Enriquez Pinedo, LucíaOrtega Quispe, KevinCcopi Trucios, DennisUrquizo Barrera, JulioRios Chavarría, ClaudiaPizarro Carcausto, SamuelMatos Calderon, DianaPatricio Rosales, SolanchRodríguez Cerrón, MauroOre Aquino, ZoilaPaz Monge, MichelCastañeda Tinco, Italo2025-03-242025-03-242024-12-22Lucia Enriquez Pinedo, Kevin Ortega Quispe, Dennis Ccopi Trucios, Julio Urquizo Barrera, Claudia Rios Chavarría, Samuel Pizarro Carcausto, Diana Matos Calderon, Solanch Patricio Rosales, Mauro Rodríguez Cerrón, Zoila Ore Aquino, Michel Paz Monge, Italo Castañeda Tinco, Estimation of height and aerial biomass in Eucalyptus globulus plantations using UAV-LiDAR, Trees, Forests and People, Volume 19, 2025, 100763, ISSN 2666-7193, https://doi.org/10.1016/j.tfp.2024.100763http://hdl.handle.net/20.500.12955/2675The lack of precise methods for estimating forest biomass results in both economic losses and incorrect decisions in the management of forest plantations. In response to this issue, this study evaluated the effectiveness of using the DJI Zenmuse L1 LiDAR, mounted on a DJI Matrice 300 RTK UAV, to provide three-dimensional measurements of canopy structure and estimate the aboveground biomass of Eucalyptus globulus. Various LiDAR metrics were employed alongside field measurements to calibrate predictive models using multiple regression and machine learning algorithms. The results at the individual tree level show that RF is the most accurate model, with a coefficient of determination (R²) of 0.76 in the training set and 0.66 in the test set, outperforming Elastic Net (R² of 0.58 and 0.57, respectively). At the plot level, a multiple regression model achieved an R² of 0.647, highlighting LiDAR-derived metrics as key predictors. The findings revealed that the combination of LiDAR with advanced statistical techniques, such as multiple regression and Random Forest, significantly improves the accuracy of biomass estimation, surpassing traditional methods based on allometric equations. Therefore, the use of LiDAR in conjunction with machine learning represents an effective alternative for biomasss estimation, with great potential in such plantations and contribute to more sustainable exploitation of timber resources.1. Introduction 2. Materials and methods o 2.1. Study site o 2.2. Methodological framework o 2.3. Sampling design and field data collection  2.3.1. Tree position  2.3.2. Dendrometric variables o 2.4. UAV-LIDAR remote sensing data acquisition o 2.5. Data processing and statistical analysis  2.5.1. Point cloud generation  2.5.2. Processing of the point cloud  2.5.3. Extraction of metrics o 2.6. Forest biomass estimation  2.6.1. Area-based approach (ABA) with statistical regression models  2.6.2. Individual tree-based approach (ITD) with machine learning algorithms 3. Results o 3.1. Coefficient of determination in estimating maximum height o 3.2. Correlation analysis between LiDAR metrics and biomass o 3.3. Estimation of biomass at the individual tree level o 3.4. Estimation of maximum height at the individual tree level o 3.5. Multiple linear regression model at the plot level 4. Discussion 5. Conclusions Declaration of competing interest Acknowledgments Referencesapplication/pdfenginfo:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/4.0/Forest biomassRemote sensorsLiDAREucalyptus globulusUAVinfo:eu-repo/semantics/articlehttps://purl.org/pe-repo/ocde/ford#4.01.0210.1016/j.tfp.2024.100763biomasa forestal | sensores remotos | LIDAR | Eucalyptus globulus | vehículos aéreos no tripulados