Competition among trees for limited resources (e.g., sunlight, water, and nutrients) impacts their growth differently. Crown plays a crucial role in resource access for trees. However, uncertainties persist regarding crown size differences, tree growth, and tree competition levels between coniferous and broadleaf trees in mixed-age forests. We conducted a study on 3008 live trees across 28 plots in Hunan Province to measure individual crown size and tree growth increment. Introducing a new metric, the Crown Size Competition Index (CSCI), we assessed competition pressure among coniferous and broadleaf species in mixed-age forests. We examined the correlation between competition indices and tree growth increment while also investigating the influence of neighboring species diversity on tree competition. Our results revealed a significant negative correlation between the tree growth of Cunninghamia lanceolata (Lamb.) Hook.(CL) and Phoebe bournei (Hemsl.) Yang (PB) and the competition index. Increased competitive pressure on the focal tree corresponded to a decline in the growth of focal tree volume, with a more pronounced impact observed in PB compared to CL. The diversity of neighboring species contributed to variations in competition for the focal tree, with broadleaved species (PB) exerting a greater influence on the focal tree than coniferous species (CL). These findings underscore the competitive potential of PB in mature coniferous stands and advocate for the restoration of stratified mixes in CL broadleaf forests. Furthermore, our findings support the management strategies for the valuable tree species PB.

The spatial structure of forest stands significantly influences inter-tree competition and the overall stability of the stand’s ecological dynamics, and a profound understanding of forest stand spatial structure is essential for both effective forest management and ecological research. Previous studies on spatial structure have primarily employed single variables, offering only one-dimensional structural insights and lacking the capacity to interpret multidimensional information. In light of these limitations, our study introduces a novel approach founded on a six-variable distribution, aimed at conducting a comprehensive analysis and interpretation of the spatial attributes of forest stands. Diverging from conventional univariate or bivariate methods, the hexi-variate approach simultaneously considers six variables, facilitating a more intricate exploration of the intricate interrelationships within forest ecosystems from six distinct dimensions. We conducted an in-depth analysis of the spatial structural attributes within the forest stand, encompassing factors such as species diversity, size variation, spatial distribution patterns, openness, vertical stratification, and stand competition. To capture a comprehensive view of the trees’ spatial information, we employed the hexadecimal distribution method, effectively quantifying their characteristics across six dimensions. Our study unveiled a significant correlation between spatial structure and stand growth, establishing a connection by integrating the spatial structure with key structural features relevant to tree size. The outcomes of this study shed light on the effectiveness and superiority of the six-element distribution method when it comes to the analysis of forest structural characteristics. Our approach offers valuable insights into the optimization of forest management strategies, encompassing selective harvesting and biodiversity conservation, thereby establishing a solid footing for sustainable forest management practices.

Based on forest management inventory data, this study applies machine learning algorithms to explore the relationships between forest water conservation capacity and forest management inventory factors, thus providing more extensive insights into forest water conservation services. By integrating the InVEST model and machine learning algorithms, this study identifies the key factors related to water conservation services based on forest management inventory factors and investigates the differences in and accuracy of forest water conservation models using the random forest algorithm. The results are as follows: (1) The determination coefficients (R²) of the three machine learning models range from 0.508 to 0.869, with root mean square errors (RMSEs) ranging from 28.380 to 69.339. The performance of these models is generally satisfactory, with the random forest algorithm showing superior results. (2) By leveraging the advantages of the three machine learning algorithms in handling categorical data, this study analyzes the contributions of forest management inventory factors, revealing the impact mechanisms of forest-type water conservation services. (3) The integration of machine learning algorithms allows for better processing of the scale and correlation of independent variables, providing more objective information on the main controlling factors of forest water conservation. (4) Predictions of water conservation capacity using machine learning are consistent with that of the InVEST model. The water conservation per unit area shows a variation trend as follows: slow-growing broadleaf forests > shrub forests > middle-growing broadleaf forests > cunninghamia lanceolata forests > fast-growing broadleaf forests > pine forests > bamboo forests. (5) Since this study considers only the factors available in the forest management inventory, which does not encompass all relevant influencing factors, it is difficult to fully address the complexities of how forest water conservation services interact with forest structure. Therefore, further research is needed to investigate the intrinsic mechanisms underlying the interactions between water conservation and forest management inventory factors.

Accurate estimation of individual tree aboveground biomass (AGB) is essential for understanding forest carbon dynamics, optimizing resource management, and addressing climate change. Conventional methods rely on destructive sampling, whereas unmanned aerial vehicle (UAV) remote sensing provides a non-destructive alternative. In this study, spectral indices, textural features, and canopy height attributes were extracted from high-resolution UAV optical imagery and Light Detection And Ranging (LiDAR) point clouds. We developed an improved YOLOv8 model (NB-YOLOv8), incorporating Neural Architecture Manipulation (NAM) attention and a Bidirectional Feature Pyramid Network (BiFPN), for individual tree detection. Combined with a random forest algorithm, this hybrid framework enabled accurate biomass estimation of Chinese fir, Chinese pine, and larch plantations. NB-YOLOv8 achieved superior detection performance, with 92.3% precision and 90.6% recall, outperforming the original YOLOv8 by 4.8% and 4.2%, and the watershed algorithm by 12.4% and 11.7%, respectively. The integrated model produced reliable tree-level AGB predictions (R² = 0.65–0.76). SHapley Additive exPlanation (SHAP) analysis further revealed that local feature contributions often diverged from global rankings, underscoring the importance of interpretable modeling. These results demonstrate the effectiveness of combining deep learning and machine learning for tree-level AGB estimation, and highlight the potential of multi-source UAV remote sensing to support large-scale, fine-resolution forest carbon monitoring and management.