Above-ground biomass estimation from LiDAR data using random forest algorithms

•The paper explores Random Forest models to estimate the biomass.•In the paper real data of Pinus Radiata species in a specific area of the Basque Country (Spain) were used.•The LiDAR data used to create the models are of low-density•The dataset used to create the models has a very small size.•Two m...

Full description

Saved in:
Bibliographic Details
Published inJournal of computational science Vol. 58; p. 101517
Main Authors Torre-Tojal, Leyre, Bastarrika, Aitor, Boyano, Ana, Lopez-Guede, Jose Manuel, Graña, Manuel
Format Journal Article
LanguageEnglish
Published Elsevier B.V 01.02.2022
Subjects
Biomass
LiDAR
Random forest
Regression
Regression
Random forest
Biomass
LiDAR
Online AccessGet full text

Cover

More Information
Summary:•The paper explores Random Forest models to estimate the biomass.•In the paper real data of Pinus Radiata species in a specific area of the Basque Country (Spain) were used.•The LiDAR data used to create the models are of low-density•The dataset used to create the models has a very small size.•Two models were obtained showing an R2 higher than 0.7 and a prediction between 16–18 % higher than those given by the Basque Government. Random forest (RF) models were developed to estimate the biomass for the Pinus radiata species in a region of the Basque Autonomous Community where this species has high cover, using the National Forest Inventory, allometric equations and low-density discrete LiDAR data. This article explores the tuning for RF hyperparameters, obtaining two models with an R2 higher than 0.7 using 2-fold cross-validation. The models selected were applied in Orozko, a municipality with more than 5000 ha of this species, where the model predicts a biomass of 1.06–1.08 Mton, which is between 16–18 % higher than the biomass predicted by the Basque Government.
ISSN:1877-7503
1877-7511
DOI:10.1016/j.jocs.2021.101517