ABOVEGROUND BIOMASS ESTIMATION IN A TROPICAL FOREST WITH SELECTIVE LOGGING USING RANDOM FOREST AND LIDAR DATA

Juliana Marchesan,Elisiane Alba,José Augusto Spiazzi Favarin,Mateus Sabadi Schuh,Rudiney Soares Pereira

doi:10.5380/rf.v50i4.66589

Juliana Marchesan, Elisiane Alba + Show 3 more

Open Access

https://doi.org/10.5380/rf.v50i4.66589

Copy DOI

Abstract

The tropical forest is characterized by expressive biomass and stores high amounts of carbon, which is an important variable for climate monitoring. Thus, studies aiming to analyze suitable methods to predict biomass are crucial, especially in the tropics, where dense vegetation makes modeling difficult. Thus, the objective of the present study was to estimate aboveground biomass (AGB) in a tropical forest area with selective logging in the Amazon forest using the Random Forest (RF) machine learning algorithm and LiDAR data. For this, 85 sample units were used at Fazenda Cauaxi, in the municipality of Paragominas, Pará State. LiDAR data were collected in 2014 and made available by the Sustainable Landscapes Project. The software R was used for data analysis. Among the LiDAR metrics, the average height was used as it had the greatest significance to compose the model. The model presented a pseudo R² of 0.69 (value obtained by the RF), Spearman's Correlation Coefficient of 0.80, RMSE of 47.05 Mg.ha-1 (19.84%), and Bias of 2.06 Mg.ha-1 (0.87%). With the results, it was possible to infer that the average height metric was enough to estimate AGB in a tropical forest with selective logging, in addition, the RF algorithm the biomass to be estimated, which can be used to assist in monitoring and action management in areas of selective logging and serve as a basis for climate change mitigation policies.

Highlights

Tropical forests are one of the most biodiverse habitats known and cover 45% of the total forest area of the world (D'ANNUNZIO et al, 2017)
The Shapiro-Wilk test indicated that the data did not show normality (p-value = 0.0058), which is due to the discrepancy between the aboveground biomass (AGB) values obtained in the sample units as a result of the existence of gaps in certain areas combined with sampling units with dense vegetation
The AGB values found in the study area were similar to those found in other areas located in the same biome, such as by Benítez et al (2016), who obtained average AGB of 195.80 Mg.ha-1 and d'Oliveira et al (2012) and Andersen et al (2014), who analyzed regions of the Amazon biome with selective logging and found AGB values that varied between 96.9 and 493.6 Mg.ha-1, averaging 230.9 Mg.ha-1

Summary

Introduction

Tropical forests are one of the most biodiverse habitats known and cover 45% of the total forest area of the world (D'ANNUNZIO et al, 2017). These biomes represent two-thirds of the total terrestrial area of the planet and are characterized by expressive biomass and storing high amounts of carbon (PAN et al, 2013). Despite their importance, tropical forests have been destroyed at a rapid pace, with the forest typology having lost the largest area (D'ANNUNZIO et al, 2017).

Objectives

Methods

Results

Conclusion