<!-- *** Custom HTML *** --> LiDAR remote sensing data combined with machine learning (ML) techniques have presented great potential for large-scale modeling of tropical forest attributes. However, the large amount of information that can be derived from an aerial LiDAR survey, summed with the intrinsic heterogeneity of tropical environments (e.g., the Amazon), makes it a challenge to accurately estimate forest biophysical variables. The aim of our work is to investigate the potential and accuracy of different ML techniques and a generalized linear model (GLM) to learn the relationships between LiDAR-derived metrics and forest inventory data for aboveground biomass (AGB) prediction in Amazon forest sites under selective logging regimes. The predictive performance of three ML techniques, namely random forest (RF), support vector machine (SVM), and artificial neural network (ANN), was compared against result from the GLM technique, across 85 sample plots. Interestingly, the GLM retrieved the most accurate estimations of forest AGB (rho Spearman’s coefficient = 0.87), compared with the ML techniques (RF = 0.77, SVM = 0.67, and ANN = 0.50). A number of possible factors affecting such results are listed and discussed in the text, including sample size and number of predictor variables. Continued research is necessary to improve the confidence of AGB estimation, especially over complex forest structures.
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.
Developing an efficient method to accurately estimate aboveground biomass in tropical forests is critical to monitoring the carbon stock and implementing policies to reduce emissions caused by deforestation. Thus, the objective of the present study was to estimate aboveground biomass in areas of the Amazonian Forest with selective logging, using the random forest (RF), support vector machine (SVM), and artificial neural network (ANN) machine learning algorithms, using light detection and ranging (LiDAR) data and these combined with OLI/Landsat 8 variables, as well as mapping the biomass for the years 2014 and 2017, allowing one to analyze its dynamics between the years of analysis. The RF and SVM algorithms obtained the lowest error values in all datasets. The association of the variables increased the RF performance. Analyzing the dynamics of biomass, it was observed that the oldest exploration units (2006, 2007, and 2008) have lower biomass stocks. The highest biomass losses in 2017 came from units operated between 2012 and 2013 (the most recent record). Thus, with the method used in this study, it was possible to infer that the machine learning algorithms were efficient in estimating the biomass, emphasizing the RF and the SVM.
31 August 2024 in iForest - Biogeosciences and Forestry
Gap formations in the forest canopy have natural causes, such as bad weather, and anthropic ones, such as sustainable selective extraction of trees and illegal logging, which can already be detected through orbital remote sensing. However, the Amazon region is under frequent cloud cover, which makes it challenging to detect gaps using passive sensors. This study aimed to identify and delimit gaps in the Amazon forest canopy through airborne LiDAR (Light Detection and Ranging) sensor application while testing six different return densities. LiDAR and forest inventory data were obtained over an Amazon rainforest region, defining the minimum area as a forest canopy gap. The point cloud was processed to obtain six return densities with the generation of their respective CHM (Canopy Height Model), which were applied for segmentation and subsequent identification of gap areas and roads. The minimum gap area found was 34 m2, and the Kruskal Wallis test showed no significant difference among the six densities in gap detection; however, road identification decreased as the return density decreased. We concluded that LiDAR data proved promising as point clouds with low return density can be used without impairing gap identification. However, reducing the return density for road identification is not recommended.
Through the variation of the functional attributes, it is possible to verify the functioning of an ecosystem, both by the species organization as by their responses to the environmental variations. In this sense, the objective of this study was to analyze the ecological strategies of the main tree species by analyzing their functional attributes. PCoA was used to verify which species are acquisitive and conservative; clustering was used to verify the functional attributes by groups; the Pearson’s correlation between the functional attributes and a CWM-RDA analysis was used to verify the environmental variables. Most species were classified as light-demanding climax and having zoochoric dispersion. The species presented phenotypic plasticity as an important ecological strategy in the composition of their functional attributes, especially when related to leaf area and specific leaf area. Most of the species belonged to the acquisitive group. The acquisitive and conservative groups indicate the resilience potential of the tree community and the change processes in ecological succession. There was a strong negative correlation between the leaf attributes, and a positive one with diameter and height, both correlations related to plant growth and development. Of the environmental variables only pH, K, and average elevation, were related to the attributes, indicating that environmental conditions are important for the establishment of the sampled species. Also, it was found that the species composition is linked to several conditions of ecological strategies associated with changes in the environment.