Remote Sensing Estimation of Bamboo Forest Aboveground Biomass Based on Geographically Weighted Regression

Abstract

Bamboo forests are widespread in subtropical areas and are well known for their rapid growth and great carbon sequestration ability. To recognize the potential roles and functions of bamboo forests in regional ecosystems, forest aboveground biomass (AGB)—which is closely related to forest productivity, the forest carbon cycle, and, in particular, carbon sinks in forest ecosystems—is calculated and applied as an indicator. Among the existing studies considering AGB estimation, linear or nonlinear regression models are the most frequently used; however, these methods do not take the influence of spatial heterogeneity into consideration. A geographically weighted regression (GWR) model, as a spatial local model, can solve this problem to a certain extent. Based on Landsat 8 OLI images, we use the Random Forest (RF) method to screen six variables, including TM457, TM543, B7, NDWI, NDVI, and W7B6VAR. Then, we build the GWR model to estimate the bamboo forest AGB, and the results are compared with those of the cokriging (COK) and orthogonal least squares (OLS) models. The results show the following: (1) The GWR model had high precision and strong prediction ability. The prediction accuracy (R2) of the GWR model was 0.74, 9%, and 16% higher than the COK and OLS models, respectively, while the error (RMSE) was 7% and 12% lower than the errors of the COK and OLS models, respectively. (2) The bamboo forest AGB estimated by the GWR model in Zhejiang Province had a relatively dense spatial distribution in the northwestern, southwestern, and northeastern areas. This is in line with the actual bamboo forest AGB distribution in Zhejiang Province, indicating the potential practical value of our study. (3) The optimal bandwidth of the GWR model was 156 m. By calculating the variable parameters at different positions in the bandwidth, close attention is given to the local variation law in the estimation of the results in order to reduce the model error.

Differential characteristics and driving forces of the spatial distribution of heritage trees in Luoyang, an ancient capital of China

“…The GWR model provided each spatial position with a regression coefficient, which was unattainable using the ordinary least squares (OLS) model. Regression analysis performed using the GWR model was used to select the center point and standard distance in each selected area to determine whether different regression coefficients can be acquired (Wang et al, 2021). Hence, the regression coefficient was not calculated using a constant value.…”

“…3) Regarding the relationship between influencing factors and the spatial distribution of heritage trees, most of the existing studies were carried out by qualitative induction or simple quantitative regression analysis (Zhang et al, 2017;Liu et al, 2019). Nevertheless, trees and their communities have certain spatial autocorrelation and heterogeneity (Wang et al, 2021). Therefore, various influencing factors of the distribution of heritage trees are spatially unbalanced.…”

Spatial–Temporal Variations of the Gross Ecosystem Product under the Influence of the Spatial Spillover Effect of Urbanization and Ecological Construction in the Yangtze River Delta Region of China

“…The geographically weighted regression model (GWR) is widely recognized as one of the most effective methods for addressing spatial heterogeneity [52]. There are significant differences in urbanization development and ecological construction in different counties, meaning that the impacts of urbanization and ecological construction indicators on the GEP are spatial-temporal heterogeneous in different counties and in different development periods.…”

Prediction of Urban Forest Aboveground Carbon Using Machine Learning Based on Landsat 8 and Sentinel-2: A Case Study of Shanghai, China

“…The texture features are based on the original image waveform. The texture features (i.e., mean, variance, homogeneity, contrast, dissimilarity, entropy, angular second-order moment, and correlation) are based on the original image bands calculated using the grayscale co-occurrence matrix [39]. The window size for texture feature extraction is set to 3 × 3, 5 × 5, 7 × 7, 9 × 9, and 11 × 11.…”