0.443	60
Band 2:blue	0.490	10
Band 3:green	0.560	10
Band 4:red	0.665	10
Band 5:vegetation red edge	0.705	20
Band 6:vegetation red edge	0.740	20
Band 7:vegetation red edge	0.783	20
Band 8:NIR	0.842	10
Band 8A:vegetation red edge	0.865	20
Band 9:water vapor	0.945	60
Band 10:SWIR-cirrus	1.375	60
Band 11:SWIR	1.610	20
Band 12:SWIR	2.190	20

Landsat-8 波段	波长/μm	分辨率/m
Band 1:Coastal aerosol	0.43~0.45	30
Band 2:Blue	0.45~0.51	30
Band 3:Green	0.53~0.59	30
Band 4:Red	0.64~0.67	30
Band 5:Near infrared	0.85~0.88	30
Band 6:Shortwave infrared 1	1.57~1.65	30
Band 7:Shortwave infrared 1	2.11~2.29	30
Band 8:Panchromatic	0.52~0.90	15
Band 9:Cirrus	1.36~1.38	15
Band 10:Thermal infrared 1	10.60~11.19	30
Band 11:Thermal infrared 2	11.50~12.51	30
BQA:Landsat Collection 1 QA Bitmask		30

年份	RF算法		SVM算法
年份	OA/%	Kappa系数	OA/%	Kappa系数
2017	98.94	0.976 7	96.86	0.930 9
2018	98.82	0.974 1	97.00	0.934 6
2019	99.26	0.983 6	98.17	0.959 8
2020	99.22	0.982 8	97.38	0.942 3
2021	99.13	0.980 8	97.37	0.942 0
2022	99.03	0.978 7	97.25	0.939 7

年份	分类	互花米草	非互花米草
2017	互花米草	3 798	8
2017	非互花米草	109	7123
2018	互花米草	3 802	4
2018	非互花米草	126	7 106
2019	互花米草	3 794	12
2019	非互花米草	70	7 162
2020	互花米草	3 800	6
2020	非互花米草	80	7 152
2021	互花米草	3 795	11
2021	非互花米草	85	7 147
2022	互花米草	3 799	7
2022	非互花米草	100	7 132

[1]	TANG Jinhao, ZHANG Jialong, CHEN Liye, CHENG Tao. Research on Estimation of Aboveground Biomass and Scale Conversion for Pinus densata Mast [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(6): 83-89.
[2]	ZHANG Diandai, WANG Xuemei. Comparison of Vegetation Classification Methods Based on High Resolution Remote Sensing Image [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(3): 108-113.
[3]	QIU Shiping, WEI Mingxin, MA Yisha. Study on Automatic Extraction of Fast-Growing Eucalyptus Stand Parameters Based on UAV Remote Sensing Images [J]. FOREST RESOURCES WANAGEMENT, 2021, 0(3): 114-119.
[4]	SUN Zhongqiu, WU Fayun, HU Yang, GAO Xianlian, Gao Jingping. Determination and Estimation of Pinus massoniana Stand Volume and Saturation Point Based on Landsat-8 OLI Data [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(6): 135-142.
[5]	LU Xianjian, HUANG Yuhui, YAN Hongbo, WEI Wanqiu, LI Zhenbao. Research on Eucalyptus Extraction Based on Automatic Threshold Decision Tree Classification [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(4): 117-126.
[6]	QI Xinglan, CAO Zuning, LIU Jian, CHEN Fang, ZHUANG Wei. Research Progress in the Monitoring of Forest Diseases, Insect and Pests Based on Satellite Remote Sensing Images [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(2): 181-186.
[7]	Zhongming JIN, Shanshan CAO, Lei WANG, Wei SUN. Study on Extraction of Tree Crown Information from UAV Visible Light Image of Piceaschrenkiana var.tianschanica Forest [J]. FOREST RESOURCES WANAGEMENT, 2020, 0(1): 125-135.
[8]	LU Xianjian, HUANG Yuhui, YAN Hongbo, ZHOU Lv, WU Chenlong, ZHOU Bin, LUO Le. Study on Rapid Extraction of Eucalyptus Vegetation Information in Guangxi Based on GEE [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(5): 52-60.
[9]	CHEN Xinyun, LI Liwei, LIU Chengfang, WANG Liuru, DING Jing. Remote Sensing inversion of Classification and Stocking Volume of Tropical Virgin Forest Types Based on Multivariate Data [J]. FOREST RESOURCES WANAGEMENT, 2019, 0(2): 39-46.
[10]	LI Weiwei, HE Dongjin, YAN Sixiao, CAI Jinbiao, WANG Ren, YOU Weibin, HOU Dongliang, BAI Jing. Analysis of the Impacts on the Physical Properties of Mangrove Soil in Eastern Fujian Coastal Wetlands under the Invasion of Spartina alterniflora [J]. FOREST RESOURCES WANAGEMENT, 2018, 0(2): 151-156.
[11]	HUANG Bei, ZHU Liyan, LIU Wenguo. Inspection and Application Analysis of Forestland Management Based on Unmanned Aerial Vehicle [J]. FOREST RESOURCES WANAGEMENT, 2017, 0(6): 153-158.
[12]	HUANG Tian, ZHANG Chao, JI Yitao, YU Zhexiu, LUO Hengchun, ZHANG Yi. Study on Remote Sensing Classification of Typical Forest Types in Central Yunnan Based on Endmember Extraction,ZHANG Yi [J]. FOREST RESOURCES WANAGEMENT, 2017, 0(4): 110-116.
[13]	MOU Huaiyi. Monitoring of Forestland Dynamic Changes by Using Multi Source and High Resolution Satellite Remote Sensing Images [J]. FOREST RESOURCES WANAGEMENT, 2016, 0(4): 107-113.
[14]	DANG Yongfeng. Estimation of Forest Harvesting Area and Harvest Volume on Scale Extrapolating Approach [J]. FOREST RESOURCES WANAGEMENT, 2013, 0(3): 129-133.
[15]	YU Xiaoguang, WANG Xiaokun, JIANG Aijun, HU Jiping, YU Shiyong. Discussion on Application of Medium and High Resolution Remote Sensing Images in Afforestation Effect Monitoring [J]. FOREST RESOURCES WANAGEMENT, 2012, 0(5): 59-63.