TY - JOUR

T1 - Large scale multi-layer fuel load characterization in tropical savanna using GEDI spaceborne lidar data

AU - Leite, Rodrigo Vieira

AU - Silva, Carlos Alberto

AU - Broadbent, Eben North

AU - Amaral, Cibele Hummel do

AU - Liesenberg, Veraldo

AU - Almeida, Danilo Roberti Alves de

AU - Mohan, Midhun

AU - Godinho, Sérgio

AU - Cardil, Adrian

AU - Hamamura, Caio

AU - Faria, Bruno Lopes de

AU - Brancalion, Pedro H.S.

AU - Hirsch, André

AU - Marcatti, Gustavo Eduardo

AU - Dalla Corte, Ana Paula

AU - Zambrano, Angelica Maria Almeyda

AU - Costa, Máira Beatriz Teixeira da

AU - Matricardi, Eraldo Aparecido Trondoli

AU - Silva, Anne Laura da

AU - Goya, Lucas Ruggeri Ré Y.

AU - Valbuena, Ruben

AU - Mendonça, Bruno Araujo Furtado de

AU - Silva Junior, Celso H.L.

AU - Aragão, Luiz E.O.C.

AU - García, Mariano

AU - Liang, Jingjing

AU - Merrick, Trina

AU - Hudak, Andrew T.

AU - Xiao, Jingfeng

AU - Hancock, Steven

AU - Duncason, Laura

AU - Ferreira, Matheus Pinheiro

AU - Valle, Denis

AU - Saatchi, Sassan

AU - Klauberg, Carine

PY - 2022/1

Y1 - 2022/1

N2 - Quantifying fuel load over large areas is essential to support integrated fire management initiatives in fire-prone regions to preserve carbon stock, biodiversity and ecosystem functioning. It also allows a better understanding of global climate regulation as a potential carbon sink or source. Large area assessments usually require data from spaceborne remote sensors, but most of them cannot measure the vertical variability of vegetation structure, which is required for accurately measuring fuel loads and defining management interventions. The recently launched NASA's Global Ecosystem Dynamics Investigation (GEDI) full-waveform lidar sensor holds potential to meet this demand. However, its capability for estimating fuel load has yet not been evaluated. In this study, we developed a novel framework and tested machine learning models for predicting multi-layer fuel load in the Brazilian tropical savanna (i.e., Cerrado biome) using GEDI data. First, lidar data were collected using an unnamed aerial vehicle (UAV). The flights were conducted over selected sample plots in distinct Cerrado vegetation formations (i.e., grassland, savanna, forest) where field measurements were conducted to determine the load of surface, herbaceous, shrubs and small trees, woody fuels and the total fuel load. Subsequently, GEDI-like full-waveforms were simulated from the high-density UAV-lidar 3-D point clouds from which vegetation structure metrics were calculated and correlated to field-derived fuel load components using Random Forest models. From these models, we generate fuel load maps for the entire Cerrado using all on-orbit available GEDI data. Overall, the models had better performance for woody fuels and total fuel loads (R2 = 0.88 and 0.71, respectively). For components at the lower stratum, models had moderate to low performance (R2 between 0.15 and 0.46) but still showed reliable results. The presented framework can be extended to other fire-prone regions where accurate measurements of fuel components are needed. We hope this study will contribute to the expansion of spaceborne lidar applications for integrated fire management activities and supporting carbon monitoring initiatives in tropical savannas worldwide.

AB - Quantifying fuel load over large areas is essential to support integrated fire management initiatives in fire-prone regions to preserve carbon stock, biodiversity and ecosystem functioning. It also allows a better understanding of global climate regulation as a potential carbon sink or source. Large area assessments usually require data from spaceborne remote sensors, but most of them cannot measure the vertical variability of vegetation structure, which is required for accurately measuring fuel loads and defining management interventions. The recently launched NASA's Global Ecosystem Dynamics Investigation (GEDI) full-waveform lidar sensor holds potential to meet this demand. However, its capability for estimating fuel load has yet not been evaluated. In this study, we developed a novel framework and tested machine learning models for predicting multi-layer fuel load in the Brazilian tropical savanna (i.e., Cerrado biome) using GEDI data. First, lidar data were collected using an unnamed aerial vehicle (UAV). The flights were conducted over selected sample plots in distinct Cerrado vegetation formations (i.e., grassland, savanna, forest) where field measurements were conducted to determine the load of surface, herbaceous, shrubs and small trees, woody fuels and the total fuel load. Subsequently, GEDI-like full-waveforms were simulated from the high-density UAV-lidar 3-D point clouds from which vegetation structure metrics were calculated and correlated to field-derived fuel load components using Random Forest models. From these models, we generate fuel load maps for the entire Cerrado using all on-orbit available GEDI data. Overall, the models had better performance for woody fuels and total fuel loads (R2 = 0.88 and 0.71, respectively). For components at the lower stratum, models had moderate to low performance (R2 between 0.15 and 0.46) but still showed reliable results. The presented framework can be extended to other fire-prone regions where accurate measurements of fuel components are needed. We hope this study will contribute to the expansion of spaceborne lidar applications for integrated fire management activities and supporting carbon monitoring initiatives in tropical savannas worldwide.

KW - Active remote sensing

KW - Fire

KW - Modeling

KW - Machine learning

KW - UAV-lidar

KW - Cerrado

KW - Vegetation structure

U2 - 10.1016/j.rse.2021.112764

DO - 10.1016/j.rse.2021.112764

M3 - Article

VL - 268

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

M1 - 112764

ER -