Fertilizer structure has been confined to the fertilization mode for summer corn in the Huang-Huai-Hai region of China, such as one-time basal application ("one-shot") or base-topdressing splits. There has been a serious mismatch between nutrient supply and crop demand in recent years. This study aims to propose the V-shaped layered fertilization and its mechanical supporting device. The spatial distribution of the layered fertilization was integrated with the controlled release of the specialized fertilizers. A systematic investigation was conducted using pot experiments, device design, discrete element simulation, and field validation. In the pot experiments, seven treatments (CK, T2, T3, T4, T5, T6, and T7) were carried out to investigate the effects of different fertilizer types (conventional and controlled-release urea) and application modes (single-side, bilateral, and bottom) on the maize agronomic features, soil nitrogen dynamics ammonium-N and nitrate-N, and crop yield. A V-shaped layered fertilization planter was designed with the optimal fertilization strategy (T7) that was identified from the pot experiments. Its core component, the double-disc opener, was theoretically analyzed to determine the structural parameters (the disc diameter and disc angle) and operational parameters (the forward speed). A simulation model of the opener-soil-fertilizer interaction was established using the discrete element method (EDEM). A quadratic orthogonal rotational combination was employed with the disc diameter, disc angle, and forward speed as the experimental factors, while the operational resistance and fertilization qualification rate as the performance indicators. Regression models were developed and then optimized to determine the optimal parameters. Field trials were carried out to verify the operational performance of the prototype with the optimal parameters. Fertilization positioning accuracy was achieved to clarify the impact on the root development and final yield. The pot experiment results showed that compared with other treatments, the T7 treatment (controlled-release urea combined with conventional phosphorus and potassium fertilizers applied in bilateral and bottom layers at a ratio of 30%, 30% and 40%) increased the stem diameter, leaf area and chlorophyll content of maize. More importantly, this treatment could maintain a relatively high level of soil ammonium nitrogen and nitrate nitrogen in the late growth stage of maize, effectively prevent the occurrence of nitrogen deficiency, and realize the matching of nutrient release with crop demand. Ultimately, the maize yield in the T7 treatment reached 31.7050 g, which was significantly higher than that in all other treatments (P＜0.05). Simulation results were derived into the optimal combination of the parameters: The disc diameter of 360.75 mm, disc angle of 10.97°, and forward speed of 4.26 km/h. The predicted operational resistance was 239.71 N, and the fertilization qualification rate was 95.69% under the optimal combination of the parameters. Field tests confirmed that the highly accurate positions of the fertilization were measured with an average vertical distance of 39.6 mm for the side fertilizer to the seed, a horizontal distance of 99.4 mm between side fertilizer bands, and a vertical distance of 110.7 mm for the base fertilizer to the seed. All parameters were within a 10 mm error margin from the design targets, indicating the high performance of the device. The trials demonstrated that the V-shaped fertilization (VF) treatment significantly promoted the root growth, thus resulting in longer, denser root systems with more aerial roots, compared with the conventional fertilization (CF). Ultimately, the VF treatment achieved a 100-grain weight of 37.42 g and a yield of 11 100 kg/hm², which were significantly greater than the CF treatment's 31.85 g and 9 520 kg/hm² (P＜0.05), indicating a yield increase of 16.6%. The VF treatment with the controlled-release and conventional fertilizers was effectively achieved in the precise spatial and temporal nutrient supply, thereby enhancing the nitrogen utilization efficiency, maize root and shoot development, as well as the yield. The supporting device was optimized through discrete element simulation. Features rational design and stable performance fully meet the agronomic requirements for precise fertilization. This finding can provide a theoretical foundation and effective technical solution for simplified, efficient, and high-yielding maize cultivation.

Maize and weed identification can often require for the high accuracy under varying lighting conditions, particularly at the seedling stage of the maize growth. In this study, an accurate and rapid detection method was proposed to detect the maize and weeds in the field using the WEED-YOLOv10 framework. Detection performance was then enhanced to maintain the computational efficiency. High-resolution images were captured from the field using UAVs. A dataset was then constructed for the maize and its weeds. The YOLOv10 architecture was served as the baseline. But its backbone network was replaced with the ConvNeXtV2, in order to extract the detailed features from the input images. Convolutional block attention module (CBAM) was integrated into the network, in order to further enhance the robustness against lighting disturbances. This module was also focused the attention on the most relevant features in the image. Irrelevant information was mitigated to improve the model performance under diverse environments. Additionally, a SlimNeck structure was introduced to optimize the computational efficiency of the network. Unnecessary processing was then reduced to maintain the high feature representation. Focaler-EIoU loss function was incorporated to improve the localization accuracy. Precise identification was realized on both maize and weed instances, even in challenging scenarios. Experimental results demonstrated that the WEED-YOLOv10 outperformed the baseline model over several key evaluation metrics. The high accuracy reached 85.4%, the recall rate of 88.1%, and the mean average precision (mAP) of 90.9% at an intersection over union (IoU) threshold of 50% (mAP@50). Significant improvements were achieved in the mAP at the IoU thresholds from 50% to 95% (mAP@50:95), with a score of 48.5%. The F1-Score was 86.7%, indicating the high performance to balance the precision and recall. Compared with the baseline, the WEED-YOLOv10 model was improved by 2.4, 2.9, 3.5, 7, and 2.6 percentage points of accuracy, recall, mAP@50, mAP@50:95, and F1-score, respectively. The inference speed was also highly optimized as 28.7 frames per second, when deployed on an NVIDIA Jetson Orin NX. The weed detection was obtained to balance the speed and accuracy in real time. In addition, the targeted pesticide spraying was integrated to capture the recognition signals. The herbicide application was precisely controlled using the output, in order to treat only weeds rather than the maize plants. Field tests demonstrated that the spraying system achieved a high spraying accuracy of 93.7%, a coverage rate of 90.5%, and a target deviation of only 1.45 cm. The weed was detected at a speed of 20.10 frames per second, suitable for the weed control in maize fields. A reliable and efficient solution can be offered for the weed detection under complex lighting conditions. The high speed, accuracy and precision of the weed control can greatly contribute to the field operations in intelligent farming. The WEED-YOLOv10 system can be expected for the more sustainable, precise and efficient agricultural practices. This finding can also provide the high productivity and resource management in precision agriculture.