Farmland shelterbelts are important linear vegetation infrastructures in oasis agricultural landscapes. Their accurate extraction is essential for shelterbelt inventory and farmland management, but remains challenging because shelterbelts are narrow, elongated, locally discontinuous, and spectrally similar to croplands, orchards, roadside vegetation, bare soil, and irrigation-related features. This study developed a GF-2-based deep learning workflow for farmland shelterbelt extraction in the 11th Regiment of Alar City, Xinjiang, China. Four representative semantic segmentation models, namely U-Net, U-Net with scSE attention, U-Net++, and DeepLabV3+, were trained and evaluated using four-band GF-2 optical imagery under a unified experimental setting. Model performance was assessed using Precision, Recall, F1-score, Intersection over Union (IoU), overall accuracy, and Kappa coefficient. Patch-level statistical comparison and visual interpretation were further conducted to examine performance differences, shelterbelt continuity, boundary integrity, omission errors, and background confusion. The results showed that U-Net achieved the best overall performance, with a Precision of 94.58%, Recall of 94.77%, F1-score of 94.67%, IoU of 89.88%, overall accuracy of 99.71%, and Kappa coefficient of 0.9452. Compared with U-Net with scSE attention, U-Net++, and DeepLabV3+, U-Net better preserved the continuity and boundary integrity of narrow shelterbelts in regular field-boundary networks. The other models showed varying degrees of omission, boundary fragmentation, or confusion with spectrally similar agricultural objects. The best-performing U-Net model was then applied to the complete study area, and the extracted shelterbelt area was approximately 6.5 km², accounting for about 4.37% of the cultivated land area. These results indicate that GF-2 optical imagery combined with semantic segmentation can support fine-scale farmland shelterbelt mapping in oasis agricultural landscapes. They also show that model evaluation for narrow linear vegetation features should consider not only pixel-level accuracy but also spatial continuity, boundary integrity, and typical error patterns. The proposed workflow provides a practical reference for GF-2-based farmland shelterbelt inventory, high-resolution linear vegetation mapping, and shelterbelt monitoring in arid oasis agricultural landscapes.

To quantify the spatial and lagged associations between ecological water conveyance and fractional vegetation cover (FVC) in Populus euphratica Oliv. forests, we integrated Landsat imagery (1995–2025), conveyance records, groundwater observations, and multi-period random forest classifications in the lower Tarim River. Newly formed or expanded surface water was mapped within dynamic annual response windows and characterized by annual surface inundation expansion area, multi-year inundation frequency, and distance from forest pixels to recurrently inundated water surfaces. These metrics were related to FVC using Theil–Sen trends and Lag 0–Lag 3 correlations. After 2010, reservoir releases, annual surface inundation expansion area, and groundwater conditions generally improved. Mean FVC increased by 0.182 percentage points per year, with improvement and degradation interspersed spatially. Relatively low- to moderate-frequency inundation was associated with pronounced positive FVC trends, and FVC improvement was concentrated within 0–0.5 km of recurrently inundated water surfaces. Associations of FVC with reservoir releases, groundwater depth, and annual surface inundation expansion area were strongest after 2–3 years. Together, these surface inundation metrics complement reservoir-release and groundwater records and support spatially differentiated monitoring of FVC changes in P. euphratica forests.