Search

Spectral features (SFs) and texture features (TFs) extracted from optical remote sensing images can capture the structural composition and growth information of forests, and combining remote sensing variables with a few ground measurement samples is a common method for mapping forest stock volume (FSV). However, the accuracy of mapping FSV using optical images with a high spatial resolution (one meter or sub-meters) is often lower than medium resolutions (larger than 10 m) using the same types of features and approaches. To overcome the limitations of high spatial resolution images in mapping FSV, down-scaled images with spatial resolution ranging from 1 to 30 m were obtained by GF-2 image to interpret the relationships between spatial resolutions of features and the accuracy of mapping FSV, and combination strategies of variables with various spatial resolutions were proposed to improve the accuracy of mapping FSV. The results show that the spatial resolution of features significantly affects the performance of employed models in estimating FSV, the sensitivity between SFs and FSV gradually increases with the decreasing of spatial resolution, and the optimal spatial resolutions of two types of features (SFs and TFs) are not synchronized in mapping forest FSV. After using combination strategies of variables with various spatial resolutions, the accuracy of mapping FSV is significantly higher than those derived from variable sets with the same spatial resolutions. It is proved that TFs derived from GF-2 images have great potential to improve the accuracy of mapping FSV, and the contribution of features depends on the approaches of extracting and combination strategies. [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]

Forest growing stem volume (GSV) is regarded as one of the most important parameters for the quality evaluation and dynamic monitoring of forest resources. The accuracy of mapping forest GSV is highly related to the employed models and involved remote sensing features, and the criteria of feature evaluation severely affect the performance of the employed models. However, due to the linear or nonlinear relationships between remote sensing features and GSV, widely used evaluation criteria inadequately express the complex sensitivity between forest GSV and spectral features, especially the saturation levels of features in a planted forest. In this study, novel feature evaluation criteria were constructed based on the Pearson correlations and optical saturation levels of the alternative remote sensing features extracted from two common optical remote sensing image sets (GF-1 and Sentinel-2). Initially, the spectral saturation level of each feature was quantified using the kriging spherical model and the quadratic model. Then, optimal feature sets were obtained with the proposed criteria and the linear stepwise regression model. Finally, four widely used machine learning models—support vector machine (SVM), multiple linear stepwise regression (MLR), random forest (RF) and K-neighborhood (KNN)—were employed to map forest GSV in a planted Chinese fir forest. The results showed that the proposed feature evaluation criteria could effectively improve the accuracy of estimating forest GSV and that the systematic distribution of errors between the predicted and ground measurements in the range of forest GSV was less than 300 m3/hm2. After using the proposed feature evaluation criteria, the highest accuracy of mapping GSV was obtained with the RF model for GF-1 images (R2 = 0.49, rRMSE = 28.67%) and the SVM model for Sentinel-2 images (R2 = 0.52, rRMSE = 26.65%), and the decreased rRMSE values ranged from 1.1 to 6.2 for GF-1 images (28.67% to 33.08%) and from 2.3 to 6.8 for Sentinel-2 images (26.85% to 33.28%). It was concluded that the sensitivity of the optimal feature set and the accuracy of the estimated GSV could be improved using the proposed evaluation criteria (less than 300 m3/hm2). However, these criteria were barely able to improve mapping accuracy for a forest with a high GSV (larger than 300 m3/hm2). [ABSTRACT FROM AUTHOR]