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

Abstract

Accurate forest above-ground biomass (AGB) is crucial for sustaining forest management and mitigating climate change to support REDD+ (reducing emissions from deforestation and forest degradation, plus the sustainable management of forests, and the conservation and enhancement of forest carbon stocks) processes. Recently launched Sentinel imagery offers a new opportunity for forest AGB mapping and monitoring. In this study, texture characteristics and backscatter coefficients of Sentinel-1, in addition to multispectral bands, vegetation indices, and biophysical variables of Sentinal-2, based on 56 measured AGB samples in the center of the Changbai Mountains, China, were used to develop biomass prediction models through geographically weighted regression (GWR) and machine learning (ML) algorithms, such as the artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that texture characteristics and vegetation biophysical variables were the most important predictors. SVR was the best method for predicting and mapping the patterns of AGB in the study site with limited samples, whose mean error, mean absolute error, root mean square error, and correlation coefficient were 4 × 10 −3 , 0.07, 0.08 Mg·ha −1 , and 1, respectively. Predicted values of AGB from four models ranged from 11.80 to 324.12 Mg·ha −1 , and those for broadleaved deciduous forests were the most accurate, while those for AGB above 160 Mg·ha −1 were the least accurate. The study demonstrated encouraging results in forest AGB mapping of the normal vegetated area using the freely accessible and high-resolution Sentinel imagery, based on ML techniques.Traditional field-based measurements provide the most accurate AGB values, but they are destructive and spatially limited [10,11]. Uncertainty and bias in field measurements obviously exist, particularly those with large trees and tropical issues [4,5]. Combining remote sensing and sample plot data has become a popular method to generate spatially explicit estimations of forest AGB [12,13]. 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]. However, the widespread usage of optical data is limited...

A Generalized Model of Complex Allometry I: Formal Setup, Identification Procedures and Applications to Non-Destructive Estimation of Plant Biomass Units

“…Concomitantly important is the adaptation of methods aimed at non-destructive estimation. For instance, aboveground tree biomass in forest ecosystems has been estimated through remote sensing protocols [7][8][9][10]. Nevertheless, a number of factors such as sample size, weather, complexity of biophysical settings, study area scale, software, or spatial resolution can induce uncertainty of remote-sensed estimation [11][12][13][14][15].…”

Remote Sensing Technology Applications in Forestry and REDD+

“…This Special Issue contains 12 studies that provided insight into new advances in the field of remote sensing for forest management and REDD+. This included developments into (1) algorithm development using satellite data [10][11][12][13][14][15][16]; (2) synthetic aperture radar (SAR) [11,17];…”

“…(3) airborne [18] and terrestrial [19,20] LiDAR; and (4) forest reference emissions level (FREL) frameworks [21]. Chen et al [11] combine texture characteristics and backscatter coefficients of Sentinel-1 with multispectral information derived from Sentinel-2 and traditional field inventory data to develop above-ground biomass (AGB) prediction models using machine learning. Shen et al [12] apply machine learning techniques, using Landsat-5 Thematic Mapper (TM) and Landsat-8 Operational Land Imager (OLI) images to monitor the five-year change in AGB over three regions with different topographic conditions in Zhejiang Province, China.…”

“…Random forest (RF) has been the most popular machine learning algorithm to link remote sensing data to forest structural attributes such as AGB [11,12], canopy cover [10] or forest fire susceptibility [15]. Spracklen and Spracklen [14] apply RF to identify old-growth forests using remote sensing data.…”

“…Spracklen and Spracklen [14] apply RF to identify old-growth forests using remote sensing data. Chen et al [11] and Gigovic et al [15] test different machine learning approaches for predicting AGB. Whereas Chen et al [11] identify that RF was not always the most suitable method for predicting and mapping AGB, Gigovic et al [15] obtain comparable results between RF and support vector machine approaches.…”