Abstract: Desert shrubs are indispensable in maintaining ecological stability by reducing soil erosion, enhancing water retention, and boosting soil fertility, which are critical factors in mitigating desertification processes. Due to the complex topography, variable climate, and challenges in field surveys in desert regions, this paper proposes YOLO-Desert-Shrub (YOLO-DS), a detection method for identifying desert shrubs in UAV remote sensing images based on an enhanced YOLOv8n framework. This method accurately identifying shrub species, locations, and coverage. To address the issue of small individual plants dominating the dataset, the SPDconv convolution module is introduced in the Backbone and Neck layers of the YOLOv8n model, replacing conventional convolutions. This structural optimization mitigates information degradation in fine-grained data while strengthening discriminative feature capture across spatial scales within desert shrub datasets. Furthermore, a structured state-space model is integrated into the main network, and the MambaLayer is designed to dynamically extract and refine shrub-specific features from remote sensing images, effectively filtering out background noise and irrelevant interference to enhance feature representation. Benchmark evaluations reveal the YOLO-DS framework attains 79.56% mAP40weight, demonstrating 2.2% absolute gain versus the baseline YOLOv8n architecture, with statistically significant advantages over contemporary detectors in cross-validation trials. The predicted plant coverage exhibits strong consistency with manually measured coverage, with a coefficient of determination (R²) of 0.9148 and a Root Mean Square Error (RMSE) of 1.8266%. The proposed UAV-based remote sensing method utilizing the YOLO-DS effectively identify and locate desert shrubs, monitor canopy sizes and distribution, and provide technical support for automated desert shrub monitoring.

Key words: Desert shrubs, Deep learning, Object detection, UAV remote sensing, YOLOv8, Mamba