Integrating Airborne LiDAR and Optical Data to Estimate Forest Aboveground Biomass in Arid and Semi-Arid Regions of China

Abstract

Forest Aboveground Biomass (AGB) is a key parameter for assessing forest productivity and global carbon content. In previous studies, AGB has been estimated using various prediction methods and types of remote sensing data. Increasingly, there is a trend towards integrating various data sources such as Light Detection and Ranging (LiDAR) and optical data. In this study, we constructed and compared the accuracies of five models for estimating AGB of forests in the upper Heihe River Basin in Northwest China. The five models were constructed using field and remotely-sensed data (optical and LiDAR) and algorithms including Random Forest (RF), Support Vector Machines (SVM), Back Propagation Neural Networks (BPNN), K-Nearest Neighbor (KNN) and the Generalized Linear Mixed Model (GLMM). Models based on the RF algorithm emerged as being the best among the five algorithms irrespective of the datasets used. The Random Forest AGB model, using only LiDAR data (R 2 = 0.899, RMSE = 14.0 t/ha) as the input data, was more effective than the one using optical data (R 2 = 0.835, RMSE = 22.724 t/ha). Compared to LiDAR or optical data alone, the AGB model (R 2 = 0.913, RMSE = 13.352 t/ha) that used the RF algorithm and integrated LiDAR and optical data was found to be optimal. Incorporation of terrain variables with optical data resulted in only slight improvements in accuracy. The models developed in this study could be useful for using integrated airborne LiDAR and passive optical data to accurately estimate forest biomass.

Analyzing the Uncertainty of Estimating Forest Aboveground Biomass Using Optical Imagery and Spaceborne LiDAR

“…Among the three nonparametric algorithms in this study, GPs generated suboptimal predicted results in terms of R 2 , RMSE, and relative error. The SVM showed the least favorable accuracy, which is consistent with the conclusions from recent studies [59,60].…”

Estimation of Forest Above-Ground Biomass by Geographically Weighted Regression and Machine Learning with Sentinel Imagery

“…The evaluation of the forest AGB mapping results by the four models was insufficient for this study as we were limited by the sample size. Future verification work should be conducted; this is conventionally done by independent sample sets or by acknowledged high-accuracy results such as airborne data, especially unmanned aerial vehicle LiDAR data [17,97].…”

“…Similarly, previous researchers have used these four methods to estimate forest AGB and achieve good accuracies, while results of the models' comparison vary compared with this study. Cao et al (2018), integrating airborne LiDAR and optical data, compared the accuracies of forest AGB models in the upper Heihe River Basin in northwest China, and found that RF was the best (R 2 = 0.9, RMSE = 13.4 Mg·ha −1 ), following by ANN and SVR [17]. Based on Landsat satellite imagery, Wu et al (2016) implemented the optimal spatial forest AGB estimation in northwestern Zhejiang Province, China, and RF (R 2 = 0.6, RMSE = 26.4 Mg·ha −1 ) also performed better than SVR [11].…”

“…Various types of remote-sensing data are used for forest biomass estimation such as optical sensor data, radio detection and ranging (radar) data, and light detection and ranging (LiDAR) data, with each one having certain advantages over the others [14,15]. Optical sensors were first applied to retrieve the horizontal forest structure and AGB assessments through field sampling, due to their aggregate spectral signatures (reflectance or vegetation indices) with global coverage, repetitiveness, and cost-effectiveness [16,17]. Optical remote sensing data from a number of platforms, such as IKONOS, Quickbird, Worldview, ZY-3, systeme probatoire d'observation de la terre (SPOT), Sentinel, Landsat, and moderate-resolution imaging spectroradiometer (MODIS), with spatial resolutions varying from less than one meter to hundreds of meters, have been used by numerous researchers for biomass estimation [18][19][20].…”

Peer Review #2 of "Estimation of maize above-ground biomass based on stem-leaf separation strategy integrated with LiDAR and optical remote sensing data (v0.2)"

“…It works with UAV platforms and provides accurate three-dimensional structural information of the vegetation canopy (Wallace et al 2014). It provides rapid and nondestructive estimates of structural information, such as height, volume, leaf area index, and leaf area density of vegetation, which can resolve the problem of spectral saturation that occurs in optical remote sensing (Cao et al 2018;Du et al 2016;Luo et al 2018;Tagarakis et al 2018). Unlike manned aircraft, UAVs are being increasingly used to provide detailed, high-resolution imagery and associated digital elevation models (DEMs) for surface processes and geomorphological research (James & Robson 2014).…”