Building Tree Allometry Relationships Based on TLS Point Clouds and Machine Learning Regression
Source abstract
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).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Remote Sensing and LiDAR Applications · Forest ecology and management · Tree Root and Stability Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Engineering and Research Centre CIAIMBITAL, University of Almería, Carretera de Sacramento s/n, La Cañada de San Urbano, 04120 Almería, Spain
Faculty of Technical Education for Development, Santiago de Guayaquil Catholic University, Av. Carlos Julio Arosamena, Guayaquil 090615, Ecuador
Funding
Regional Government of Andalusia · Catholic University of Santiago de Guayaquil · Generalitat Valenciana
References (51)
Show source-provided references
1. The structure, distribution, and biomass of the world’s forests10.1146/annurev-ecolsys-110512-135914 ↗
2. Terrestrial Gross Carbon Dioxide Uptake: Global Distribution and Covariation with Climate10.1126/science.1184984 ↗
3. A large and persistent carbon sink in the world’s forests10.1126/science.1201609 ↗
4. Individual Tree Crown Methods for 3D Data from Remote Sensing10.1007/s40725-017-0051-6 ↗
5. Negative emissions from stopping deforestation and forest degradation, globally10.1111/gcb.13876 ↗
6. A New Method for Segmenting Individual Trees from the Lidar Point Cloud10.14358/PERS.78.1.75 ↗
7. Wallace, L., Lucieer, A., Malenovskỳ, Z., Turner, D., and Vopěnka, P. (2016). Assessment of forest structure using two UAV techniques: A comparison of airborne laser scanning and structure from motion (SfM) point clouds. Forests, 7.10.3390/f7030062 ↗
8. Aguilar, F.J., Rivas, J.R., Nemmaoui, A., Peñalver, A., and Aguilar, M.A. (2019). UAV-Based Digital Terrain Model Generation under Leaf-Off Conditions to Support Teak Plantations Inventories in Tropical Dry Forests. A Case of the Coastal Region of Ecuador. Sensors, 19.10.3390/s19081934 ↗
9. Remote sensing for the Spanish forests in the 21stcentury: A review of advances, needs, and opportunities
10. Remote Sensing Technologies for Enhancing Forest Inventories: A Review10.1080/07038992.2016.1207484 ↗
11. Individual tree biomass estimation using terrestrial laser scanning10.1016/j.isprsjprs.2012.10.003 ↗
12. Terrestrial laser scanning in forest inventories10.1016/j.isprsjprs.2016.01.006 ↗
13. Automatic dendrometry: Tree detection, tree height and diameter estimation using terrestrial laser scanning
14. Aguilar, F.J., Nemmaoui, A., Peñalver, A., Rivas, J.R., and Aguilar, M.A. (2019). Developing allometric equations for teak plantations located in the coastal region of ecuador from terrestrial laser scanning data. Forests, 10.10.3390/f10121050 ↗
15. Forest biomass estimation from airborne LiDAR data using machine learning approaches10.1016/j.rse.2012.07.006 ↗
16. Li, Y., Li, C., Li, M., and Liu, Z. (2019). Influence of Variable Selection and Forest Type on Forest Aboveground Biomass Estimation Using Machine Learning Algorithms. Forests, 10.10.3390/f10121073 ↗
17. Improved allometric models to estimate the aboveground biomass of tropical trees10.1111/gcb.12629 ↗
18. Allometric equations for integrating remote sensing imagery into forest monitoring programmes10.1111/gcb.13388 ↗
19. Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data10.1111/2041-210X.12575 ↗
20. Propagating uncertainty through individual tree volume model predictions to large-area volume estimates10.1007/s13595-015-0473-x ↗
21. Holdridge, L.R. (1982). Ecología Basada en Zonas de Vida, Instituto Interamericano de Cooperacion para la Agricultura.
22. The influence of scan mode and circle fitting on tree stem detection, stem diameter and volume extraction from terrestrial laser scans10.1016/j.isprsjprs.2012.12.001 ↗
23. Trochta, J., Krůček, M., Vrška, T., and Král, K. (2017). 3D Forest: An application for descriptions of three-dimensional forest structures using terrestrial LiDAR. PLoS ONE, 12.10.1371/journal.pone.0176871 ↗
24. (2021, April 22). FUSION/LDV LIDAR Analysis and Visualization Software. Available online: http://forsys.cfr.washington.edu/fusion/fusion_overview.html.
25. Zhang, Y., Ma, J., Liang, S., Li, X., and Li, M. (2020). An Evaluation of Eight Machine Learning Regression Algorithms for Forest Aboveground Biomass Estimation from Multiple Satellite Data Products. Remote Sens., 12.10.3390/rs12244015 ↗
26. Luo, M., Wang, Y., Xie, Y., Zhou, L., Qiao, J., Qiu, S., and Sun, Y. (2021). Combination of Feature Selection and CatBoost for Prediction: The First Application to the Estimation of Aboveground Biomass. Forests, 12.10.3390/f12020216 ↗
27. Hancock, J.T., and Khoshgoftaar, T.M. (2020). CatBoost for big data: An interdisciplinary review. J. Big Data, 7.10.1186/s40537-020-00369-8 ↗
28. Modeling forest biomass using Very-High-Resolution data—Combining textural, spectral and photogrammetric predictors derived from spaceborne stereo images10.5721/EuJRS20154814 ↗
29. Reducing Emissions from Deforestation and Forest Degradation10.1146/annurev-environ-042009-094508 ↗
30. Modelling height-diameter relationships in complex tropical rain forest ecosystems using deep learning algorithm
31. Aplicación de ecuaciones de conicidad para teca (Tectona grandis L.F.) en la zona costera ecuatoriana10.18779/cyt.v4i2.109 ↗
32. Aboveground biomass of Tectona grandis plantations in Costa Rica
33. The Utility of Image-Based Point Clouds for Forest Inventory: A Comparison with Airborne Laser Scanning10.3390/f4030518 ↗
34. Mohan, M., Silva, C., Klauberg, C., Jat, P., Catts, G., Cardil, A., Hudak, A., and Dia, M. (2017). Individual Tree Detection from Unmanned Aerial Vehicle (UAV) Derived Canopy Height Model in an Open Canopy Mixed Conifer Forest. Forests, 8.10.3390/f8090340 ↗
35. 3-D mapping of a multi-layered Mediterranean forest using ALS data10.1016/j.rse.2012.01.020 ↗
36. Calders, K., Jonckheere, I., Nightingale, J., and Vastaranta, M. (2020). Remote Sensing Technology Applications in Forestry and REDD+. Forests, 11.10.3390/f11020188 ↗
37. Vafaei, S., Soosani, J., Adeli, K., Fadaei, H., Naghavi, H., Pham, T.D., and Bui, D.T. (2018). Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran). Remote Sens., 10.10.3390/rs10020172 ↗
38. Prognoses of diameter and height of trees of eucalyptus using artificial intelligence10.1016/j.scitotenv.2017.11.138 ↗
39. Bayat, M., Bettinger, P., Heidari, S., Khalyani, A.H., Jourgholami, M., and Hamidi, S.K. (2020). Estimation of Tree Heights in an Uneven-Aged, Mixed Forest in Northern Iran Using Artificial Intelligence and Empirical Models. Forests, 11.10.3390/f11030324 ↗
40. Using machine learning to synthesize spatiotemporal data for modelling DBH-height and DBH-height-age relationships in boreal forests10.1016/j.foreco.2020.118104 ↗
41. Innovative deep learning artificial intelligence applications for predicting relationships between individual tree height and diameter at breast height
42. Configuração de algoritmos de aprendizado de máquina na modelagem florestal: Um estudo de caso na modelagem da relação hipsométrica10.5902/1980509828392 ↗
43. Machine learning: Modeling increment in diameter of individual trees on Atlantic Forest fragments10.1016/j.ecolind.2020.106685 ↗
44. Abegg, M., Kükenbrink, D., Zell, J., Schaepman, M.E., and Morsdorf, F. (2017). Terrestrial laser scanning for forest inventories-tree diameter distribution and scanner location impact on occlusion. Forests, 8.10.3390/f8060184 ↗
45. Automatic Estimation of Tree Stem Attributes Using Terrestrial Laser Scanning in Central Indian Dry Deciduous Forests10.18520/cs/v114/i01/201-206 ↗
46. Precisión y eficiencia del inventario de plantaciones de teca en Ecuador mediante escáner láser terrestre
47. Comparison of ALS- and UAV(SfM)-derived high-density point clouds for individual tree detection in Eucalyptus plantations10.1080/01431161.2018.1486519 ↗
48. Lin, Y.-C., Liu, J., Fei, S., and Habib, A. (2021). Leaf-Off and Leaf-On UAV LiDAR Surveys for Single-Tree Inventory in Forest Plantations. Drones, 5.10.3390/drones5040115 ↗
49. Terrestrial laser scanning for plot-scale forest measurement10.1007/s40725-015-0025-5 ↗
50. Automated Stem Curve Measurement Using Terrestrial Laser Scanning10.1109/TGRS.2013.2253783 ↗
51. Feasibility of Terrestrial laser scanning for collecting stem volume information from single trees10.1016/j.isprsjprs.2016.11.012 ↗