Citrus pests pose a major threat to both citrus yield and fruit quality. The early prevention of pests is essential for sustainable citrus cultivation, cost savings, and the reduction of environmental pollution. Despite the increasing application of deep learning techniques in agriculture, the performance of existing models for small target detection of citrus pests is limited, mainly in terms of information bottlenecks that occur during the transfer of information. This hinders its effectiveness in fully automating the detection of citrus pests. In this study, a new approach was introduced to overcome these limitations. Firstly, a comprehensive large-scale dataset named IP-CitrusPests13 was developed, encompassing 13 distinct citrus pest categories. This dataset was amalgamated from IP102 and web crawlers, serving as a fundamental resource for precision-oriented pest detection tasks in citrus farming. Web crawlers can supplement information on various forms of pests and changes in pest size. Using this comprehensive dataset, we employed the SPD Module in the backbone network to preserve fine-grained information and prevent the model from losing important information as the depth increased. In addition, we introduced the AFFD Head detection module into the YOLOv8 architecture, which has two important functions that effectively integrate shallow and deep information to improve the learning ability of the model. Optimizing the bounding box loss function to WIoU v3 (Wise-IoU v3), which focuses on medium-quality anchor frames, sped up the convergence of the network. Experimental evaluation on a test set showed that the proposed SAW-YOLO (SPD Module, AFFD, WIoU v3) model achieved an average accuracy of 90.3%, which is 3.3% higher than the benchmark YOLOv8n model. Without any significant enlargement in the model size, state-of-the-art (SOTA) performance can be achieved in small target detection. To validate the robustness of the model against pests of various sizes, the SAW-YOLO model showed improved detection performance on all three scales of pests, significantly reducing the rate of missed detections. Our experimental results show that the SAW-YOLO model performs well in the detection of multiple pest classes in citrus orchards, helping to advance smart planting practices in the citrus industry.

Tree species classification is an important and challenging task in image recognition and the management of forest resources. Moreover, the task of tree species classification based on remote sensing images can significantly improve the efficiency of the tree species survey and save costs. In recent years, many large models have achieved high accuracy in the task of tree species classification in an airborne remote-sensing manner, but due to their fixed geometric structure, traditional convolutional neural networks are inherently limited to the local receptive field and can only provide segmental context information. The limitation of insufficient context information greatly affects the segmentation accuracy. In this paper, a dual-attention residual network (AMDNet) and a re-parameterized model approach are proposed to capture the global context information, fuse the weight, reduce the model volume, and maintain the computational efficiency. Firstly, we propose MobileNetV2 as the backbone network for feature extraction to further improve the feature identification by modeling semantic dependencies in the spatial dimension and channel dimension and adding the output of the two attention modules. Then, the attention perception features are generated by stacking the attention modules, and the in-depth residual attention network is trained using attention residual learning, through which more accurate segmentation results can be obtained. Secondly, we adopt the approach of structure re-parameterization, use a multi-branch topology for training, carry out weighted averaging on multiple trained models, and fuse multiple branch modules into a completely equivalent module in inference. The proposed approach results in a reduction in the number of parameters and an accelerated inference speed while also achieving improved classification accuracy. In addition, the model training strategy is optimized based on Transformer to enhance the accuracy of segmentation. The model was used to conduct classification experiments on aerial orthophotos of Hongya Forest Farm in Sichuan, China, and the MIOU of tree species recognition using the test equipment reached 93.8%. Compared with current models such as UNet, our model exhibits a better performance in terms of both speed and accuracy, in addition to its enhanced deployment capacity, and its speed advantage is more conducive to real-time segmentation, thereby representing a novel approach for the classification of tree species in remote sensing imagery with significant potential for practical applications.

As an important multipurpose tree species, the growth and development of Quercus robur are significantly influenced by shading conditions. Although the critical role of shading in plant growth and development has been well established, the responses of oak trees to shading remain poorly understood. This study aimed to investigate the physiological and transcriptomic changes in Q. robur under varying shade conditions. Shade had a significant impact on the growth and physiological indicators of Q. robur. As the shading level increased, the plant height, ground diameter, Pn, PRO content, and SOD activity of Q. robur initially increased before subsequently decreasing. In contrast, CHL-a, CHL-b, Car content, SP content, and POD activity exhibited an increasing trend. Transcriptome sequencing was performed on Q. robur samples subjected to different shade treatments: no shade (T1), 40% shade (T3), and 80% shade (T5). Following rigorous quality control, we obtained 57.62 Gb of high-quality sequencing data, and 3,795 DEGs (T1-VS-T3 group), 7,852 DEGs (T1-VS-T5 group), and 7,139 DEGs (T3-VS-T5 group) were identified. KEGG pathway analyses of 978 overlapping DEGs identified crucial involvement of photosynthesis-antenna proteins and plant hormone signal transduction pathways. RT-qPCR validation of six DEGs confirmed the reliability of the transcriptome sequencing data. Notably, we demonstrated significant associations (p < 0.05) between 516 core genes and key growth-physiological traits by correlation analysis. This study provides insights into the patterns of growth changes and physiological responses in Q. robur under shading conditions. Q. robur has adapted to shade conditions by inhibiting photosynthesis, synthesizing chlorophyll and Car, activating the antioxidant system, and regulating osmoregulatory substances. Furthermore, this study elucidated the transcriptional responses of Q. robur to shading, thereby revealing the molecular mechanisms underlying shade adaptation. This research provides a foundational understanding of physiological and molecular mechanisms of Q. robur in shade conditions.

Cunninghamia plays an important role in China’s southern forest industry in the face of increasingly arid climate; thus it is urgent to identify and screen drought-tolerant varieties. In this study, 2-year-old seedlings of C. unica and C. lanceolata from four provenances were subjected to water-break tests, and their physiological responses to different drought conditions were observed. The results showed that with the aggravation of drought stress, C. unica had more stable changes in relative water content (RWC), water potential (Ψw) and intercellular CO₂ concentration (Ci) with more cumulative amounts of proline (PRO) than C. lanceolata, and its H₂O₂ maintained at a lower level, along with antioxidant enzyme activities decreasing later as compared with C. lanceolata. Moreover, comprehensive evaluation showed that C. unica had a higher drought tolerance than C. lanceolata as a whole, which could have been shaped by maintaining Ψw and opening stomata in its relative drought conditions. This work provides a theoretical basis for understanding the drought tolerance of C. unica and C. lanceolate individuals, so as to accelerate selective breeding in Chinese fir.

Quercus palustris possesses significant ecological and ornamental value, yet its clonal propagation remains challenging, hindering germplasm utilization. To address this, an efficient tissue culture propagation system was established. This study systematically evaluated the effects of different plant growth regulator combinations on shoot proliferation, rooting, and callus induction using the Woody Plant Medium (WPM) as the basal culture. The optimal protocol among the tested cytokinin combinations (including 6-benzylaminopurine [6-BA] and kinetin [KT]) for shoot proliferation employed 0.3 mg/L 6-BA and 0.4 mg/L KT, achieving a mean proliferation coefficient of 5.22. For root induction, the most effective treatment consisted of 0.3 mg/L indole-3-butyric acid (IBA) and 0.2 mg/L naphthaleneacetic acid (NAA), yielding a rooting rate of 83.33%. Callus formation was optimally induced by 0.8 mg/L 6-BA combined with 0.3 mg/L NAA, resulting in a high induction rate of 90.63% along with a comparatively low browning incidence of 34.38%. Furthermore, the piperazine derivative fipexide (FPX) exhibited a dual role: promoting callus formation at 10 μmol/L while significantly inhibiting it at concentrations ≥ 20 μmol/L. The established system provides a robust technical foundation for the rapid propagation and germplasm conservation of Quercus palustris.

Chinese fir [Cunninghamia lanceolata (Lamb.) Hook.] is a fast-growing species widely utilized in construction, industrial raw materials. Owing to its broad application scope, research on Chinese fir is fragmented across multiple disciplines, making it difficult to grasp the overall research context and trends. Following the PRISMA guidelines, we retrieved articles related to Chinese fir published between 1942 and 2024 from Chinese databases (i.e., CNKI, Wanfang Data, and VIP Chinese Journal Database) and the Web of Science Core Collection (WOSCC). After removing duplicate and irrelevant records, a total of 7174 valid records were retained, including 5862 from Chinese databases and 1312 from WOSCC. The PRISMA-screened literature was imported into CiteSpace V.6.2.R4 for bibliometric analysis. Through keyword clustering, burst detection, and timeline mapping, we focused on analyzing the domestic resource distribution, research hotspots, and evolutionary trends of Chinese fir research. The results showed that research publications on Chinese fir have increased year by year, and international research started earlier and is more in-depth, while Chinese research covers a wider scope. Both follow two stages (germination and growth). Chinese research focuses on basic application areas such as seedling cultivation and plantation management; international research emphasizes ecological functions and biomass development. Global research exhibits convergence in the field of eco-environmental interactions; specifically, both domestic and international studies investigate the impacts of climate change (e.g., drought and global warming) and nitrogen deposition on the growth and functional evolution of Chinese fir. This study provides references for researchers, forestry policymakers, and planters.