Estimation of Forest Canopy Cover by Combining ICESat-2/ATLAS Data and Geostatistical Method/Co-Kriging
Jinge Yu, Hongyan Lai, Li Xu, Shaolong Luo, Wenwu Zhou, Hanyue Song, Lei Xi, Qingtai Shu
Abstract
Accurately estimating forest canopy cover (FCC) is challenging by using traditional remote sensing images at regional level due to the spectral saturation phenomenon. In this study, to improve the estimation accuracy, a new method of FCC wall-to-wall mapping was suggested based on ICESat-2/ATLAS (Ice, Cloud, and land Elevation Satellite/Advanced Topographic Laser Altimeter System) data. Specifically, one data set of FCC's observations was combined with pre-processed ATLAS data and topographic factor to build a random forest regression (RFR) model. Moreover, the Co-Kriging method was used to generate spatially explicit values that are required by the RFR from the point data of ATLAS parameters, and then the wall-to-wall mapping of the FCC was conducted. The results showed the RFR model had an accuracy of relative root mean square error (rRMSE) = 0.09 with coefficient of determination (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) = 0.91. The best-fit semi-variogram models between primary variables and covariates were asr & TR (Model: Gaussian model, R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.94, the residual sum of squares (RSS) = 1.73×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-6</sup> ), landsat_perc & NDVI (Model: spherical model, R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.46, RSS = 1.58×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-4</sup> ), and photon_rate_can & slope (Model: exponential model, R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.77, RSS = 6.45×10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-4</sup> ), respectively. FCC validation result showed that the FCC's wall-to-wall mapping was in great agreement with the dataset-2 (R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.79; rRMSE = 0.11).