Comparison of Statistical Modelling Approaches for Estimating Tropical Forest Aboveground Biomass Stock and Reporting Their Changes in Low-Intensity Logging Areas Using Multi-Temporal LiDAR Data

Author(s):Show less -

Rex, Franciel Eduardo ^[1] ; Silva, Carlos Alberto ^{[2, 3]} ; Dalla Corte, Ana Paula ^[1] ; Klauberg, Carine ^[4] ; Mohan, Midhun ^[5] ; Cardil, Adrian ^[6] ; da Silva, Vanessa Sousa ^[7] ; Alves de Almeida, Danilo Roberti ^[8] ; Garcia, Mariano ^[9] ; Broadbent, Eben North ^[10] ; Valbuena, Ruben ^[11] ; Stoddart, Jaz ^[11] ; Merrick, Trina ^[12] ; Hudak, Andrew Thomas ^[13]

Affiliation:Show less -

^[1] Univ Fed Parana, Dept Forest Engn, BR-80210170 Curitiba, Parana - Brazil

^[2] Univ Florida, Sch Forest Resources & Conservat, Gainesville, FL 32611 - USA

^[3] Univ Maryland, Dept Geog Sci, College Pk, MD 20740 - USA

^[4] Univ Fed Sao Joao del Rei, BR-35701970 Sete Lagoas - Brazil

^[5] Univ Calif Berkeley, Dept Geog, Berkeley, CA 94709 - USA

^[6] Tecnosylva, Parque Tecnol Leon, Leon 24009 - Spain

^[7] Univ Fed Rural Pernambuco, Dept Forest Sci, Rua Dom Manoel Medeiros S-N, BR-52171900 Recife, PE - Brazil

^[8] Univ Sao Paulo Luiz de Queiroz, Dept Forest Sci, Coll Agr USP ESALQ, BR-13418900 Piracicaba - Brazil

^[9] Univ Alcala De Henares, Environm Remote Sensing Res Grp, Dept Geol Geog & Environm, Calle Colegios 2, Alcala De Henares 28801 - Spain

^[10] Univ Florida, Sch Forest Resources & Conservat, Spatial Ecol & Conservat Lab, Gainesville, FL 32611 - USA

^[11] Bangor Univ, Sch Nat Sci, Bangor LL57 2UW, Gwynedd - Wales

^[12] Florida State Univ, Dept Geog, 113 Collegiate Loop, Tallahassee, FL 32306 - USA

^[13] US Forest Serv, USDA, Rocky Mt Res Stn, RMRS, 1221 South Main St, Moscow, ID 83843 - USA

• Document type: Journal article
• Source: REMOTE SENSING; v. 12, n. 9 MAY 2020.
• Web of Science Citations: 0

Abstract

Accurately quantifying forest aboveground biomass (AGB) is one of the most significant challenges in remote sensing, and is critical for understanding global carbon sequestration. Here, we evaluate the effectiveness of airborne LiDAR (Light Detection and Ranging) for monitoring AGB stocks and change (Delta AGB) in a selectively logged tropical forest in eastern Amazonia. Specifically, we compare results from a suite of different modelling methods with extensive field data. The calibration AGB values were derived from 85 square field plots sized 50 x 50 m field plots established in 2014 and which were estimated using airborne LiDAR data acquired in 2012, 2014, and 2017. LiDAR-derived metrics were selected based upon Principal Component Analysis (PCA) and used to estimate AGB stock and change. The statistical approaches were: ordinary least squares regression (OLS), and nine machine learning approaches: random forest (RF), several variations of k-nearest neighbour (k-NN), support vector machine (SVM), and artificial neural networks (ANN). Leave-one-out cross-validation (LOOCV) was used to compare performance based upon root mean square error (RMSE) and mean difference (MD). The results show that OLS had the best performance with an RMSE of 46.94 Mg/ha (19.7%) and R-2 = 0.70. RF, SVM, and ANN were adequate, and all approaches showed RMSE <= 54.48 Mg/ha (22.89%). Models derived from k-NN variations all showed RMSE >= 64.61 Mg/ha (27.09%). The OLS model was thus selected to map AGB across the time-series. The mean (+/- sd-standard deviation) predicted AGB stock at the landscape level was 229.10 (+/- 232.13) Mg/ha in 2012, 258.18 (+/- 106.53) in 2014, and 240.34 (sd +/- 177.00) Mg/ha in 2017, showing the effect of forest growth in the first period and logging in the second period. In most cases, unlogged areas showed higher AGB stocks than logged areas. Our methods showed an increase in AGB in unlogged areas and detected small changes from reduced-impact logging (RIL) activities occurring after 2012. We also detected that the AGB increase in areas logged before 2012 was higher than in unlogged areas. Based on our findings, we expect our study could serve as a basis for programs such as REDD+ and assist in detecting and understanding AGB changes caused by selective logging activities in tropical forests. (AU)

• FAPESP's process: 19/14697-0 - Monitoring the demography and diversity of forests undergoing restoration using a drone-lidar-hyperspectral system
• Grantee: Danilo Roberti Alves de Almeida
• Support Opportunities: Scholarships abroad - Research Internship - Post-doctor
• FAPESP's process: 18/21338-3 - Monitoring forest landscape restoration from unmanned aerial vehicles using Lidar and hyperspectral remote sensing
• Grantee: Danilo Roberti Alves de Almeida
• Support Opportunities: Scholarships in Brazil - Post-Doctoral