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

• Published in: International journal of applied earth observation and geoinformation Vol. 92; p. 102163
• Main Authors: Li, Wang, Niu, Zheng, Shang, Rong, Qin, Yuchu, Wang, Li, Chen, Hanyue
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2020; Elsevier
• Subjects: artificial intelligence; biodiversity; canopy height; carbon sequestration; Deep-learning; forest canopy; Forest canopy height; forests; ICESat-2; Landsat; Landsat-8; lidar; Machine-learning; mountains; prediction; Random forest; regression analysis; remote sensing; Sentinel-1; Sentinel-2; spatial data; Landsat-8; Forest canopy height; Deep-learning; ICESat-2; Sentinel-1; Sentinel-2; Random forest; Machine-learning
• ISSN: 1569-8432; 1872-826X
• DOI: 10.1016/j.jag.2020.102163

•A machine-learning based high-resolution mapping workflow was proposed.•Canopy height product from ICESat-2 satellite was validated by airborne LiDAR data.•Deep-learning and random forest models were used to upscale ICESat-2 canopy height.•Sentinel-2 and Landsat-8 data were compared in the prediction of forest height.•Sentinel-1 & -1 satellites showed high capacity on the prediction of forest height. 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 (Hcanopy) footprint product from ICESat-2 with the Sentinel-1 and Sentinel-2 satellite data. The ICESat-2 Hcanopy 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 Hcanopy 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 Hcanopy assisted by Sentinel satellite co-variables with an R-value between the observed and predicted Hcanopy equalling 0.78 and 0.68, respectively. Compared to Sentinel satellites, Landsat-8 showed relatively weaker performance in Hcanopy 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.