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
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.
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
[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
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
[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.
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.
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
[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
[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
[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
[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
[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
[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
[16]
陈焕镛. 海南植物志[M]. 北京: 科学出版社, 1964:338.
Chen H Y. Flora of Hainan[M]. Beijing: Science Press, 1964:338.
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.
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
[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
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
[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
[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
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.
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
[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