EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Biomass and Carbon of Eucalyptus spp. Genotypes Estimated With UAV‐LIDAR Using Area‐Based Approach and Machine Learning

Carla Talita Pertille, Alexandre Behling, Carlos Roberto Sanquetta, Otávio Camargo Campoe, Guerric Le Maire, Joannès Guillemot, Geovanni Malatesta Barros, Emerson Roberto Schoeninger, Ana Paula Dalla Corte

International Journal of Forestry Research · 2025-01 · 2025 (1)

DOI: 10.1155/ijfr/5516907 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Forestry Research, online erschienen am 15.10.2025. Verfasst von Carla Talita Pertille und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aimed to quantify aboveground biomass and aboveground carbon in the total, trunk, and canopy compartments of Eucalyptus spp. using UAV‐LiDAR data, using modeling techniques. The study area is part of the EUCFLUX project located in São Paulo, Brazil, and consists of five experimental blocks with 25 Eucalyptus spp. genotypes. Forest inventory and destructive sampling to assess biomass took place in May 2023. UAV‐LiDAR data were collected with a Zenmuse L1 sensor on a DJI Matrice 300 aircraft, and predictive models were developed based on the metrics selected through principal component analysis. RF obtained an adjusted R 2 of 0.952 and 0.959 for total and trunk aboveground biomass, respectively, and an RMSE of 5.42% for total aboveground biomass and 4.59% for trunk biomass. The adjusted R 2 values for total aboveground carbon and trunk carbon were 0.947 and 0.959, with RMSE of 5.38% and 4.54%, respectively. The XGB algorithm outperformed the other methods in the canopy compartment, with adjusted R 2 of 0.765 and 0.707 and RMSE of 13.49% and 15.06%, respectively. This study highlights the potential of UAV‐LiDAR and nonparametric algorithms for accurately estimating carbon stock in Eucalyptus spp., contributing to climate change mitigation strategies.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior

Zitieren

APA

Pertille, C. T., Behling, A., Sanquetta, C. R., Campoe, O. C., Maire, G. L., Guillemot, J., Barros, G. M., Schoeninger, E. R., & Corte, A. P. D. (2025). Biomass and Carbon of Eucalyptus spp. Genotypes Estimated With UAV‐LIDAR Using Area‐Based Approach and Machine Learning. International Journal of Forestry Research, 2025(1). https://doi.org/10.1155/ijfr/5516907

Vancouver

Pertille CT, Behling A, Sanquetta CR, Campoe OC, Maire GL, Guillemot J, et al. Biomass and Carbon of Eucalyptus spp. Genotypes Estimated With UAV‐LIDAR Using Area‐Based Approach and Machine Learning. International Journal of Forestry Research. 2025;2025(1). doi:10.1155/ijfr/5516907

BibTeX
@article{Pertille2025,
  author = {Pertille, Carla Talita and Behling, Alexandre and Sanquetta, Carlos Roberto and Campoe, Otávio Camargo and Maire, Guerric Le and Guillemot, Joannès and Barros, Geovanni Malatesta and Schoeninger, Emerson Roberto and Corte, Ana Paula Dalla},
  title = {Biomass and Carbon of Eucalyptus spp. Genotypes Estimated With UAV‐LIDAR Using Area‐Based Approach and Machine Learning},
  journal = {International Journal of Forestry Research},
  year = {2025},
  volume = {2025},
  number = {1},
  doi = {10.1155/ijfr/5516907}
}
Kostenlos starten →