As the main area for photosynthesis in trees, the canopy absorbs a large amount of carbon dioxide and plays an irreplaceable role in regulating the carbon cycle in the atmosphere and mitigating climate change. Therefore, monitoring the growth of the canopy is crucial. However, traditional field investigation methods are often limited by time-consuming and labor-intensive methods, as well as limitations in coverage, which may result in incomplete and inaccurate assessments. In response to the challenges encountered in the application of tree crown segmentation algorithms, such as adhesion between individual tree crowns and insufficient generalization ability of the algorithm, this study proposes an improved algorithm based on Mask R-CNN (Mask Region-based Convolutional Neural Network), which identifies irregular edges of tree crowns in RGB images obtained from drones. Firstly, it optimizes the backbone network by improving it to ResNeXt and embedding the SENet (Squeeze-and-Excitation Networks) module to enhance the model’s feature extraction capability. Secondly, the BiFPN-CBAM module is introduced to enable the model to learn and utilize features more effectively. Finally, it optimizes the mask loss function to the Boundary-Dice loss function to further improve the tree crown segmentation effect. In this study, TCSNet also incorporated the concept of panoptic segmentation, achieving the coherent and consistent segmentation of tree crowns throughout the entire scene through fine tree crown boundary recognition and integration. TCSNet was tested on three datasets with different geographical environments and forest types, namely artificial forests, natural forests, and urban forests, with artificial forests performing the best. Compared with the original algorithm, on the artificial forest dataset, the precision increased by 6.6%, the recall rate increased by 1.8%, and the F₁-score increased by 4.2%, highlighting its potential and robustness in tree detection and segmentation.

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.

This paper presents a method for predicting the total nitrogen content in sandalwood using digital image processing. The goal of this study is to provide a real-time, efficient, and highly automated nutritional diagnosis system for producers by analyzing images obtained in forests. Using images acquired from field servers, which were installed in six forest farms of different cities located in northern Hainan Province, we propose a new segmentation algorithm and define a new indicator named “growth status" (GS), which includes two varieties: GS_MER (the ratio of sandalwood pixels to the minimum enclosing rectangle pixels) and GS_MCC (the ratio of sandalwood pixels to minimum circumscribed circle pixels). We used the error-in-variable model by considering the errors that exist in independent variables. After comparison and analysis, the obtained results show that (1) The b and L channels in the Lab color system have complementary advantages. By combining this system with the Otsu method, median filtering and a morphological operation, sandalwood can be separated from the background. (2) The fitting degree of the models improves after adding the GS indicator and shows that GS_MCC performs better than GS_MER. (3) After using the error-in-variable model to estimate the parameters, the accuracy and precision of the model improved compared to the results obtained using the least squares method. The optimal model for predicting the total nitrogen content is . This study demonstrates the use of Internet of Things technology in forestry and provides guidance for the nutritional diagnosis of the important sandalwood tree species.

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.

As climate change intensifies the frequency and magnitude of extreme weather events, such as storm surges, understanding how extreme weather events alter mangrove carbon dynamics is critical for predicting the resilience of blue carbon ecosystems under climate change. Mangrove forests are generally recognized for their resilience to natural disturbances, a characteristic largely attributed to the evolutionary development of species-specific functional traits. However, limited research has explored the impacts of storm surges on carbon flux dynamics in both natural and restored mangrove ecosystems. In this study, we analyzed short-term responses of storm surges on carbon dioxide flux and methane flux in natural and restored mangroves. The results revealed that following the storm surge, CO₂ uptake decreased by 51% in natural mangrove forests and increased by 20% in restored mangroves, while CH₄ emissions increased by 14% in natural mangroves and decreased by 22% in restored mangroves. GPP is mainly driven by PPFD and negatively affected by VPD and RH, while Reco and CH₄ flux respond to a combination of temperature, humidity, and hydrological factors. NEE is primarily controlled by GPP and Reco, with environmental variables acting indirectly. These findings highlight the complex, site-specific pathways through which extreme events regulate carbon fluxes, underscoring the importance of incorporating ecological feedbacks into coastal carbon assessments under climate change.