RT Journal Article
T1 Estimating biomass of mixed and uneven-aged forests using spectral data and a hybrid model combining regression trees and linear models
A1 López Serrano, Pablito Marcelo
A1 López Sánchez, Carlos Antonio
A1 Díaz Varela, Ramón Alberto
A1 Corral Rivas, José Javier
A1 Solís Moreno, Raúl
A1 Vargas Larreta, Benedicto
A1 Álvarez González, Juan Gabriel
K1 Regression trees
K1 Stepwise regression
K1 Remote sensing
K1 ATCOR3
K1 Terrain features
K1 Image texture
AB The Sierra Madre Occidental mountain range (Durango, Mexico) is of great ecological interest because of the high degree of environmental heterogeneity inthe area. The objective of the present study was to estimate the biomass ofmixed and uneven-aged forests in the Sierra Madre Occidental by using Landsat-5 TM spectral data and forest inventory data. We used the ATCOR3 ® atmospheric and topographic correction module to convert remotely sensed imagery digital signals to surface reflectance values. The usual approach of modeling stand variables by using multiple linear regression was compared with ahybrid model developed in two steps: in the first step a regression tree wasused to obtain an initial classification of homogeneous biomass groups, andmultiple linear regression models were then fitted to each node of the prunedregression tree. Cross-validation of the hybrid model explained 72.96% of theobserved stand biomass variation, with a reduction in the RMSE of 25.47% withrespect to the estimates yielded by the linear model fitted to the completedatabase. The most important variables for the binary classification process inthe regression tree were the albedo, the corrected readings of the short-waveinfrared band of the satellite (2.08-2.35 µm) and the topographic moistureindex. We used the model output to construct a map for estimating biomass inthe study area, which yielded values of between 51 and 235 Mg ha-1. The useof regression trees in combination with stepwise regression of corrected satellite imagery proved a reliable method for estimating forest biomass.
PB Italian Society of Silviculture and Forest Ecology (SISEF)
YR 2015
FD 2015
LK http://hdl.handle.net/10347/22342
UL http://hdl.handle.net/10347/22342
LA eng
NO López-Serrano PM, López-Sánchez CA, Díaz-Varela RA, Corral-Rivas JJ, Solís-Moreno R, Vargas-Larreta B, Álvarez-González JG (2015). Estimating biomass of mixed and uneven-aged forests using spectral data and a hybrid model combining regression trees and linear models. iForest 9: 226-234. - doi: 10.3832/ifor1504-008
NO This research was supported by SEPPROMEP (Project: Seguimiento y Evaluación de Sitios Permanentes de Investigación Forestal y el Impacto Socioeconómico del anejo Forestal en el Norte de México)
DS Minerva
RD 25 abr 2026