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

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 (ΔAGB) 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 × 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 R² = 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.

Exploring Forest Change Spatial Patterns in Papua New Guinea: A Pilot Study in the Bumbu River Basin

“…Since many tropical forests are in the frontier stage undergoing land-use transformations due to logging and agricultural expansion, several recent remote sensing studies-not only satellite-based endeavors, but also initiatives from drones and LiDAR (Light Detection and Ranging) spheres-have focused on these aspects in addition to analyzing the impacts of deforestation from the perspective of increased carbon emissions [16][17][18][19][20][21]. By identifying inherent trends, it was found possible to further investigate the rate of land-use change happening over the years and the motives behind these land-use transformations.…”

Model-Based Estimation of Amazonian Forests Recovery Time after Drought and Fire Events

“…Light detection and ranging (Lidar) remote sensing is widely used for monitoring forest structure and biomass dynamics [69,70] in many forest ecosystems [71]. For instance, airborne lidar (ALS) technologies help quantify changes in canopy structure, carbon stocks and recovery time at the local-to-regional scale under different types of forest degradation (e.g., [25,72,73]).…”

Identification of Significative LiDAR Metrics and Comparison of Machine Learning Approaches for Estimating Stand and Diversity Variables in Heterogeneous Brazilian Atlantic Forest

“…Figure 4a shows the contribution of each PC in the total variance. Some authors, such as [13,19], have used the PCA to select variables. They selected one single metric from each PC, based on the highest eigenvector value.…”

“…Regarding native Brazilian forests, the combination of LiDAR metrics and machine learning techniques is mainly focused on the Amazonian forest to estimate the aboveground biomass. In low-intensity logging areas, [19] estimated the aboveground biomass (AGB) stock by comparing multiple linear regression with some machine learning approaches. Linear regression was the most appropriate method for the case study, with an RMSE of 19.7%, slightly better than the methods of RF, ANN, and SVM with a RMSE of 22.8% for the three methods.…”