In densely planted solar greenhouses, tomato crops face increasing challenges with pest and disease control due to high temperature and humidity conditions. The existing spraying equipment often suffers from low mechanization and inadequate foliar deposition coverage. This study presents the design of a vertical spray bar electrostatic sprayer, which combines a multi-nozzle vertical spray bar with electrostatic spraying technology, making it suitable for greenhouse applications. In order to obtain the best working parameters of the sprayer, the coverage rate of the front and back sides of the tomato leaves was taken as the performance target. Key influencing factors, including electrostatic voltage, spray pressure, and target distance, were investigated using a multi-factor response surface methodology. Field experiments were conducted in a greenhouse environment based on the optimized parameters to validate the performance. The results indicate that: (1) The factors influencing droplet adherence on the upper surface of tomato leaves ranked in the order of target distance, spray pressure, and electrostatic voltage, while for the underside, the order was electrostatic voltage, target distance, and spray pressure. (2) Under the conditions of electrostatic voltage of 10 kV, spray pressure of 0.7 MPa, and target distance of 35 cm, the sprayer achieves the optimal operation of leaf comprehensive coverage. (3) Compared to non-electrostatic spraying, the greenhouse electrostatic sprayer significantly improved the coverage on both sides of the leaves, enhancing pesticide utilization efficiency. This novel electrostatic sprayer meets the operational requirements for greenhouse crop protection in the Xinjiang region of China.

Mulch-film covering technology has been widely adopted in cotton production in arid regions; however, the associated problem of residual-film pollution has become increasingly prominent, creating an urgent demand for efficient and accurate monitoring approaches. Owing to the small target scale, irregular morphology, blurred boundaries, and complex soil backgrounds of residual-film fragments, residual-film detection based on close-range UAV imagery remains a challenging task. To address these issues, this study proposes an improved algorithm, termed YOLO-EGASF, for residual-film detection in arid-region cotton fields, built upon the lightweight YOLOv11n framework. To enhance the detection of small targets with weak boundary characteristics, the baseline model is improved from three aspects. First, a boundary-enhanced multi-branch small-target extraction module (EMSE) is designed to reinforce shallow-layer details and gradient information through multi-scale convolution and explicit edge enhancement. Second, a GLoCA attention module that integrates global coordinate information with local geometric features is constructed to improve the discriminative capability of the model for residual-film targets under complex background conditions. Third, an ASF-layer multi-scale feature fusion structure is introduced, together with an additional small-target detection layer, to strengthen the participation of high-resolution features in cross-scale fusion and prediction. Experimental results on a self-constructed UAV-based residual-film dataset from cotton fields demonstrate that YOLO-EGASF outperforms several mainstream detection models in terms of Precision, Recall, mAP@0.5, and mAP@0.5:0.95, achieving mAP@0.5 and mAP@0.5:0.95 values of 71.9% and 26.8%, respectively. These results indicate a significant improvement in detection accuracy and robustness, confirming that the proposed method can effectively meet the practical requirements of fine-grained residual-film monitoring in arid-region cotton fields.