Olive trees, which are planted widely in China, are economically significant. Timely and accurate acquisition of olive tree crown information is vital in monitoring olive tree growth and accurately predicting its fruit yield. The advent of unmanned aerial vehicles (UAVs) and deep learning (DL) provides an opportunity for rapid monitoring parameters of the olive tree crown. In this study, we propose a method of automatically extracting olive crown information (crown number and area of olive tree), combining visible-light images captured by consumer UAV and a new deep learning model, U²-Net, with a deeply nested structure. Firstly, a data set of an olive tree crown (OTC) images was constructed, which was further processed by the ESRGAN model to enhance the image resolution and was augmented (geometric transformation and spectral transformation) to enlarge the data set to increase the generalization ability of the model. Secondly, four typical subareas (A–D) in the study area were selected to evaluate the performance of the U²-Net model in olive crown extraction in different scenarios, and the U²-Net model was compared with three current mainstream deep learning models (i.e., HRNet, U-Net, and DeepLabv3+) in remote sensing image segmentation effect. The results showed that the U²-Net model achieved high accuracy in the extraction of tree crown numbers in the four subareas with a mean of intersection over union (IoU), overall accuracy (OA), and F1-Score of 92.27%, 95.19%, and 95.95%, respectively. Compared with the other three models, the IoU, OA, and F1-Score of the U²-Net model increased by 14.03–23.97 percentage points, 7.57–12.85 percentage points, and 8.15–14.78 percentage points, respectively. In addition, the U²-Net model had a high consistency between the predicted and measured area of the olive crown, and compared with the other three deep learning models, it had a lower error rate with a root mean squared error (RMSE) of 4.78, magnitude of relative error (MRE) of 14.27%, and a coefficient of determination (R²) higher than 0.93 in all four subareas, suggesting that the U²-Net model extracted the best crown profile integrity and was most consistent with the actual situation. This study indicates that the method combining UVA RGB images with the U²-Net model can provide a highly accurate and robust extraction result for olive tree crowns and is helpful in the dynamic monitoring and management of orchard trees.

This paper investigates the changes in species diversity and the spatial pattern of the population of a moso bamboo (Phyllostachys edulis) forest community in the Wuyi Mountain Nature Reserve in Fujian Province, China. Using the method of space–time substitution, the composition of species and changes in the spatial patterns of different communities were analyzed by taking Phyllostachys edulis mixed forests after 0, 3, 5, 10, 15, and 40 years of enclosure as the survey object. The results showed that as the number of years of enclosure extended, the important values of the Japanese bay tree (Machilus thunbergii Sieb. & Zucc.), chinquapin (Castanopsis faberi Hance), and Masson’s pine (Pinus massoniana Lamb.) increased continuously. These trees became the dominant species of mature forest after 40 years of enclosure. The species diversity of mature and young trees in the community generally increased in parallel with the years of enclosure, and the species diversity of the shrubs generally increased first and then decreased as the number of years of enclosure increased. With the extension of enclosure years, the average diameter at breast height of the mature trees tended to increase, indicating that there were increasing advantages of mature growth as the time of enclosure increased. With the extension of enclosure years, the pattern of spatial distribution of the mature trees in the forest community was generally an aggregated distribution. The Phyllostachys edulis forest community under the prolonged enclosure conditions responded in a positive direction and ultimately formed a more stable Phyllostachys edulis mixed forest community.

The growth dynamics of Ma bamboo (Dendrocalamus latiflorus Munro) are intricately linked to nitrogen availability, a pivotal nutrient. Escalating global nitrogen deposition, primarily driven by anthropogenic factors, is reshaping nutrient fluxes and productivity within forest and bamboo ecosystems. Such alterations bear significant implications for the growth equilibrium and yields of rapid-growth species such as Ma bamboo, thereby influencing their sustainable management strategies. This investigation delves into the responses of Ma bamboo under varying nitrogen deposition scenarios (0 g·clump⁻¹, 11.2 g·clump⁻¹, 13.5 g·clump⁻¹, and 22.5 g·clump⁻¹), examining stoichiometric attributes in bamboo shoots, leaves, and soil across distinct growth phases. Our empirical findings reveal that in the early growth stage, nitrogen enrichment markedly augmented N and P concentrations in the foliage and shoots, alongside a corresponding enhancement in soil P content. This was paralleled by a substantial reduction in the C:N ratio in leaves and the C:P ratio in shoots and soil, indicating an amplified uptake of P and N in both plant and soil matrices. During the middle stage, all nitrogen treatments boosted nitrogen levels across various plant tissues, while concurrently, soil C content exhibited a notable decline with increased nitrogen supplementation. In the late stage, leaf and soil N content continued to ascend; however, alterations in C content in both soil and leaves were not pronounced. Contrastingly, N and P levels in shoots showed a gradual decrement. Yield assessments disclosed that during the early stage, the N3 treatment (22.5 g·clump⁻¹) not only delayed shoot emergence by 14 days but also surged the yield by 115.87% in comparison to the control (CK). In the late stage, the N2 treatment (13.5 g·clump⁻¹) extended emergence duration by 10 days, with the yield apex under N3 treatment (22.5 g·clump⁻¹) evidencing a 116.67% yield augmentation over CK. In summation, this study elucidates the stoichiometric balancing and distribution strategies within the plant–soil system of Ma bamboo, investigating its adaptability and responsive feedback to diverse nitrogen deposition gradients. This research contributes to a deeper understanding of plant nutrient adaptation mechanisms in the context of nitrogen deposition, enriches the discourse on plant population stoichiometry, and offers valuable insights and scientific underpinnings for broader-scale community or ecosystem stoichiometry studies.