As a new type of crop protection machinery, the Crop Protection Unmanned Aerial System (CPUAS) has developed rapidly and been widely used in China; currently, how to use the CPUAS scientifically has become a top priority. However, the relationships between the operating parameters of the CPUAS and the effective spraying width (ESW), droplet distribution characteristics, and control effects of insect pests and diseases are not clear yet. Therefore, three levels of flight speed (FS) as 3, 4, and 5 m/s, three levels of flight height (FH) as 1.5, 2.0, and 2.5 m, and spraying volume 2.0 L/min experiments were carried out to investigate the effects of FS and FH on the ESW, droplet deposition uniformity (DDU), and droplet penetration rate (DPR) by using an electric single-rotor CPUAS CE20. Based on the obtained results, combined with the insect pests and diseases occurrence agronomic laws, the optimal operation parameters of the CPUAS were selected to control the wheat aphids, powdery mildew, and head blight. The results showed that the ESW of CE20 was not consistent, the maximum value was 5.78 m, and the minimum one was 2.51 m. The FS had a highly significant impact on ESW (p = 0.0033 < 0.01), while the FH and the interaction between FS and FH had no significant impact on ESW. The coefficients of variation (CV) of the droplet deposition were between 23.3% and 34.4%, which meant good deposition uniformity. The FH (p = 0.0019) and the interaction between FS and FH (p = 0.02) had significant impacts on the DDU. The control effects on aphids were 78.71% (1 day), 84.88% (3 days), and 90.42% (7 days), the control effects on powdery mildew were 77.17% (7 days) and 82.83% (14 days), and the control effect on head blight was 88.32% (20 days). This study proved that by the optimization of parameters and the combination of agronomy, good control effects for insect pests and diseases could be achieved by the CPUAS. The research results would provide some technical supports for CPUAS application.

Dynamic behavior modeling and parameter optimization of the spray boom based on multi-body vibration were developed to study the influence of the boom sprayer’s motion in a complex working environment on the dynamic behavior of the spray boom. First, a geometric continuous model of spray boom vibration was established considering the influence of the boom sprayer body and boom suspension. Then, the dynamic behavior of the spray boom under step excitation was studied on a SWAN3WP-500 self-propelled boom spray experimental platform. The time-domain response of spray boom movement was characterized using a multi-channel dynamic test system, and the simulation results of the geometric continuous model were verified. The correlation coefficient between the simulated and experimental results is 0.917, and the maximum relative error is 12.16%. Finally, the effects of boom sprayer speed, spray boom length, and spray boom cross-section shape on spray boom vibration were analyzed through the geometric continuous model. (1) The amplitude and period of vibration at the extremity of the spray boom gradually decline with a rise in boom sprayer speed. (2) The amplitude and period of vibration at the extremity of the spray boom gradually increase when the unilateral spray boom is shorter than 5 m but slowly decrease when it is longer than 5 m. To avoid excessive static elastic deformation of the spray boom, the length of the unilateral spray boom should be controlled within 6 m. (3) A reasonable cross-sectional shape can improve the spray boom vibration, and the spray boom with a type B cross-section can better inhibit the vertical vibration of the spray boom under the same cross-sectional area.

We propose a Semantic Feature Pyramid Network (FPN)-based algorithm to derive agricultural field boundaries and internal non-planting regions from satellite imagery. It is aimed at providing guidance not only for land use management, but more importantly for harvest or crop protection machinery planning. The Semantic Convolutional Neural Network (CNN) FPN is first employed for pixel-wise classification on each remote sensing image, detecting agricultural parcels; a post-processing method is then developed to transfer attained pixel classification results into closed contours, as field boundaries and internal non-planting regions, including slender paths (walking or water) and obstacles (trees or electronic poles). Three study sites with different plot sizes (0.11 ha, 1.39 ha, and 2.24 ha) are selected to validate the effectiveness of our algorithm, and the performance compared with other semantic CNN (including U-Net, U-Net++, PSP-Net, and Link-Net)-based algorithms. The test results show that the crop acreage information, field boundaries, and internal non-planting area could be determined by using the proposed algorithm in different places. When the boundary number applicable for machinery planning is attained, average and total crop planting area values all remain closer to the reference ones generally when using the semantic FPN with post-processing, compared with other methods. The post-processing methodology would greatly decrease the number of inapplicable and redundant field boundaries for path planning using different CNN models. In addition, the crop planting mode and scale (especially the small-scale planting and small/blurred gap between fields) both make a great difference to the boundary delineation and crop acreage determination.

Pesticide application is an essential means of controlling plant diseases and pests in citrus orchards. In recent years, fixed spraying systems have gradually been used as alternatives to traditional sprayers and manual sprayers in some hilly citrus orchards. In this paper, influences of fixed system spraying parameters, such as droplet size and spraying height, on spraying quality were elucidated and analyzed. The performances of two nozzle types, pressure-swirl nozzles and fixed spray plate sprinklers, were assessed and compared by effective droplet coverage ratio (DCR), droplet distribution uniformity coefficient of variation (CV), and droplet penetration ratio (DPR). The results showed that appropriately increasing droplet size and spraying height could improve the DCR and distribution uniformity of pressure-swirl nozzles. The DCR and distribution uniformity of fixed spray plate sprinklers had a positive correlation with droplet size, while spraying height had no significant effect on these variables. Additionally, with the increase in droplet size, DPR initially increased and then gradually decreased. The optimized results showed that the optimal parameters for pressure-swirl nozzles were a droplet size of 240 μm and spraying height of 100 cm, while for fixed spray plate sprinklers, the results were a droplet size of 240 μm and spraying height of 50 cm. Comparison results showed that the spraying quality of fixed spray plate sprinklers was better overall, with values of DCR, CV, and DPR being 37.15%, 24.20%, and 71.67%, respectively, while the corresponding values for pressure-swirl nozzles were 39.65%, 35.41%, and 56.02%. Based on the above results and the occurrence rule of citrus pests and disease, the optimal spraying parameters of fixed spraying systems were selected to control the Asian citrus psyllid Diaphorina citri. Furthermore, the effect of fixed spraying systems on controlling Diaphorina citri reached the maximum at 3 days after spraying, which was 97.83%, and the effect declined at 14 days after spraying, which was 85.47%. This study provides valuable scientific references for guiding the application of fixed spraying systems in hilly citrus orchards.

Pollination success is essential for hybrid oilseed rape (OSR, Brassica napus) seed production, and the pollination method has some influences on the OSR plant growth traits. In order to explore the roles of different pollination methods, four pollination methods of “unmanned agricultural aerial system” (UAAS), “natural wind + UAAS” (NW+UAAS), “honeybee” (HB), and “no pollinators” (NP) were set in a hybrid OSR field to investigate their effects on OSR plant traits and rapeseed yields in this study. The control check (CK) area with natural wind (NW) pollination was set as a reference for comparison. The experiments were conducted continuously for 20 days during the OSR plant early to full-bloom stage. The results based on the evaluated OSR plants showed that the growth traits and the rapeseed yields exhibited some differences under different pollination methods. The average plant height under NP pollination was maximum, which was 231.52 cm, while the average plant heights under the other pollination methods exhibited nearly no difference. Except for the HB pollination, the average first-branch heights of the evaluated plants all exceeded 100 cm under the other pollination methods. The average once branch quantity of all the evaluated plants under different pollination methods was 5–7. The average number of effective siliques per plant varied greatly. The average quantity of effective siliques in each OSR plant was about 160 under UAAS, NW+UAAS, and NW pollination, about 100 under HB pollination, and only 2.12 under NP pollination. The thousand-rapeseed weight was 7.32 g under HB pollination, which was the highest of all of the pollination areas. In terms of rapeseed yield, the average rapeseed yields per plant were all more than 10 g, except for the one under NP pollination; the yield per hectare was highest under NW+UAAS pollination, reaching 4741.28 kg, and the yield under NP pollination was lowest, which was only 360.39 kg. The research results provide technical support for supplementary pollination in hybrid OSR seed production.

Unmanned aerial vehicle (UAV) remote sensing can reveal spatial variability in maize, but its value depends on whether observations support timely and reliable management. This structured critical review synthesizes UAV applications from stand establishment and canopy development to water and nutrient assessment, stress monitoring, yield prediction, and decision support. The evidence corpus comprised 82 sources, including 51 core maize–UAV studies, evaluated by growth stage, validation strength, and operational endpoint. RGB, multispectral, hyperspectral, thermal, and three-dimensional methods provide complementary information for plant counting, canopy traits, treatment-related water and nitrogen responses, visible stress mapping, and within-experiment yield variation. Most evidence, however, comes from experimental or site-specific settings. Independent testing across sites, years, cultivars, and production environments remains uncommon, as do physiological confirmation of interacting stresses and translation of diagnostic maps into machinery-ready operations. UAV sensing should therefore be viewed as complementary to satellite observations and field scouting, with its advantage determined by target, scale, timing, and decision requirements. Future research should prioritize phenology-aware acquisition, independent field validation, uncertainty relative to management thresholds, interoperable prescription and machinery data, and closed-loop evaluation of input use, crop response, yield, and economic return. These steps are needed to move from high-resolution mapping toward reproducible precision management in maize.