Search

Introduction: Quantifying forest biomass requires the application of allometric equations which is a fundamental step. Generalized allometric equations have been applied to quantify aboveground biomass (AGB) of forests. But, adopting generalized allometric equations to quantify AGB of different forests creates uncertainty. Therefore, developing species- and site-specific allometric equations is essential to accurately quantify the biomass. The study was aimed to develop species-specific allometric equations for Diospyros abyssinica (Hiern) F. White in Yayu Coffee Forest Biosphere Reserve using the Semi-destructive method. The vegetation types of Yayu Coffee Forest Biosphere Reserve is categorized to Moist Evergreen Montane Rainforest of Ethiopia. Results and discussion: Evaluating statistical relationships of AGB against predictor variables, eight allometric equations were formulated. AGB was regressed against trunk diameter (D), total height (H), and wood density (ρ) individually and in combination. Selection of allometric equations was employed using model performance statistics. Equations with a higher coefficient of determination (adjusted R2), lower residual standard error, and Akaike information criterion (AIC) values were found best-fitted. Relationships of AGB and independent variables were found statistically significant (p < 0.000). Overall, formulating species- and site-specific allometric equations is significant for accurate estimation of forest biomass and carbon stock budget. [ABSTRACT FROM AUTHOR]

This paper aims to assess the performance of generalized aboveground biomass (AGB) allometric models in the Australian context by investigating the correlation between the AGB estimates and the lidar-based individual tree parameters. A hybrid tree segmentation algorithm is proposed to segment an airborne lidar point cloud into individual trees. Although the diameter at breast height (DBH) of a tree is a crucial parameter for the AGB estimation, a typical airborne lidar data contains only a few points representing partial DBH, hence a localized DBH regression model is proposed. Principal component analysis is applied to examine the multicollinearity in the input variables and ridge regression is applied to remove the less important variables. Four machine learning techniques, namely random forest, support vector regression, multilayer perceptron and radial basis function, are applied to generate AGB regression models. The qualities of the calibrated AGB models are assessed by calculating the adjusted-coefficient-of-determination, leave-one-out cross-validation, the Akaike information criterion, normalized-mean-square-error and the model efficiency index. The test results indicate that the random forest-based AGB model outperforms other machine learning techniques. It is concluded that, if the environmental conditions of tree samples resemble the study region, the generalized AGB allometric model would perform well with the tree samples regardless of their geographical context. [ABSTRACT FROM AUTHOR]