Abstract
Most of the allometric models used to estimate tree aboveground biomass rely on tree diameter at breast height (DBH). However, it is difficult to measure DBH from airborne remote sensors, and is common to draw upon traditional least squares linear regression models to relate DBH with dendrometric variables measured from airborne sensors, such as tree height (H) and crown diameter (CD). This study explores the usefulness of ensemble-type supervised machine learning regression algorithms, such as random forest regression (RFR), categorical boosting (CatBoost), gradient boosting (GBoost), or AdaBoost regression (AdaBoost), as an alternative to linear regression (LR) for modelling the allometric relationships DBH = Φ(H) and DBH = Ψ(H, CD). The original dataset was made up of 2272 teak trees (Tectona grandis Linn. F.) belonging to three different plantations located in Ecuador. All teak trees were digitally reconstructed from terrestrial laser scanning point clouds. The results showed that allometric models involving both H and CD to estimate DBH performed better than those based solely on H. Furthermore, boosting machine learning regression algorithms (CatBoost and GBoost) outperformed RFR (bagging) and LR (traditional linear regression) models, both in terms of goodness-of-fit (R2) and stability (variations in training and testing samples).
Highlights
Forests contain 80% of the Earth’s biomass, accounting for 75% of the gross primary productivity of the terrestrial biosphere [1]
Regarding supervised machine learning methods, this study has focused on testing tree-based regression learners such as individual tree-based models (Decision Tree Regression, DTR) and some derive ensemble algorithms grouped in bagging techniques (Random Forest Regression, random forest regression (RFR)) and boosting techniques (AdaBoost Regression, AdaBoost; Gradient Boosting Regression, gradient boosting (GBoost); and Categorical Boosting Regression, CatBoost)
AdaBoost and RFR were statistically situated between the very good results offered by GBoost and CatBoost and the good results offered by linear regression, providing predictions not significantly different from those provided by linear regression
Summary
Forests contain 80% of the Earth’s biomass, accounting for 75% of the gross primary productivity of the terrestrial biosphere [1] In this way, they are a major component of the global carbon cycle, representing up to 50% of the annual carbon flux between the atmosphere and the Earth’s land surface [2], contributing to atmospheric carbon fixing up to rates of about 30% of the fossil fuel emissions [3]. They are a major component of the global carbon cycle, representing up to 50% of the annual carbon flux between the atmosphere and the Earth’s land surface [2], contributing to atmospheric carbon fixing up to rates of about 30% of the fossil fuel emissions [3] In other words, they are extremely important for our planet, and one of the reasons why forest modelling and monitoring are essential for the development of a sustainable bio-economy based on renewable resources [4]. Field inventories are labor-intensive, time-consuming, and limited by spatial accessibility, while traditional large-scale aerial photography does not directly provide accurate 3D forest information [6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
