Predicting the Forest Canopy Height from LiDAR and Multi-Sensor Data Using Machine Learning over India

Abstract

Forest canopy height estimates, at a regional scale, help understand the forest carbon storage, ecosystem processes, the development of forest management and the restoration policies to mitigate global climate change, etc. The recent availability of the NASA’s Global Ecosystem Dynamics Investigation (GEDI) LiDAR data has opened up new avenues to assess the plant canopy height at a footprint level. Here, we present a novel approach using the random forest (RF) for the wall-to-wall canopy height estimation over India’s forests (i.e., evergreen forest, deciduous forest, mixed forest, plantation, and shrubland) by employing the high-resolution top-of-the-atmosphere (TOA) reflectance and vegetation indices, the synthetic aperture radar (SAR) backscatters, the topography and tree canopy density, as the proxy variables. The variable importance plot indicated that the SAR backscatters, tree canopy density and the topography are the most influential height predictors. 33.15% of India’s forest cover demonstrated the canopy height <10 m, while 44.51% accounted for 10–20 m and 22.34% of forests demonstrated a higher canopy height (>20 m). This study advocates the importance and use of GEDI data for estimating the canopy height, preferably in data-deficit mountainous regions, where most of India’s natural forest vegetation exists.

Forest Canopy Height Estimation by Integrating Structural Equation Modeling and Multiple Weighted Regression

“…We divided the training and test sets randomly in the ratio of 0.9:0.1 for the training and accuracy evaluation of the forest canopy height estimation [40]. The land and vegetation height (ATL08) product is derived from publicly available data from the National Snow and Ice Data Center (https://nsidc.org/data, accessed on 17 April 2023) [41][42][43]. The data were obtained from a 17-m diameter footprint acquired by a laser pulse.…”

A Novel ICESat-2 Signal Photon Extraction Method Based on Convolutional Neural Network

“…In terms of shallow sea bathymetry inversion, photon data can offer numerous high-precision and extensive coverage bathymetric control points [2][3][4][5][6][7]. Additionally, in forested areas, photon data are also a reliable source for canopy height information over large regions, which is conducive to various studies such as surface biomass estimation [8][9][10][11][12]. In urban areas, photon data can also be utilized to provide information about the height of urban buildings, which assists in the detection of changes in urban areas [13,14].…”