Farmland shelterbelts are crucial elements in safeguarding agricultural ecological security and sustainable development, with their precise extraction being vital for regional ecological monitoring and precision agriculture management. However, constrained by their narrow linear distribution, complex farmland backgrounds, and spectral confusion issues, traditional remote sensing methods encounter significant challenges in terms of accuracy and generalization capability. In this study, six representative deep learning semantic segmentation models—U-Net, Attention U-Net (AttU_Net), ResU-Net, U²-Net, SwinUNet, and TransUNet—were systematically evaluated for farmland shelterbelt extraction using high-resolution Gaofen-6 imagery. Model performance was assessed through four-fold cross-validation and independent test set validation. The results indicate that convolutional neural network (CNN)-based models show overall better performance than Transformer-based architectures; on the independent test set, the best-performing CNN model (U-Net) achieved a Dice Similarity Coefficient (DSC) of 91.45%, while the lowest DSC (88.86%) was obtained by the Transformer-based TransUNet model. Among the evaluated models, U-Net demonstrated a favorable balance between accuracy, stability, and computational efficiency. The trained U-Net was applied to large-scale farmland shelterbelt mapping in the study area (Alar City, Xinjiang), achieving a belt-level visual accuracy of 95.58% based on 385 manually interpreted samples. Qualitative demonstrations in Aksu City and Shaya County illustrated model transferability. This study provides empirical guidance for model selection in high-resolution agricultural remote sensing and offers a feasible technical solution for large-scale and precise farmland shelterbelt extraction.

Populus euphratica (P. euphratica) is a dominant tree species in the arid and semi-arid regions along the main stem of the Tarim River. This study aims to explore the response of microbial communities in the rhizosphere soil of P. euphratica to varying groundwater depths (GWD) and to elucidate the ecological functions of key microbial groups in drought resistance. We established three groundwater depth levels (3.8 m, 5.4 m, and 7.35 m) and employed metagenomic sequencing technology to systematically analyze the topological characteristics of functional microbial community networks, as well as the types and quantities of key microbial groups in the rhizosphere soil of P. euphratica under different GWD conditions. The results indicate that compared to GWDs of 3.8 m and 7.35 m, the average degree and graph density of microbial communities in the rhizosphere soil of P. euphratica at a depth of 5.4 m are the highest. This suggests that at a GWD of 5.4 m, the connectivity and stability of the microbial network structure in the rhizosphere soil of P. euphratica are significantly enhanced. Analysis of the Zi-Pi values within the microbial network structure reveals that, compared to GWDs of 3.8 m and 7.35 m, a depth of 5.4 m supports the greatest variety and quantity of key microbial species in the rhizosphere soil of P. euphratica. The four connecting nodes identified are Actinophytocola, Haladaptatus, Devosia and Pseudonocardia. Spearman correlation analysis demonstrates that the relative abundance of the key bacterial genus Mesorhizobium in the rhizosphere soil of P. euphratica at different GWD is significantly positively correlated with soil catalase (CAT) and urease (UE) activity. Furthermore, the relative abundance of the key bacterial genus Pseudonocardia shows a significant positive correlation with soil total nitrogen (TN) and ammonium nitrogen (NH₄⁺-N) (p < 0.05). The relative abundance of the key bacterial genus Devosia exhibits a highly significant positive correlation with soil water content (SWC) (p < 0.01) and a significant negative correlation with soil NH₄⁺-N (p < 0.05). Additionally, the relative abundance of Devosia is significantly positively correlated with soil CAT (p < 0.05). This study provides a theoretical foundation for the conservation of desert poplar forests in arid regions and for the identification and cultivation of specific key microbial communities in the rhizosphere soil of P. euphratica.