Search

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]

Labeled as a fast-growing tree species, eucalyptus has outstanding carbon sequestration capacity. Forest stock volume (FSV) is regarded as an important parameter for evaluating the quality of planted eucalyptus forests. However, it is an intractable problem to map FSV of planted eucalyptus forests using optical images because of growth characteristics of the crown and low saturation levels. To improve the accuracy of FSV in planted eucalyptus forests, time series Landsat 8 OLI (LC8) images and ZY-3 stereo images were acquired in the study area. Additionally, then, three composite images were proposed using acquired Landsat 8 OLI images based on the size and shape of eucalyptus crowns, and several spectra variables were extracted from these composite images. Furthermore, corrected canopy height model (CCHM) was also extracted from ZY-3 stereo images. Meanwhile, four models (random forest (RF), support vector machine (SVM), K-nearest neighbor (KNN), and multiple linear regression (MLR)) were used to estimate the FSV with various variable sets using the importance of the alternative variables ranked by RF. The results show that the sensitivity between proposed spectral variables and FSV is significantly improved using proposed composed images based on the growth characteristics of the crown, especially for young eucalyptus forests. After adding CCHM and stand age to the optimal variable set, the average relative root mean square error (rRMSE) of estimated FSV decreased from 41.01% to 29.94% for single LC8 images and from 32.64% to 26.47% for proposed composite LC8 images, respectively. After using the variable set extracted from composite LC8 images, the number of samples with overestimated FSV was significantly decreased for the young forest. Furthermore, forest height plays an important role in improving the accuracy of mapping FSV, whether young or mature eucalyptus forest. It was also proved that composite images related to crown close and CCHM have great potential to delay the saturation phenomenon for mapping FSV in planted eucalyptus forest. [ABSTRACT FROM AUTHOR]

Remote sensing technology is becoming mainstream for mapping the growing stem volume (GSV) and overcoming the shortage of traditional labor-consumed approaches. Naturally, the GSV estimation accuracy utilizing remote sensing imagery is highly related to the variable selection methods and algorithms. Thus, to reduce the uncertainty caused by variables and models, this paper proposes a combined strategy involving improved variable selection with the collinearity test and the secondary ensemble algorithm to obtain the optimally combined variables and extract a reliable GSV from several base models. Our study extracted four types of alternative variables from the Sentinel-1A and Sentinel-2A image datasets, including vegetation indices, spectral reflectance variables, backscattering coefficients, and texture features. Then, an improved variable selection criterion with the collinearity test was developed and evaluated based on machine learning algorithms (classification and regression trees (CART), k-nearest neighbors (KNN), support vector regression (SVR), and artificial neural network (ANN)) considering the correlation between variables and GSV (with random forest (RF), distance correlation coefficient (DC), maximal information coefficient (MIC), and Pearson correlation coefficient (PCC) as evaluation metrics), and the collinearity among the variables. Additionally, we proposed a secondary ensemble with an improved weighted average approach (IWA) to estimate the reliable forest GSV using the first ensemble models constructed by Bagging and AdaBoost. The experimental results demonstrated that the proposed variable selection criterion efficiently obtained the optimal combined variable set without affecting the forest GSV mapping accuracy. Specifically, considering the first ensemble, the relative root mean square error (rRMSE) values ranged from 21.91% to 30.28% for Bagging and 23.33% to 31.49% for AdaBoost, respectively. After the secondary ensemble involving the IWA, the rRMSE values ranged from 18.89% to 21.34%. Furthermore, the variance of the GSV mapped by the secondary ensemble with various ranking methods was significantly reduced. The results prove that the proposed combined strategy has great potential to reduce the GSV mapping uncertainty imposed by current variable selection approaches and algorithms. [ABSTRACT FROM AUTHOR]