Please wait a minute...
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (2) : 215-223     DOI: 10.6046/zrzyyg.2021156
Classification of tropical natural forests in Hainan Island based on multi-temporal Landsat8 remote sensing images
ZHU Qi1,2(), GUO Huadong1,2, ZHANG Lu1,2,3(), LIANG Dong1,2, LIU Xuting1,2, WAN Xiangxing4
1. Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. Sanya Institute of Remote Sensing, Sanya 572029, China
4. Institute of Forest Resources Information Technique, Chinese Academy of Forestry, Beijing 100091, China
Download: PDF(4055 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

Tropical forests play a vital role in biodiversity conservation and research on global climate change. However, the complexity and diversity of vegetation types pose challenges to the fine remote sensing-based classification of tropical forests. The classification of tropical forests in the Jianfengling area, Hainan Province was analyzed using the multi-temporal Landsat8 data of the Google Earth Engine (GEE) platform. Based on the analysis of the impacts of the size and combination of multi-temporal data on the classification accuracy, this study proposed a classification method based on multi-temporal Landsat8 images for the vegetation type groups of tropical natural forests, such as typical tropical rain forest, tropical monsoon forest, and evergreen broad-leaved forests. The results are as follows. ① The classification accuracy of tropical natural forests was significantly improved as the size of multi-temporal data increased. The classification accuracy of the vegetation type groups of natural forests in Hainan Island reached 91%. ② When the multi-temporal data reached a certain size, the classification accuracy tended to be stable. Different combinations of multi-temporal data can improve the classification accuracy of tropical forests, especially when the classification accuracy of individual data involved was low. This finding reflects the broadness of the selection of temporal data. The proposed method, taking advantage of the temporal changes in remote sensing data, provides an effective reference for the remote sensing-based classification of tropical natural forests in Hainan Island.

Keywords classification of tropical forests      Google Earth Engine      support vector machine      temporal data      big earth data     
ZTFLH:  TP79  
Corresponding Authors: ZHANG Lu     E-mail:;
Issue Date: 20 June 2022
E-mail this article
E-mail Alert
Articles by authors
Huadong GUO
Xuting LIU
Xiangxing WAN
Cite this article:   
Qi ZHU,Huadong GUO,Lu ZHANG, et al. Classification of tropical natural forests in Hainan Island based on multi-temporal Landsat8 remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(2): 215-223.
URL:     OR
Fig.1  Location of the Jianfengling study area
Fig.2  Technical route of remote sensing classification of natural forests in Hainan Island based on temporal changes
Fig.3  Statistics of each band of Landsat8 OLI data
Fig.4  Statistics of vegetation index information
Fig.5  Time-phase spectral characteristic curve of typical features in 2018
Fig.6  Multi-band Landsat8 image classification result
Fig.7  Changes in the accuracy of monthly time series classification in 2018
Fig.8  Increase in OA and Kappa coefficients
NDVI 1.000 0 -0.731 9 -0.954 4 0.688 1 0.862 5 4.236 9
NDTI -0.731 9 1.000 0 0.696 7 -0.552 5 -0.659 0 3.640 0
LSWI -0.954 4 0.696 7 1.000 0 -0.494 5 -0.904 5 4.050 1
EVI 0.688 1 -0.552 5 -0.494 5 1.000 0 0.478 2 3.213 2
SAVI 0.862 5 -0.659 0 -0.904 5 0.478 2 1.000 0 3.904 3
Tab.1  Correlation of 5 vegetation indexes
Fig.9  Comparison of OA before and after the feature band selection
Fig.10  Accuracy of time series classification results
分组 原始平均分类结果 时序分类结果 增幅/% 分组 原始平均分类结果 时序分类结果 增幅/%
OA Kappa OA Kappa OA Kappa OA Kappa OA Kappa OA Kappa
a 0.705 9 0.548 4 0.789 1 0.685 6 11.78 25.02 c 0.658 1 0.471 7 0.801 4 0.695 5 21.77 47.45
b 0.567 4 0.328 2 0.721 5 0.547 7 27.15 66.88 d 0.655 6 0.469 4 0.844 6 0.739 7 28.83 57.58
Tab.2  Accuracy change of time series image classification
Fig.11  Classification results of natural forests in Jianfengling, Hainan Island
[1] Aragao L, Poulter B, Barlow J, et al. Environmental change and the carbon balance of Amazonian forests[J]. Biological Reviews, 2014, 89(4):913-931.
doi: 10.1111/brv.12088 url:
[2] Finer M, Babbitt B, Novoa S, et al. Future of oil and gas development in the western Amazon[J]. Environmental Research Letters, 2015, 10(2):024003.
doi: 10.1088/1748-9326/10/2/024003 url:
[3] 邓燔, 陈秋波, 刘建波. 海南省热带天然林保护和补偿现状及缺陷分析[J]. 热带农业科学, 2007, 27(2):72-76.
[3] Deng F, Chen Q B, Liu J B. Analysis of the status quo and deficiencies of the protection and compensation of tropical natural forests in Hainan Province[J]. Chinese Journal of Tropical Agriculture, 2007, 27(2):72-76.
[4] Lawrence D, Vandecar K. Effects of tropical deforestation on climate and agriculture[J]. Nature Climate Change, 2015, 5(1):27-36.
doi: 10.1038/nclimate2430 url:
[5] Kalamandeen M, Gloor E, Mitchard E, et al. Pervasive rise of small-scale deforestation in Amazonia[J]. Scientific Reports, 2018, 8(1):1-10.
[6] 陈新云, 李利伟, 刘承芳, 等. 热带原始森林类型分类和蓄积量遥感反演研究[J]. 林业资源管理, 2019, 28(2):39.
[6] Chen X Y, Li L W, Liu C F, et al. Research on classification of tropical primeval forest types and stock volume remote sensing inversion[J]. Forest Resources Management, 2019, 28(2):39.
[7] 田庆久, 闵祥军. 植被指数研究进展[J]. 地球科学进展, 1998, 13(4):327-333.
[7] Tian Q J, Min X J. Research progress in vegetation index[J]. Advances in Earth Science, 1998, 13(4):327-333.
[8] Homer C, Dewitz J, Fry J, et al. Completion of the 2001 national land cover database for the counterminous United States[J]. Photogrammetric Engineering and Remote Sensing, 2007, 73(4):337.
[9] Merchant J W. Remote sensing of the environment:An earth resource perspective[J]. Cartography and Geographic Information Science, 2000, 27(4):311.
doi: 10.1559/152304000783547768 url:
[10] Gómez C, White J C, Wulder M A. Optical remotely sensed time series data for land cover classification:A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116:55-72.
doi: 10.1016/j.isprsjprs.2016.03.008 url:
[11] Jamali S, Jönsson P, Eklundh L, et al. Detecting changes in vegetation trends using time series segmentation[J]. Remote Sensing of Environment, 2015, 156:182-195.
doi: 10.1016/j.rse.2014.09.010 url:
[12] Senf C, Leitão P J, Pflugmacher D, et al. Mapping land cover in complex Mediterranean landscapes using Landsat:Improved classification accuracies from integrating multi-seasonal and synthetic imagery[J]. Remote Sensing of Environment, 2015, 156:527-536.
doi: 10.1016/j.rse.2014.10.018 url:
[13] Wang J, Zhao Y, Li C, et al. Mapping global land cover in 2001 and 2010 with spatial-temporal consistency at 250 m resolution[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 103:38-47.
doi: 10.1016/j.isprsjprs.2014.03.007 url:
[14] Shimabukuro Y E, Beuchle R, Grecchi R C, et al. Assessment of forest degradation in Brazilian Amazon due to selective logging and fires using time series of fraction images derived from Landsat ETM+ images[J]. Remote Sensing Letters, 2014, 5(9):773-782.
doi: 10.1080/2150704X.2014.967880 url:
[15] Pouliot D, Latifovic R, Zabcic N, et al. Development and assessment of a 250 m spatial resolution MODIS annual land cover time series (2000—2011) for the forest region of Canada derived from change-based updating[J]. Remote Sensing of Environment, 2014, 140:731-743.
doi: 10.1016/j.rse.2013.10.004 url:
[16] 陈焕镛. 海南植物志[M]. 北京: 科学出版社, 1964:338.
[16] Chen H Y. Flora of Hainan[M]. Beijing: Science Press, 1964:338.
[17] 李意德. 海南岛尖峰岭热带山地雨林的群落结构特征[J]. 热带亚热带植物学报, 1997, 5(1):18-26.
[17] Li Y D. Community structure characteristics of tropical mountain rainforest in Jianfengling Hainan Island[J]. Journal of Tropical and Subtropical Botany, 1997, 5(1):18-26.
[18] 盛大勇, 庄雪影, 许涵, 等. 尖峰岭热带山地雨林海南特有木本植物群落结构[J]. 植物生态学报, 2012, 36(9):935.
[18] Sheng D Y, Zhuang X Y, Xu H, et al. Community structure of endemic woody plants in the tropical mountain rain forest of Jianfengling in Hainan[J]. Chinese Journal of Plant Ecology, 2012, 36(9):935.
doi: 10.3724/SP.J.1258.2012.00935 url:
[19] Chambers J Q, Tribuzy E S, Toledo L C, et al. Respiration from a tropical forest ecosystem:Partitioning of sources and low carbon use efficiency[J]. Ecological Applications, 2004, 14(s4):72-88.
doi: 10.1890/01-6012 url:
[20] 王伯荪, 彭少麟, 郭泺, 等. 海南岛热带森林景观类型多样性[J]. 生态学报, 2007, 27(5):1690-1695.
[20] Wang B S, Peng S L, Guo L, et al. Diversity of tropical forest landscape types in Hainan Island[J]. Acta Ecologica Sinica, 2007, 27(5):1690-1695.
doi: 10.1016/S1872-2032(07)60040-7 url:
[21] Chander G, Markham B L, Helder D L. Summary of current radiometric calibration coefficients for Landsat MSS,TM,ETM+,and EO-1 ALI sensors[J]. Remote Sensing of Environment, 2009, 113(5):893-903.
doi: 10.1016/j.rse.2009.01.007 url:
[22] Oreopoulos L, Wilson M J, Várnai T. Implementation on Landsat data of a simple cloud-mask algorithm developed for MODIS land bands[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(4):597-601.
doi: 10.1109/LGRS.2010.2095409 url:
[23] 张滔, 唐宏. 基于Google Earth Engine的京津冀2001—2015年植被覆盖变化与城镇扩张研究[J]. 遥感技术与应用, 2018, 33(4):593-599.
[23] Zhang T, Tang H. Beijing-Tianjin-Hebei 2001—2015 based on Google Earth Engine vegetation cover change and urban expansion[J]. Remote Sensing Technology and Application, 2018, 33(4):593-599.
[24] 宋永昌. 对中国植被分类系统的认知和建议[J]. 植物生态学报, 2011, 35(8):882.
doi: 10.3724/SP.J.1258.2011.00882
[24] Song Y C. Cognition and suggestions on China’s vegetation classification system[J]. Chinese Journal of Plant Ecology, 2011, 35(8):882.
doi: 10.3724/SP.J.1258.2011.00882 url:
[25] Zhang L, Wan X, Sun B. Tropical natural forest classification using time-series Sentinel-1 and Landsat-8 images in Hainan Island[C]// IEEE International Geoscience and Remote Sensing Symposium, 2019:6732-6735.
[26] Cherkassky V, Ma Y. Practical selection of SVM parameters and noise estimation for SVM regression[J]. Neural Networks, 2004, 17(1):113-126.
pmid: 14690712
[1] LI Zhixin, WANG Mengfei, JIA Weijie, JI Song, WANG Yufei. A method for identifying the number of building floors based on shadow information[J]. Remote Sensing for Natural Resources, 2023, 35(3): 97-106.
[2] YU Sen, JIA Mingming, CHEN Gao, LU Yingying, LI Yi, ZHANG Bochun, LU Chunyan, LI Huiying. A study of the disturbance to mangrove forests in Dongzhaigang, Hainan based on LandTrendr[J]. Remote Sensing for Natural Resources, 2023, 35(2): 42-49.
[3] ZHU Lin, HUANG Yuling, YANG Gang, SUN Weiwei, CHEN Chao, HUANG Ke. Information extraction and spatio-temporal evolution analysis of the coastline in Hangzhou Bay based on Google Earth Engine and remote sensing technology[J]. Remote Sensing for Natural Resources, 2023, 35(2): 50-60.
[4] CHEN Huixin, CHEN Chao, ZHANG Zili, WANG Liyan, LIANG Jintao. A remote sensing information extraction method for intertidal zones based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2022, 34(4): 60-67.
[5] LI Yi, CHENG Lina, LU Yingying, ZHANG Bochun, YU Sen, JIA Mingming. A study on the changes in coastal tidal flats in the Laizhou Bay based on MSIC and OTSU[J]. Remote Sensing for Natural Resources, 2022, 34(4): 68-75.
[6] WANG Chunxia, ZHANG Jun, LI Yixu, PHOUMILAY. The construction and verification of a water index in the complex environment based on GF-2 images[J]. Remote Sensing for Natural Resources, 2022, 34(3): 50-58.
[7] DENG Jingwen, TIAN Yichao, ZHANG Qiang, TAO Jin, ZHANG Yali, HUANG Shengguang. Application of airborne LiDAR in the estimation of the mean height of mangrove stand[J]. Remote Sensing for Natural Resources, 2022, 34(3): 129-137.
[8] LUO Hongjian, MING Dongping, XU Lu. Time series calculation of remote sensing ecological index based on GEE[J]. Remote Sensing for Natural Resources, 2022, 34(2): 271-277.
[9] SUN Xiao, PENG Junhuan, ZHAO Feng, WANG Xiaoyang, LYU Jie, ZHANG Dengfeng. Principal component selection method for hyperspectral remote sensing images based on spatial statistics[J]. Remote Sensing for Natural Resources, 2022, 34(2): 37-46.
[10] FANG Mengyang, LIU Xiaohuang, KONG Fanquan, LI Mingzhe, PEI Xiaolong. A method for creating annual land cover data based on Google Earth Engine: A case study of the Yellow River basin[J]. Remote Sensing for Natural Resources, 2022, 34(1): 135-141.
[11] ZHENG Xiucheng, ZHOU Bin, LEI Hui, HUANG Qiyu, YE Haolin. Extraction and spatio-temporal change analysis of the tidal flat in Cixi section of Hangzhou Bay based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2022, 34(1): 18-26.
[12] YAO Jinxi, ZHANG Zhi, ZHANG Kun. An analysis of the characteristics, causes, and trends of spatio-temporal changes in vegetation in the Nuomuhong alluvial fan based on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2022, 34(1): 249-256.
[13] LAI Peiyu, HUANG Jing, HAN Xujun, MA Mingguo. An analysis of impacts from water impoundment in Three Gorges Dam Project on surface water in Chongqing area base on Google Earth Engine[J]. Remote Sensing for Natural Resources, 2021, 33(4): 227-234.
[14] FENG Dongdong, ZHANG Zhihua, SHI Haoyue. Fine extraction of urban villages in provincial capitals based on multivariate data[J]. Remote Sensing for Natural Resources, 2021, 33(3): 272-278.
[15] YE Wantong, CHEN Yihong, LU Yinhao, Wu Penghai. Spatio-temporal variation of land surface temperature and land cover responses in different seasons in Shengjin Lake wetland during 2000—2019 based on Google Earth Engine[J]. Remote Sensing for Land & Resources, 2021, 33(2): 228-236.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech