Leaf chlorophyll content (LCC) is a key indicator in representing the photosynthetic capacity of Populus deltoides (Populus deltoides Marshall). Unmanned aerial vehicle (UAV) hyperspectral imagery provides an effective approach for LCC estimation, but the issue of band redundancy significantly impacts model accuracy and computational efficiency. Commonly used single feature selection algorithms not only fail to balance computational efficiency with optimal set search but also struggle to combine different regression algorithms under dynamic set conditions. This study proposes an ensemble feature selection framework to enhance LCC estimation accuracy using UAV hyperspectral data. Firstly, the embedded algorithm was improved by introducing the SHapley Additive exPlanations (SHAP) algorithm into the ranking system. A dynamic ranking strategy was then employed to remove bands in steps of 10, with LCC models developed at each step to identify the initial band subset based on estimation accuracy. Finally, the wrapper algorithm was applied using the initial band subset to search for the optimal band subset and develop the corresponding model. Three regression algorithms including gradient boosting regression trees (GBRT), support vector regression (SVR), and gaussian process regression (GPR) were combined with this framework for LCC estimation. The results indicated that the GBRT-Optimal model developed using 28 bands achieved the best performance with R² of 0.848, RMSE of 1.454 μg/cm² and MAE of 1.121 μg/cm². Compared with a model performance that used all bands as inputs, this optimal model reduced the RMSE value by 24.37%. In addition to estimating biophysical and biochemical parameters, this method is also applicable to other hyperspectral imaging tasks.

To determine optimal light conditions for Hopea hainanensis Merr. & Chun seedling growth, this study examined growth and physiological parameters under four shading treatments (0%, 30%, 60%, and 90% irradiance reduction) over 12 months. Shading significantly affected the growth adaptability of seedlings. As shading increased, height, leaf traits (area, length, width), and light saturation point all initially increased, peaked at 30% shading, and then decreased. Conversely, basal diameter, leaf thickness, the maximum net photosynthetic rate, net photosynthetic rate, photosynthetic quantum efficiency, transpiration rate, and stomatal conductance progressively declined as shading increased. Biomass accumulation (in stems and roots), dark respiration rate, and light compensation point exhibited a U-shaped response to shading, being minimized under low or moderate shading. All shading treatments significantly reduced biomass and photosynthetic performance compared to controls. Multivariate analysis identified 0%–30% shading as optimal for cultivation, with 30% shading enhancing photomorphogenic responses while maintaining photosynthetic efficiency. The study findings suggest a novel seedling cultivation protocol for nursery use, in which initial establishment occurs under 30% shading to maximize vertical elongation, followed by the progressive reduction in shading to stimulate radial growth and optimal biomass partitioning. This approach mimics natural canopy gap dynamics, effectively mimicking natural regeneration in tropical rainforest ecosystems.

Accurate forest type classification in subtropical regions is essential for ecological monitoring and sustainable management. Multimodal remote sensing data provide rich information support, yet the synergy between network architectures and fusion strategies in deep learning models remains insufficiently explored. This study established a multimodal deep learning framework with integrated interpretability analysis by combining high-resolution Beijing-2 RGB imagery, Sentinel-1 data, and time-series Sentinel-2 NDVI data. Two representative architectures (U-Net and Swin-UNet) were systematically combined with three fusion strategies, including feature concatenation (Concat), gated multimodal fusion (GMU), and Squeeze-and-Excitation (SE). To quantify feature contributions and decision patterns, three complementary interpretability methods were also employed: Shapley Additive Explanations (SHAP), Grad-CAM++, and occlusion sensitivity. Results show that Swin-UNet consistently outperformed U-Net. The SwinUNet-SE model achieved the highest overall accuracy (OA) of 82.76%, exceeding the best U-Net model by 3.34%, with the largest improvement of 5.8% for mixed forest classification. The effectiveness of fusion strategies depended strongly on architecture. In U-Net, SE and Concat improved OA by 0.91% and 0.23% compared with the RGB baseline, while GMU slightly declined. In Swin-UNet, all strategies achieved higher gains between 1.03% and 2.17%, and SE effectively reduced NDVI sensitivity. SHAP analysis showed that RGB features contributed most (values > 0.0015), NDVI features from winter and spring ranked among the top 50%, and Sentinel-1 features contributed less. These findings reveal how architecture and fusion design interact to enhance multimodal forest classification.

The real-time nondestructive monitoring of plant water content can enable operators to understand the water demands of crops in a timely manner and provide a reliable basis for precise irrigation. In this study, a method for rapid estimation of water content in Aquilaria sinensis using multispectral imaging was proposed. First, image registration and segmentation were performed using the Fourier–Mellin transform (FFT) and the fuzzy local information c-means clustering algorithm (FLICM). Second, the spectral features (SFs), texture features (TFs), and comprehensive features (CFs) of the image were extracted. Third, using the eigenvectors of the SFs, TFs, and CFs as input, a random forest regression model for estimating the water content of A. sinensis was constructed, respectively. Finally, the monarch butterfly optimization (MBO), Harris hawks optimization (HHO), and sparrow search algorithm (SSA) were used to optimize all models to determine the best estimation model. The results showed that: (1) 60%–80% soil water content is the most suitable for A. sinensis growth. Compared with waterlogging, drought inhibited A. sinensis growth more significantly. (2) FMT + FLICM could achieve rapid segmentation of discrete A. sinensis multispectral images on the basis of guaranteed accuracy. (3) The prediction effect of TFs was basically the same as that of SFs, and the prediction effect of CFs was higher than that of SFs and TFs, but this difference would decrease with the optimization of the RFR model. (4) Among all models, SSA-RFR_CFs had the highest accuracy, with an R² of 0.8282. These results confirmed the feasibility and accuracy of applying multispectral imaging technology to estimate the water content of A. sinensis and provide a reference for the protection and cultivation of endangered precious tree species.

Cephalotaxus hainanensis, a valuable medicinal and endangered conifer, requires scientific conservation and precision management to ensure the sustainable utilization of its genetic and ecological resources. Nitrogen (N) is a key nutrient that regulates plant growth and metabolism; rapid and accurate nitrogen diagnosis is vital for optimizing fertilization, reducing nutrient losses, and promoting healthy plant development. This study employed a combined approach integrating stepwise regression, correlation analysis, and Least Absolute Shrinkage and Selection Operator (LASSO) regression to identify leaf color features strongly correlated with leaf nitrogen content (LNC). A support vector regression (SVR) model, suitable for small-sample datasets, was then employed to accurately estimate LNC across canopy layers. Nine color variables were found to be highly associated with LNC, among which the Green Minus Blue index (GMB) consistently appeared across all correlation methods, demonstrating strong robustness and generality. Color features effectively reflected LNC variations among nitrogen treatments—especially between N1 and N4—and across canopy layers, with the most pronounced contrasts observed between upper and lower leaves. The Spearman-based SVR model revealed that the middle canopy maintained the highest and most stable LNC. However, the lower leaves were most sensitive to nitrogen deficiency, while the upper leaves were more sensitive to nitrogen excess. Comprehensive analysis identified N2 as the optimal nitrogen treatment, representing a balanced nutrient state. Overall, this study confirms the reliability of color features for LNC estimation and highlights the importance of vertical canopy LNC distribution in nitrogen diagnostics, providing a theoretical and methodological foundation for color-based nitrogen diagnosis and precision nutrient management in evergreen conifers.

Monitoring tree growth helps operators better understand the growth mechanism of trees and the health status of trees and to formulate more effective management measures. Computer vision technology can quickly restore the three-dimensional geometric structure of trees from two-dimensional images of trees, playing a huge role in planning and managing tree growth. This study used binocular reconstruction technology to measure the height, canopy width, and ground diameter of Castanopsis hystrix and compared the growth differences under different nitrogen levels. In this research, we proposed a wavelet exponential decay thresholding method for image denoising. At the same time, based on the traditional semi-global matching (SGM) algorithm, a cost search direction is added, and a multi-line scanning semi-global matching (MLC-SGM) algorithm for stereo matching is proposed. The results show that the wavelet exponential attenuation threshold method can effectively remove random noise in red cone images, and the denoising effect is better than the traditional hard-threshold and soft-threshold denoising methods. The disparity images produced by the MLC-SGM algorithm have better disparity continuity and noise suppression than those produced by the SGM algorithm, with more minor measurement errors for C. hystrix growth factors. Medium nitrogen fertilization significantly promotes the height, canopy width, and ground diameter growth of C. hystrix. However, excessive fertilization can diminish this effect. Compared to tree height, excessive fertilization has a more pronounced impact on canopy width and ground diameter growth.