Modeling of Aboveground Biomass with Landsat 8 OLI and Machine Learning in Temperate Forests

Pablito M López-Serrano,Enrique Jiménez,Carlos A López-Sánchez,José Luis Cárdenas Domínguez,Daniel José Vega-Nieva,José Javier Corral-Rivas

doi:10.3390/f11010011

Pablito M López-Serrano, Enrique Jiménez + Show 4 more

Open Access

https://doi.org/10.3390/f11010011

Copy DOI

Abstract

An accurate estimation of forests’ aboveground biomass (AGB) is required because of its relevance to the carbon cycle, and because of its economic and ecological importance. The selection of appropriate variables from satellite information and physical variables is important for precise AGB prediction mapping. Because of the complex relationships for AGB prediction, non-parametric machine-learning techniques represent potentially useful techniques for AGB estimation, but their use and comparison in forest remote-sensing applications is still relatively limited. The objective of the present study was to evaluate the performance of automatic learning techniques, support vector regression (SVR) and random forest (RF), to predict the observed AGB (from 318 permanent sampling plots) from the Landsat 8 Landsat 8 Operational Land Imager (OLI) sensor, spectral indexes, texture indexes and physical variables the Sierra Madre Occidental in Mexico. The result showed that the best SVR model explained 80% of the total variance (root mean square error (RMSE) = 8.20 Mg ha−1). The variables that best predicted AGB, in order of importance, were the bands that belong to the region of red and near and middle infrared, and the average temperature. The results show that the SVR technique has a good potential for the estimation of the AGB and that the selection of the model hyperparameters has important implications for optimizing the goodness of fit.

Highlights

Forest ecosystems, which cover 30% of the land surface, play a key role in the global carbon cycle, by mitigating anthropogenic emissions [1]
For support vector machine (SVM) models, the highest model accuracy was obtained with values of cost = 4 and epsilon = 0.5, resulting in R2 value of 0.80 and an RMSE of 8.2 Mg ha−1
The optimum number of support vectors were obtained from the optimized parameterization of the support vector regression (SVR) model

Summary

Introduction

Forest ecosystems, which cover 30% of the land surface, play a key role in the global carbon cycle, by mitigating anthropogenic emissions [1]. A more accurate estimation of the regional to global distribution of forest aboveground biomass is required to provide the baseline of forest carbon stocks, and to quantify the anthropogenic emissions caused by deforestation and forest degradation [2,3]. The quantification of forest biomass has large economic implications for the supply of goods such as wood, timber, food, fiber and energy [4,5]. Forest biomass has important ecological implications in ecosystem sustainability, including soil and water management [6]. Forest biomass and its change influence other ecosystem services, such as biodiversity [7].

Objectives

Results

Conclusion