High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data

doi:10.1016/j.jag.2020.102163

	High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data
	Li, Wang 1,2; Niu, Zheng 1,3; Shang, Rong 4; Qin, Yuchu 1; Wang, Li 1; Chen, Hanyue 5
刊名	INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
	2020-10-01
卷号	92 页码:14
关键词	Forest canopy height ICESat-2 Sentinel-1 Sentinel-2 Landsat-8 Machine-learning Deep-learning Random forest
ISSN号	1569-8432
DOI	10.1016/j.jag.2020.102163
通讯作者	Li, Wang(lwwhdz@sina.com) ; Shang, Rong(shangr@lreis.ac.cn)
英文摘要	Forest canopy height is an important indicator of forest carbon storage, productivity, and biodiversity. The present study showed the first attempt to develop a machine-learning workflow to map the spatial pattern of the forest canopy height in a mountainous region in the northeast China by coupling the recently available canopy height (H-canopy) footprint product from ICESat-2 with the Sentinel-1 and Sentinel-2 satellite data. The ICESat-2 H-canopy was initially validated by the high-resolution canopy height from airborne LiDAR data at different spatial scales. Performance comparisons were conducted between two machine-learning models - deep learning (DL) model and random forest (RF) model, and between the Sentinel and Landsat-8 satellites. Results showed that the ICESat-2 H-canopy showed the highest correlation with the airborne LiDAR canopy height at a spatial scale of 250 m with a Pearson's correlation coefficient (R) of 0.82 and a mean bias of -1.46 m, providing important evidence on the reliability of the ICESat-2 vegetation height product from the case in China's forest. Both DL and RF models obtained satisfactory accuracy on the upscaling of ICESat-2 H-canopy assisted by Sentinel satellite co-variables with an R-value between the observed and predicted H-canopy equalling 0.78 and 0.68, respectively. Compared to Sentinel satellites, Landsat-8 showed relatively weaker performance in H-canopy prediction, suggesting that the addition of the backscattering coefficients from Sentinel-1 and the red-edge related variables from Sentinel-2 could positively contribute to the prediction of forest canopy height. To our knowledge, few studies have demonstrated large-scale vegetation height mapping in a resolution <= 250 m based on the newly available satellites (ICESat-2, Sentinel-1 and Sentinel-2) and DL regression model, particularly in the forest areas in China. Thus, the present work provided a timely and important supplementary to the applications of these new earth observation tools.
资助项目	China Natural Science Foundation[41701392] ; China Natural Science Foundation[41730107] ; China Natural Science Foundation[41871347] ; China Natural Science Foundation[41401399] ; Youth Innovation Promotion Association Chinese Academy of Sciences[2018084] ; China's Special Funds for Major State Basic Research Project[2013CB733405] ; 100 Talents Program of the Chinese Academy of Sciences[2018YFC0506901] ; National Key R&D Program of China[2018YFC0506901] ; national 863 program Comprehensive campaign and application demonstration of high-resolution SAR remote sensing project[2011AA120405]
WOS关键词	ABOVEGROUND BIOMASS ; VEGETATION INDEX ; AIRBORNE LIDAR ; CARBON STOCKS ; COVER ; LAND ; CLASSIFICATION ; PERFORMANCE ; COMPOSITES ; HABITAT
WOS研究方向	Remote Sensing
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000550572100008
资助机构	China Natural Science Foundation ; Youth Innovation Promotion Association Chinese Academy of Sciences ; China's Special Funds for Major State Basic Research Project ; 100 Talents Program of the Chinese Academy of Sciences ; National Key R&D Program of China ; national 863 program Comprehensive campaign and application demonstration of high-resolution SAR remote sensing project
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/158340]
专题	中国科学院地理科学与资源研究所
通讯作者	Li, Wang; Shang, Rong
作者单位	1.Chinese Acad Sci, Aerosp Informat Res Inst, State Key Lab Remote Sensing Sci, POB 9718,20 Datun Rd,Olymp Sci & Technol Pk CAS, Beijing 100101, Peoples R China 2.Aarhus Univ, Ctr Biodivers Dynam Changing World BIOCHANGE, Ny Munkegade 114, DK-8000 Aarhus C, Denmark 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, 11A Datun Rd, Beijing 100101, Peoples R China 5.Fujian Agr & Forestry Univ, Coll Resource & Environm Sci, Fuzhou 350002, Peoples R China
推荐引用方式 GB/T 7714	Li, Wang,Niu, Zheng,Shang, Rong,et al. High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data[J]. INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,2020,92:14.
APA	Li, Wang,Niu, Zheng,Shang, Rong,Qin, Yuchu,Wang, Li,&Chen, Hanyue.(2020).High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data.INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION,92,14.
MLA	Li, Wang,et al."High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data".INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 92(2020):14.