Crown Structure Metrics to Generalize Aboveground Biomass Estimation Model Using Airborne Laser Scanning Data in National Park of Hainan Tropical Rainforest, China

Abstract

Forest aboveground biomass (AGB) is an important indicator for characterizing forest ecosystem structures and functions. Therefore, how to effectively investigate forest AGB is a vital mission. Airborne laser scanning (ALS) has been demonstrated as an effective way to support investigation and operational applications among a wide range of applications in the forest inventory. Moreover, three-dimensional structure information relating to AGB can be acquired by airborne laser scanning. Many studies estimated AGB from variables that were extracted from point cloud data, but few of them took full advantage of variables related to tree crowns to estimate the AGB. In this study, the main objective was to evaluate and compare the capabilities of different metrics derived from point clouds obtained from ALS. Particularly, individual tree-based alpha-shape, along with other traditional and commonly used plot-level height and intensity metrics, have been used from airborne laser scanning data. We took the random forest and multiple stepwise linear regression to estimate the AGB. By comparing AGB estimates with field measurements, our results showed that the best approach is mixed metrics, and the best estimation model is random forest (R2 = 0.713, RMSE = 21.064 t/ha, MAE = 15.445 t/ha), which indicates that alpha-shape may be a good alternative method to improve AGB estimation accuracy. This method provides an effective solution for estimating aboveground biomass from airborne laser scanning.

Biomass Estimation of Subtropical Arboreal Forest at Single Tree Scale Based on Feature Fusion of Airborne LiDAR Data and Aerial Images

“…Airborne point cloud data can easily extract features such as the vegetation height, density and topography, vertical structure, and canopy area [22][23][24] easily, which complement the vegetation index and texture features of images. It has been widely introduced into biomass estimation studies.…”

Estimating Crown Biomass in a Multilayered Fir Forest Using Airborne LiDAR Data

“…The RF is a non-parametric regression method that provides robustness and flexibility in modeling individual tree attributes with high accuracy [35]. Moreover, the RF algorithm has a significant advantage over the other machine learning algorithms, as it can effectively handle collinearity and nonlinear regression problems [52]. Overall, the results demonstrate that DB, NB and BB could be reliably estimated in a multilayered forest using the RF algorithm.…”

“…Most studies related to AGB modeling have used the correlation between LiDARderived metrics and in situ measurements [52], applying various regression methods, such as linear regression [53], random forest (RF) algorithm [11], artificial neural networks [54], support vector machines [33], nonparametric regression [55] and Gaussian process regression [56]. Specifically, [54] tested the effectiveness of different statistical approaches for AGB stock and change (∆AGB) estimation, using a plot-based approach, in a selectively logged tropical forest, reporting that the ordinary least squares model provided the most accurate estimations compared with the machine learning algorithms (i.e., RF, k-nearest neighbor, SVM and ANN).…”