Please wait a minute...
img

Wechat

Remote Sensing Technology and Application  2022, Vol. 37 Issue (4): 982-992    DOI: 10.11873/j.issn.1004-0323.2022.4.0982
    
Recognition of Vegetation Types in Hulunbuir Sandy Land and Its Surrounding Areas based on GEE Cloud Platform and Sentinel-2 Time Series Data
Xianbao Yang1,2(),Wangfei Zhang1,Bin Sun2,3(),Zhihai Gao2,3,Yifu Li2,3,Han Wang2,3
1.College of Geography and Ecotourism,Southwest Forestry University,Kunming 650224,China
2.Institute of Forest Resource Information Techniques,Chinese Academy of Forestry,Beijing 100091,China
3.Key Laboratory of Forestry Remote Sensing and Information System,Beijing 100091,China
Download:  HTML  PDF (4297KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

Sand and its surrounding vegetation types play an important role in fixing dunes, preventing soil erosion and environmental management for sandy land. Identification of Sand and its surrounding vegetation types can objectively reflect the vegetation growth environment of sandy land and its surrounding areas, so as to provide a valuable reference for ecological restoration and the control policies formulating of sandy land. With huge amount of long-term earth observation data and powerful cloud computing capabilities, Google Earth Engine (GEE) cloud platform provides a convenient way for the identification of vegetation types in a large areas. In this study, based on the Sentinel-2 time series data of 2019 stored in the GEE cloud platform, the applied potentialities of GEE cloud platform in vegetation types identification was explored by combining the RF algorithm and vegetation phenology information in Hulunbuir sandy land and its surroundings. Results showed that: ① The spectral information of Sentinel-2 image and the texture information obtained from the near-infrared band have limited ability to identify the main vegetation types in the study area, but the phenological characteristics effectively make up for this shortcoming; ② Accuracy of the vegetation types identification method achieved by the RF algorithm and considering the phenological characteristics extracted from the long time series remote sensing data is 84.37% (with the Kappa coefficient of 0.8), which is 10.01% higher than that identification result acquired based on single-phase data; ③Phenological characteristics of the main vegetation types in the Hulunbuir sandy land and its surroundings show significant differences, which is helpful for the identification of the vegetation types, especially to improve the recognition accuracy of shrubs and grassland.The research shows that the use of Sentinel-2 data and GEE cloud platform to identify vegetation types in large areas such as sandy land has great potential and broad application prospects.

Key words:  GEE      Sentinel-2      Time series data      Hulunbuir sandy land      Identification of vegetation types     
Received:  11 February 2021      Published:  28 September 2022
K901.4  
Corresponding Authors:  Bin Sun     E-mail:  2296857887@qq.com;sunbin@ifrit.ac.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Xianbao Yang
Wangfei Zhang
Bin Sun
Zhihai Gao
Yifu Li
Han Wang

Cite this article: 

Xianbao Yang,Wangfei Zhang,Bin Sun,Zhihai Gao,Yifu Li,Han Wang. Recognition of Vegetation Types in Hulunbuir Sandy Land and Its Surrounding Areas based on GEE Cloud Platform and Sentinel-2 Time Series Data. Remote Sensing Technology and Application, 2022, 37(4): 982-992.

URL: 

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2022.4.0982     OR     http://www.rsta.ac.cn/EN/Y2022/V37/I4/982

Fig.1  The study area location diagram
Fig.2  Technical route
代码植被类型特征
1针叶林森林郁闭度≥60%,以针叶林为主要类型,以樟子松、落叶松等针叶树为建群种组成的森林群落。
2阔叶林森林郁闭度≥60%,以阔叶林为主要类型,以白桦和山杨等为建群种组成的森林群落。
3针阔混交林森林郁闭度≥60%,针叶林和阔叶林相互混生且每种类型面积均不超过50%,是针叶林向阔叶林过渡的植被类型,是白桦、山杨和樟子松、落叶松相互混生的森林群落。
4灌草丛林木郁闭度在10%—60%,高度在2 m以下的灌丛,以中生或旱中生多年生草本植物为主要建群种,其中散生灌木的植物群落。主要以小叶锦鸡、冷蒿、差巴嘎蒿、黄柳、榆树等植被为主。
5草原林灌郁闭度<10%,且覆盖度大于5%,是一种以生长草本植物为主,由旱生或中旱生草本植物组成的草本植物群落,主要有线叶菊、贝加尔针茅、羊草、大针茅、克氏针茅、隐子草等。
6农作物农业上栽培的各种粮食和经济植物,包括大豆、玉米、小麦、油菜、蔬菜等植被。
7其他植被主要由天然草本植物为主的沼泽化低地草甸、沼泽植被和水生植被等。
8非植被植被覆盖度小于5%,表层主要由水体、人造地表、盐碱地、裸沙、裸地、矿坑等覆盖。
Table 1  Classification system
特征类型特征信息
光谱特征B1、B2、B3、B4、B5、B6、B7、B8、B8A、B9、B11、B12
植被指数NDVI、NDBI、MNDWI、EVI
纹理特征B8_asm、B8_contrast、B8_corr、B8_var、B8_idm、B8_savg、B8_svar、B8_sent、B8_ent、B8_dvar、B8_dent、B8_imcorr1、B8_imcorr2、B8_maxcorr、B8_diss、B8_inertia、B8_shade、B8_prom
植被覆盖度fv
物候特征1月—12月NDVI
地形特征坡向、海拔、山体阴影
Table 2  Original features and optimization
Fig.3  Spectral feature graph of different vegetation types
Fig.4  NDVI curve of different vegetation types
Fig.5  Feature dimension and the identification accuracy
数据

总体精度

/%

Kappa 系数类别生产精度 /%用户精度 /%
单一时相数据74.360.66针叶林60.6164.52
阔叶林71.7951.85
针阔混交林31.8250.00
灌草丛62.6862.07
草原76.9266.67
农作物72.8679.69
其他植被12.550.00
非植被87.2186.89
时序数据84.370.80针叶林76.0077.56
阔叶林85.1967.65
针阔混交林43.7577.78
灌草丛78.0772.92
草原93.7580.54
农作物84.7886.67
其他植被31.8287.50
非植被91.0494.31
Table 3  Different vegetation type recognition accuracy evaluation
Fig. 6  Partial enlargement diagram of recognition results in different temporal
Fig.7  Vegetation type recognition results of different temporal data
Fig.8  Proportion of different vegetation types
1 Tu Zhifang, Li Mengxian, Sun Tao. The status and trend analysis of desertification and sandification[J]. Forest Resources Management, 2016(1):1-5,13.
1 屠志方, 李梦先, 孙涛. 第五次全国荒漠化和沙化监测结果及分析[J]. 林业资源管理, 2016(1):1-5,13.
2 Yao Xueling, Jiang Lina, Li Long, et al. Biomass simulation of six shrub species in otindag sandy land[J]. Acta Ecologica Sinica, 2019, 39(3):905-912.
2 姚雪玲, 姜丽娜, 李龙, 等. 浑善达克沙地6种灌木生物量模拟[J]. 生态学报, 2019, 39(3):905-912.
3 Jia Kun, Li Qiangzi, Tian Yichen, et al. A review of classification methods of remote sensing imagery[J]. Spectroscopy and Spectral Analysis, 2011,31(10):2618-2623.
3 贾坤, 李强子, 田亦陈, 等. 遥感影像分类方法研究进展[J]. 光谱学与光谱分析, 2011, 31(10):2618-2623.
4 Li Shihua, Wang Jinliang, Bi Yan, et al. A review of methods for classification of remote sensing images[J]. Remote Sensing for Land & Resources, 2005,17(5): 1-6.
4 李石华, 王金亮, 毕艳, 等. 遥感图像分类方法研究综述[J]. 国土资源遥感, 2005,17(5):1-6.
5 Yang Chao, Wu Guofeng, Li Qingquan, et al. Fast map rectification algorithm based on error homogeneous region[J]. Geography and Geo-Information Science, 2018, 34(4):24-32.
5 杨超, 邬国锋, 李清泉, 等. 植被遥感分类方法研究进展[J]. 地理与地理信息科学, 2018, 34(4):24-32.
6 Xu Dawei. Dynamic change and analysis of different grassland types distribution in the Hulunber Grassland[D]. Beijing: Chinese Academy of Agricultural Sciences Dissertation, 2019.
6 徐大伟. 呼伦贝尔草原区不同草地类型分布变化及分析[D]. 北京:中国农业科学院, 2019.
7 Zhang Ying. Classification of forest types based on multi-dimensional features using multi-seasonal Landsat-8 OLI remote sensing images[D]. Beijing: Beijing Forestry University, 2018.
7 张莹. 基于多季相Landsat-8 OLI影像的多特征森林植被分类[D]. 北京:北京林业大学, 2018.
8 Zhang Yan. Study of remote sensing image classification based on machine learning[D]. Beijing: Beijing Forestry University, 2014.
8 张雁. 基于机器学习的遥感图像分类研究[D]. 北京:北京林业大学, 2014.
9 Zhu Sha. Remote sensing image classification based on machine learning[D]. Ganzhou: Jiangxi University of Science and Technology, 2017.
9 朱莎. 基于机器学习的遥感图像分类研究[D]. 赣州:江西理工大学, 2017.
10 Foody G M, Mathur A. Toward intelligent training of supervised image classifications: Drecting training data acquisition for SVM classification[J]. Remote Sensing Environment, 2004(93):107-117. DOI: .
doi: 10.1016/j.rse.2004.06.017
11 Ding Xiangyuan, Gao Zhihai, Sun Bin, et al. Sandy lands classification using GF-1 time series NDVI data[J]. Remote Sensing for Land and Resources, 2017, 29(3) : 196-202.
11 丁相元, 高志海, 孙斌, 等. 基于高分一号时间序列数据的沙化土地分类[J]. 国土资源遥感, 2017, 29(3):196-202.
12 Liang Shuang, Gong Zhaoning, Zhao Wenji, et al. Information extraction of Baiyangdian wetland based on multi-season Sentinel-2 Images[J]. Remote Sensing Technology and Application, 2021, 36(4): 777-790.
12 梁爽,宫兆宁,赵文吉,等. 基于多季相Sentinel-2影像的白洋淀湿地信息提取[J]. 遥感技术与应用, 2021, 36(4): 777-790.
13 Wakulińska M, Marcinkowska-Ochtyra A. Multi-temporal Sentinel-2 data in classification of mountain vegetation[J]. Remote Sensing,2020,12(17):2696.DOI: .
doi: 10.3390/rs 12172696
14 Rapinel Sébastien, Mony Cendrine, Lecoq Lucie, et al. Evaluation of Sentinel-2 time-series for mapping floodplain grassland plant communities[J]. Remote Sensing of Environment, 2019, 223(15):115-129. DOI: .
doi: 10.1016/j.rse.2019.01.018
15 Dong Jinwei, Li Shiwei, Zeng Yelu, et al. Remote sensing cloud computing and scientific analysis-applications and practices[M]. Beijing: Science Press, 2020:8-11.董金玮, 李世卫, 曾也鲁, 等. 遥感云计算与科学分析—应用与实践[M]. 北京: 科学出版社, 2020:8-11.
16 Chen Kangming, Zhu Xudong. Remote sensing of spatio-temporal dynamics of saltmarsh vegetation along south China coast based on Google Earth Engine[J]. Remote Sensing Technology and Application, 2021, 36(4): 751-759.
16 陈康明,朱旭东. 基于Google Earth Engine的南方滨海盐沼植被时空演变特征分析[J]. 遥感技术与应用, 2021, 36(4): 751-759.
17 Long Shuang, Guo Zhengfei, Xu Li, et al. Spatiotemporal variations of fractional vegetation coverage in China based on Google Earth Engine[J]. Remote Sensing Technology and Application, 2020, 35(2): 326-334.
17 龙爽,郭正飞,徐粒,等.基于Google Earth Engine的中国植被覆盖度时空变化特征分析[J].遥感技术与应用,2020,35(2):326-334.
18 Wang Xiaona, Tian Jinyan, Li Xiaojuan, et al. Benefits of Google Earth Engine in remote sensing[J]. National Remote Sensing Bulletin, 2022,26(2): 299-309.
18 王小娜, 田金炎, 李小娟, 等. Google Earth Engine云平台对遥感发展的改变.遥感学报, 2022,26(2): 299-309.
19 Deng Fang, Chen Jie. Dynamic analysis and quality evaluation of Hulunbuir Sandy Land[J]. Inner Mongolia Forestry Investigation and Design, 1997, 11(1):34-37.
19 邓芳, 陈杰. 呼伦贝尔沙地动态分析与质量评价[J]. 内蒙古林业调查设计, 1997, 11(1):34-37.
20 Bai Yan, An Huijun, Zhang Honglei, et al. Remote sensing monitoring of vegetation changes in Hulunbeier Sandy Land[J]. Forest Resources Management, 2013(3):134-137.
20 白彦, 安慧君, 张红蕾, 等. 呼伦贝尔沙地植被变化遥感监测[J]. 林业资源管理, 2013(3):134-137.
21 Dong Jianlin, Jie Ya. Analysis on the changes of land desertification in hulunbeier sandy land area over the last 10 years [J]. Forest Resources Management, 2002(4):39-43.
21 董建林, 雅洁. 呼伦贝尔沙地近十年来土地沙漠化变化分析[J]. 林业资源管理, 2002(4):39-43.
22 Ki Hyung Park, Qu Z Q, Wan Q Q, et al. Effects of enclosures on vegetation recovery and succession in Hulunbeier steppe, China[J]. Forest Science and Technology, 2013, 9(1):25-32. DOI: .
doi: 10.1080/21580103.2013.774124
23 Zhang Yujing. Remote sensing monitoring of Hulunbuir grassland phenology and the correlativity between phenology and climatic factors [D]. Beijing: Chinese Academy of Agricultural Sciences Dissertation, 2018.
23 张玉静. 呼伦贝尔草原物候遥感监测及其与气候因子的关系[D]. 北京:中国农业科学院, 2018.
24 Bai Yan. Study on vegetation coverage change of Hulunbeier sand land by remote sensing[D]. Hohhot: Inner Mongolia Agricultural University, 2013.
24 白彦. 呼伦贝尔沙地植被覆盖度变化遥感监测研究[D]. 呼和浩特:内蒙古农业大学, 2013.
25 Zhu Xiaoyu, Xu Dawei, Xin Xiaoping, et al. The spatial-temporal distribution of different grassland types in hulunber grassland based on remote sensing from 1992 to 2015[J]. Scientia Agricultura Sinica, 2020, 53(13):2715-2727.
25 朱晓昱, 徐大伟, 辛晓平, 等. 1992—2015年呼伦贝尔草原区不同草地类型分布时空变化遥感分析[J]. 中国农业科学, 2020, 53(13):2715-2727.
26 Kang Jun. Fine vegetation classification and fractional vegetation cover retrieval using time series remote sensing data[D]. Beijing: University of Chinese Academy of Sciences(Institute of Remote Sensing and Digital Earth, Chine), 2018.
26 康峻. 基于时间序列遥感数据的植被精细分类与覆盖度反演研究[D]. 北京:中国科学院大学(中国科学院遥感与数字地球研究所), 2018.
27 Chen Yansi, Huang Chunlin, Hou Jinliang, et al. Extraction of maize planting area based on multi-temporal Sentinel-2 imagery in the middle reaches of Heihe river[J]. Remote Sensing Technology and Application, 2021, 36(2): 324-331.
27 陈彦四, 黄春林, 侯金亮, 等. 基于多时相Sentinel-2影像的黑河中游玉米种植面积提取研究[J]. 遥感技术与应用, 2021, 36(2): 324-331.
28 Wu Zhengyi. Chinese vegetation[M]. Beijing: Science Press, 1980:143-682.
28 吴征镒. 中国植被[M]. 北京: 科学出版社, 1980:143-682.
29 Zhang Zengxiang, et al. Monitoring land cover in China[M]. Beijing: Planet Map Press, 2010:5-6.张增祥, 等. 中国土地覆盖监测[M]. 北京: 星球地图出版社, 2010:5-6.
30 Zhang Bo. Texture feature extraction analysis of remote sensing image based on gray level co- occurrence matrix[J]. Cultural Geography, 2017(22):190-200.
30 张博. 基于灰度共生矩阵的遥感影像纹理特征提取分析[J]. 城市地理, 2017(22):190-200.
31 He Zhaoxin, Zhang Miao, Wu Bingfang, et al. Extraction of summer crop in Jiangsu based on Google Earth Engine[J]. Journal of Geo-information Science, 2019,21(5):752-766.
31 何昭欣, 张淼, 吴炳方, 等. Google Earth Engine 支持下的江苏省夏收作物遥感提取[J]. 地球信息科学学报, 2019,21(5):752-766.
32 Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Transactions on systems, man, and cybernetics, 1973,3(6):610-621. DOI: .
doi: 10.1109/TSMC.1973.4309314
33 Wang Minyu, Luo Yi, Zhang Zhengyang, et al. Recent advances in remote sensing of vegetation phenology: Retrieval algorithm and validation strategy[J]. National Remote Sensing Bulletin, 2022,26(3): 431-455.
33 王敏钰, 罗毅, 张正阳, 等. 植被物候参数遥感提取与验证方法研究进展[J]. 遥感学报, 2022,26(3): 431-455.
34 Li Zhengguo, Tang Huajun, Yang Peng, et al. Progress in remote sensing of vegetation phenology and its application in agriculture[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2012, 33:20-28.
34 李正国, 唐华俊, 杨鹏, 等. 植被物候特征的遥感提取与农业应用综述[J]. 中国农业资源与区划, 2012, 33:20-28.
35 Wei X Q, Gu X F, Tao Y, et al. Land-cover classification using multi-temporal GF-1 wide field view data[J]. Taylor & Francis,2018,39(20):6914-6930. DOI: .
doi: 10.1080/01431161. 2018.1468106
36 Bi Kaiyi, Niu Zheng, Huang Ni, et al. Identifying vegetation with decision tree modle based on object oriented method using multi-temporal Sentinel-2A images[J]. Geography and Geo-Information Science, 2017, 33(5):16-20,27,127.
36 毕恺艺, 牛铮, 黄妮, 等. 基于Sentinel-2A时序数据和面向对象决策树方法的植被识别[J]. 地理与地理信息科学, 2017, 33(5):16-20,27,127.
37 Yao Dengju, Yangjing, Zhan Xiaojuan. Feature selection algorithm based on random forest[J]. Journal of Jilin University(Engineering and Technology Edition), 2014, 44(1):137-141.
37 姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版), 2014, 44(1):137-141.
38 Lu D, Weng Q. A survey of image classification methods and techniques for improving classification performance[J]. International Journal of Remote Sensing, 2007, 28(5): 823-870. DOI: .
doi: 10.1080/01431160600746456
39 Huang D M, Xu S J, Sun J Q, et al. Accuracy assessment model for classification result of remote sensing image based on spatial sampling[J]. Journal of Applied Remote Sensing, 2017, 11(4): 1-13. DOI: .
doi: 10.1117/1.JRS.11.046023
40 Ping Yuepeng. Crop classification based on analysis of phenological characteristics of MODIS times serise[D]. Harbin: Harbin Normal University,2016.
40 平跃鹏. 基于MODIS时间序列地表物候特征分析及农作物分类[D]. 哈尔滨: 哈尔滨师范大学, 2016.
No Suggested Reading articles found!