Search

The accurate estimation of forest above-ground biomass (AGB) is crucial for sustainable forest management and tracking the carbon cycle of forest ecosystem. Machine learning algorithms have been proven to have great potential in forest AGB estimation with remote sensing data. Though many studies have demonstrated that a single machine learning model can produce highly accurate estimations of forest AGB in many situations, efforts are still required to explore the possible improvement in forest AGB estimation for a specific scenario under study. This study aims to investigate the performance of novel ensemble machine learning methods for forest AGB estimation and analyzes whether these methods are affected by forest types, independent variables, and spatial autocorrelation. Four well-known machine learning models (CatBoost, LightGBM, random forest (RF), and XGBoost) were compared for forest AGB estimation in the study using eight scenarios devised on the basis of two study regions, two variable types, and two validation strategies. Subsequently, a hybrid model combining the strengths of these individual models was proposed for forest AGB estimation. The findings indicated that no individual model outperforms the others in all scenarios. The RF model demonstrates superior performance in scenarios 5, 6, and 7, while the CatBoost model shows the best performance in the remaining scenarios. Moreover, the proposed hybrid model consistently has the best performance in all scenarios in spite of some uncertainties. The ensemble strategy developed in this study for the hybrid model substantially improves estimation accuracy and exhibits greater stability, effectively addressing the challenge of model selection encountered in the forest AGB forecasting process. [ABSTRACT FROM AUTHOR]

Non-structural carbohydrates' (NSCs) allocation pattern is closely related to environmental factors, plant metabolism, and xylem function. At the same time, we know little about whole-tree NSC allocation patterns in different seasons, especially the high-elevation species which suffer from environmental stress. We examined the concentration of NSCs in various parts of Faxon fir trees (needles, branches, trunks, and roots) at five elevations (2800 m, 3000 m, 3200 m, 3400 m, and 3600 m) over four months (July 2019, October 2019, January 2020, and April 2020). The goal was to understand how NSC allocation patterns vary by location and time in high-elevation species and what factors contribute to these variations. The results showed that the needles had the highest concentration, followed by roots, branches, and trunks. The NSC concentration was highest in January 2020 and lowest in July 2019. The total non-structural carbohydrates (TNSCs) and soluble sugar concentrations of roots and needles were substantially higher in the cold (non-growing season) than in the warm (growing season) season. At different elevations, the soluble sugar concentrations in the needles and trunks remained the highest and lowest, respectively. Branches and roots' soluble sugar concentrations alternated and varied with the seasons at all elevations. Many factors, such as climate, morphological traits, and carbon content, affected the spatial and temporal patterns of non-structural carbohydrates, with temperature, plant moisture conditions, and carbon content being the main driving factors. Various factors' interaction mainly influenced NSCs' spatial and temporal patterns. Non-structural carbohydrates significantly improve the resistance of Faxon fir trees' terminal organs in adverse environments. [ABSTRACT FROM AUTHOR]

A comparative discussion of the advantages and disadvantages of natural stands and plantations, including in terms of their productivity and stability, began from the moment of the first forest plantings and continues to this day. In the context of the progressive replacement of natural forests by plantations due to deforestation, the question of how will change the carbon storage capacity of forest cover when replacing natural forests with artificial ones in a changing climate becomes extremely relevant. This article presents the first attempt to answer this question at the transcontinental level on a special case for two-needled pine trees (subgenus Pinus L.). The research was carried out using the database compiled by the authors on the single-tree biomass structure of forest-forming species of Eurasia, in particular, data of 1880 and 1967 of natural and plantation trees, respectively. Multi-factor regression models are calculated after combining the matrix of initial data on the structure of tree biomass with the mean January temperature and mean annual precipitation, and their adequacy indices allow us to consider them reproducible. It is found that the aboveground and stem biomass of equal-sized and equal-aged natural and plantation trees increases as the January temperature and precipitation rise. This pattern is only partially valid for the branches biomass, and it has a specific character for the foliage one. The biomass of all components of plantation trees is higher than that of natural trees, but the percent of this excess varies among different components and depends on the level of January temperatures, but does not depend at all on the level of annual precipitation. A number of uncertainties that arose during the modeling process, as well as the preliminary nature of the obtained regularities, are noted. [ABSTRACT FROM AUTHOR]

The study examines the complex dynamics of changes in LULC over three decades, focused on the years 1992, 2002, 2012, and 2022. The research highlights the significance of comprehending these alterations within the framework of environmental and socio-economic consequences. The changes in land use and land cover (LULC) have significant and far-reaching effects on ecosystems, biodiversity, and human livelihoods. This study offers useful information for politicians, conservationists, and urban planners by examining historical patterns and forecasting future changes. The study utilized a Multilayer Perceptron Neural Network (MLP-NN), a well-known machine learning technique that excels at collecting intricate patterns. This model’s design had three layers: input, hidden, and output. The model underwent 10,000 iterations during its training process, and a thorough statistical analysis was conducted to assess the impact of each driving component. The MLP-NN model demonstrated impressive performance, with a skill measure of 0.8724 and an accuracy rate of 89.08%. The accuracy of the LULC estimates for 2022 was verified by comparing them with observed data, ensuring the model’s reliability. Moreover, the presence of evidence likely was found to be a significant factor that had a substantial impact on the accuracy of the model. The study highlights the effectiveness of the MLP-NN model in accurately predicting changes in LULC. The model’s exceptional accuracy and proficiency make it a powerful tool for future LULC forecasts. Identifying the primary causes of model performance and understanding their implications may help to enhance land management strategies, encourage spatial planning, guide accurate decision-making, and facilitate the development of policies that align with sustainable growth and development. [ABSTRACT FROM AUTHOR]