Efficient detection and evaluation of soybean seedling emergence is an important measure for making field management decisions. However, there are many indicators related to emergence, and using multiple models to detect them separately makes data processing too slow to aid timely field management. In this study, we aimed to integrate several deep learning and image processing methods to build a model to evaluate multiple soybean seedling emergence information. An unmanned aerial vehicle (UAV) was used to acquire soybean seedling RGB images at emergence (VE), cotyledon (VC), and first node (V1) stages. The number of soybean seedlings that emerged was obtained by the seedling emergence detection module, and image datasets were constructed using the seedling automatic cutting module. The improved AlexNet was used as the backbone network of the growth stage discrimination module. The above modules were combined to calculate the emergence proportion in each stage and determine soybean seedlings emergence uniformity. The results show that the seedling emergence detection module was able to identify the number of soybean seedlings with an average accuracy of 99.92%, a R² of 0.9784, a RMSE of 6.07, and a MAE of 5.60. The improved AlexNet was more lightweight, training time was reduced, the average accuracy was 99.07%, and the average loss was 0.0355. The model was validated in the field, and the error between predicted and real emergence proportions was up to 0.0775 and down to 0.0060. It provides an effective ensemble learning model for the detection and evaluation of soybean seedling emergence, which can provide a theoretical basis for making decisions on soybean field management and precision operations and has the potential to evaluate other crops emergence information.

In response to the problems of low straw utilization efficiency and poor returning effect in Northeast China, this paper takes rice straw containing cow dung as the experimental material, and according to the characteristics of lignin glass transformation of the material, proposes a new method to prepare biomass seedling trays. The seedling trays prepared by this method can meet the needs of corn seedling cultivation and transplantation. To study the molding mechanism, scanning electron microscopy and a universal testing machine were used to compare the changes in the internal structure and mechanical properties of the regularly- and hot-compressed seedling trays before and after seedling raising. The results show that the material with water content of 23% has the best hot-pressing effect. The forming mechanism is: that the strength of the molded seedling tray resulted from the mechanical setting force of the multilayered stem fibers with a mosaic structure within the seedling tray. The adhesion and wrapping by lignin prevented water penetration from damaging the multilayered stem fibers and slightly improved their strength. The seedling tray made of straw and manure was completely degraded over 40 days, and the straw degradation rate was improved. This method can increase the overall quality and benefits of straw, providing a foundational reference for high-quality and high-efficiency straw utilization.

The extraction of navigation lines is a crucial aspect in the field autopilot system for intelligent agricultural equipment. Given that soybean seedlings are small, and straw can be found in certain Northeast China soybean fields, accurately obtaining feature points and extracting navigation lines during the soybean seedling stage poses numerous challenges. To solve the above problems, this paper proposes a method of extracting navigation lines based on the average coordinate feature points of pixel points in the bean seedling belt according to the calculation of the average coordinate. In this study, the soybean seedling was chosen as the research subject, and the Hue, Saturation, Value (HSV) colour model was employed in conjunction with the maximum interclass variance (OTSU) method for RGB image segmentation. To extract soybean seedling bands, a novel approach of framing binarised image contours by drawing external rectangles and calculating average coordinates of white pixel points as feature points was proposed. The feature points were normalised, and then the improved adaptive DBSCAN clustering method was used to cluster the feature points. The least squares method was used to fit the centre line of the crops and the navigation line, and the results showed that the average distance deviation and the average angle deviation of the proposed algorithm were 7.38 and 0.32. The fitted navigation line achieved an accuracy of 96.77%, meeting the requirements for extracting navigation lines in intelligent agricultural machinery equipment for soybean inter-row cultivation. This provides a theoretical foundation for realising automatic driving of intelligent agricultural machinery in the field.

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.

Collecting crop growth data in field environments is crucial for breeding research. The team’s current autonomous soybean phenotyping system requires manual control to start and stop data collection. To address the aforementioned issues, this study innovatively proposes an elliptical calibration rotating geofencing technique. Preprocess coordinates using Z-scores and mean fitting perform global error calibration via weighted least squares, calculate the inclination angle between the row direction and the relative standard direction by fitting a straight line to the same row of data, and establish a rotation model based on geometric feature alignment. Results show that the system achieves an average response time of 0.115 s for geofence entry, with perfect accuracy and Recall rates of 1, meeting the requirements for starting and stopping geographic fencing in soybean ridge trial plots. This technology provides the critical theoretical foundation for enabling a dynamic, on-demand automatic start–stop functionality in smart data collection devices for soybean field trial zones within precision agriculture.

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.