Changes in soybean flower and pod numbers are important factors affecting soybean yields. Obtaining the number of flowers and pods, as well as fallen flowers and pods, quickly and accurately is crucial for soybean variety breeding and high-quality and high-yielding production. This is especially challenging in the natural field environment. Therefore, this study proposed a field soybean flower- and pod-detection method based on an improved network model (YOLOv8-VEW). VanillaNet is used as the backbone feature-extraction network for YOLOv8, and the EMA attention mechanism module is added to C2f, replacing the CioU function with the WIoU position loss function. The results showed that the F1, mAP, and FPS (frames per second) of the YOLOv8-VEW model were 0.95, 96.9%, and 90 FPS, respectively, which were 0.05, 2.4%, and 24 FPS better than those of the YOLOv8 model. The model was used to compare soybean flower and pod counts with manual counts, and its R² for flowers and pods was 0.98311 and 0.98926, respectively, achieving rapid detection of soybean flower pods in the field. This study can provide reliable technical support for detecting soybean flowers and pod numbers in the field and selecting high-yielding varieties.

During hybrid soybean seed production, the parents’ phenotypic consistency is assessed by breeders to ensure the purity of soybean seeds. Detection traits encompass the hypocotyl, leaf, pubescence, and flower. To achieve the detection of hybrid soybean parents’ phenotypic consistency in the field, a self-propelled image acquisition platform was used to obtain soybean plant image datasets. In this study, the Large Selective Kernel Network (LSKNet) attention mechanism module, the detection layer Small Network (SNet), dedicated to detecting small objects, and the Wise Intersection over Union v3 (WIoU v3) loss function were added into the YOLOv5s network to establish the hybrid soybean parent phenotypic consistency detection model SLW-YOLO. The SLW-YOLO achieved the following: F1 score: 92.3%; mAP: 94.8%; detection speed: 88.3 FPS; and model size: 45.1 MB. Compared to the YOLOv5s model, the SLW-YOLO model exhibited an improvement in F1 score by 6.1% and in mAP by 5.4%. There was a decrease in detection speed by 42.1 FPS, and an increase in model size by 31.4 MB. The parent phenotypic consistency detected by the SLW-YOLO model was 98.9%, consistent with manual evaluation. Therefore, this study demonstrates the potential of using deep learning technology to identify phenotypic consistency in the seed production of large-scale hybrid soybean varieties.

The identification of soybean growth periods is the key to timely take field management measures, which plays an important role in improving yield. In order to realize the discrimination of soybean growth periods under complex environments in the field quickly and accurately, a model for identifying soybean growth periods based on multi-source sensors and improved convolutional neural network was proposed. The AlexNet structure was improved by adjusting the number of fully connected layer 1 and fully connected layer 2 neurons to 1024 and 256. The model was optimized through the hyperparameters combination experiment and the classification experiment of different types of image datasets. The discrimination of soybean emergence (VE), cotyledon (VC), and first node (V1) stages was achieved. The experimental results showed that after improving the fully connected layers, the average classification accuracy of the model was 99.58%, the average loss was 0.0132, and the running time was 0.41 s/step under the optimal combination of hyperparameters. At around 20 iterations, the performances began to converge and were all superior to the baseline model. Field validation trials were conducted applying the model, and the classification accuracy was 90.81% in VE, 91.82% in VC, and 92.56% in V1, with an average classification accuracy of 91.73%, and single image recognition time was about 21.9 ms. It can meet the demand for the identification of soybean growth periods based on smart phone and unmanned aerial vehicle (UAV) remote sensing, and provide technical support for the identification of soybean growth periods with different resolutions from different sensors.

To address the issue of improving the accuracy and efficiency of variable-rate application under large-scale field conditions, an RBFNN-SMC variable-rate application control system was designed and experimentally verified. A first-order inertial pure lag model of the spray flow rate was identified through step tests. Based on this, three controllers, namely traditional SMC, fuzzy SMC, and RBFNN-SMC, were designed for comparison. The simulation results indicated that RBFNN-SMC had the shortest adjustment time and the smallest steady-state error under conditions of model uncertainty and time delay. Its maximum overshoot was reduced by 11.2% compared to traditional SMC, and the steady-state error was controlled within ±0.51%. The control strategy was implemented on a microcontroller and integrated with a prescription-based spray system. Field trials showed that the average absolute error of the proposed system in tracking the target flow rate was 3.2%, and it achieved a weed control effect comparable to that of traditional uniform spraying. These results suggest that the RBFNN-SMC-based variable spray rate system can enhance flow rate control performance and support more precise and potentially more sustainable herbicide application, providing a reference and ideas for the research on variable-rate application flow rate control based on prescription maps.

Soybean lodging severely impairs yield and quality, and its precise grading is a key prerequisite for intelligent agricultural management and loss assessment in agricultural insurance. Most existing studies have focused primarily on soybean lodging identification and lodging resistance evaluation, whereas methods for the precise differentiation of lodging grades remain to be refined. This study presents an improved AlexNet model integrated with a Local Feature Aggregation (LFA) attention mechanism and a dynamic optimization strategy for the accurate grading of soybean lodging. RGB imagery of soybean canopies during the grain-filling to early maturity stages was acquired via a multispectral unmanned aerial vehicle (UAV). A dynamic Dropout strategy was adopted to enhance model stability and mitigate overfitting, and the Particle Swarm Optimization (PSO) algorithm was employed to intelligently optimize key hyperparameters of the model. The results demonstrate that the optimized model achieved an overall accuracy of 94.23% on the test set, with an average loss of 0.0682 and an inference speed of 0.422 s/step. In independent field validation, the grading accuracies for the five lodging grades were 90.12%, 86.35%, 89.47%, 88.93%, and 92.76%, respectively, with a mean accuracy of 89.53%. The proposed model enables the rapid and precise grading of soybean lodging under field conditions, thereby providing effective technical support for intelligent field management and disaster loss assessment in soybean production.

Accurate segmentation of multiple phenotypic traits in early-stage soybean plants is essential for automated phenotyping and early-stage breeding analysis. However, the morphological diversity and heterogeneous visual characteristics of key traits, including hypocotyls, flowers, pubescence, and leaves, make unified segmentation challenging under complex backgrounds. To address this problem, this study proposes LASH-SegNet, a lightweight deep learning network for multi-trait segmentation of early-stage soybean plants. The network integrates dynamic snake convolution to model elongated and non-rigid structures and incorporates a SegNeXt-Attention module to enhance multi-scale feature representation and boundary awareness. In addition, the ${\mathrm{W}\mathrm{I}\mathrm{o}\mathrm{U}}_{\mathrm{v}3}$ loss function is adopted to improve localization accuracy and boundary alignment, particularly for slender targets. Experimental results show that LASH-SegNet achieves a precision of 88.82%, recall of 89.78%, and an F1-score of 89.30%, with an mAP50 of 91.24%, while maintaining a compact model size of 5.9 M parameters and 11.3 MB. These results demonstrate that LASH-SegNet provides an accurate and efficient solution for high-throughput multi-trait early-stage soybean plant phenotyping.