Search

Forests, commonly viewed as the Earth's lungs, play a crucial role in mitigating greenhouse gas emissions, regulating the globe, and maintaining ecological equilibrium. The assessment of aboveground biomass (AGB) serves as a pivotal indicator for evaluating forest quality. By integrating remote sensing images with a small number of ground-measured samples to map, forest AGBs can significantly reduce time and labor costs. Current research mainly focuses on improving the accuracy of mapping forest AGBs, such as integrating multiple-sensors remote sensing data and models. However, due to uncertainties associated with remote sensing images and complexities inherent in forest structures, the accuracy of mapping forest AGBs is constrained by both the quantity and distribution of ground samples available. The development of transfer learning methods can fully utilize ground-based measurement data and enable the application of samples across regions and time. To evaluate the potential of transfer learning methods in mapping forest AGBs, this study conducted a spatial–temporal transfer of spectral variables (SVs) and prediction models (PMs) using a direct-push transfer method, and a new evaluation metric, relative change of R-squared (RCRS), was proposed to assess the transferability of SVs and PMs. The results showed that the transferability of SVs and PMs in the spatial target domain is obviously greater than that in the temporal target domain. Compared to the temporal target domain, the RCRS for transfer SVs in the spatial target domain was lower by 20.89 (oak) and 20.88 (Chinese fir) and for transfer PMs by 24.16 (oak) and 24.79 (Chinese fir). Tree species is also one of the main factors affecting the spatial and temporal transfer of SVs, and it is challenging to transfer SVs between different tree species. The results also show that nonparametric models have better generalization performance, and their transferability is much greater than that of parametric models. [ABSTRACT FROM AUTHOR]

Tree crown diameter (CD) values, relating to the rate of material exchange between the forest and the atmosphere, can be used to evaluate forest biomass and carbon stock. To map tree CD values using meter-level optical remote sensing images, we propose a novel method that interprets the relationships between the spectral reflectance of pixels and the CD. The approach employs the spectral reflectance of pixels in the tree crown to express the diversity of inclination angles of leaves based on the radiative transfer model and the spatial heterogeneity of these pixels. Then, simulated and acquired GF-2 images are applied to verify the relationships between spatial heterogeneity and the tree CD. Meanwhile, filter-based and object-based methods are also employed to extract three types of variables (spectral features, texture features, and spatial heterogeneity). Finally, the tree CD values are mapped by four models (random forest (RF), K-nearest neighbor (K-NN), support vector machine (SVM), and multiple linear regression (MLR)), using three single types of variables and combinations of variables with different strategies. The results imply that the spatial heterogeneity of spectral reflectance is significantly positively correlated with tree CD values and is more sensitive to tree CD values than traditional spectral features and textural features. Furthermore, the ability of spatial heterogeneity to map tree CD values is significantly higher than traditional variable sets after obtaining stable features with appropriate filter window sizes. The results also demonstrate that the accuracy of mapped tree CD values is significantly improved using combined variable sets with different feature extraction methods. For example, in our experiments, the R2 and rRMSE values of the optimal results ranged from 0.60 to 0.66, and from 15.76% to 16.68%, respectively. It is confirmed that spatial heterogeneity with high sensitivity can effectively map tree CD values, and the accuracy of mapping tree CD values can be greatly improved using a combination of spectral features extracted by an object-based method and spatial heterogeneity extracted by a filter-based method. [ABSTRACT FROM AUTHOR]