Blueberries are one of the more economically rewarding fruits for fruit growers. Identifying blueberry fruit at different stages of maturity is economically important and can aid fruit growers in planning pesticide applications, estimating yields, and efficiently conducting harvesting operations, among other benefits. Visual methods for identifying the different ripening stages of fruits are increasingly receiving widespread attention. However, due to the complex natural environment and the serious shading caused by the growth characteristics of blueberries, the accuracy and efficiency of blueberry detection are reduced to varying degrees. To address the above problems, in the study presented herein, we constructed an improved YOLOv9c detection model to accurately detect and identify blueberry fruits at different ripening stages. The size of the network was reduced by introducing the SCConv convolution module, and the detection accuracy of the network in complex and occluded environments was improved by introducing the SE attention module and the MDPIoU loss function. Compared to the original model, the mAP0.5 and mAP0.5:0.95 of the improved YOLOv9c network improved by 0.7% and 0.8%, respectively. The model size was reduced by 3.42 MB, the number of model parameters was reduced by 1.847 M, and the detection time of a single image was reduced by 4.5 ms. The overall performance of the detection model was effectively improved to provide a valuable reference for accurate detection and localization techniques for agricultural picking robots.

In precision seeding, the final displacements of the seeds are determined as a working result of the profiling mechanism, opener, seed-metering device, covering apparatus and compacting machine. For a better understanding of the disturbance of seed displacement during soil covering and compaction in the actual working process, experiments and simulations have been performed. In this paper, a type of soybean seeding monomer was taken as the research object, and a soil bin test of soil covering and compacting was executed. The experimental results showed that the traction velocity and the open angle of the covering discs had a significant influence on the changes in the horizontal and vertical displacements of seeds during the soil covering processing. With an increasing traction velocity, the vertical displacements of seeds increased after soil covering; in contrast, the horizontal displacements decreased. When the covering apparatus had a larger open angle it had a smaller disturbance influence on the soil. Therefore, with an increase in the opening angle, the changes in the vertical and horizontal displacements of seeds showed a decreasing trend. Inversely, in the process of compacting, the forward velocity had little effect on the three-dimensional displacement change in the seeds after compacting. The analysis model of the precision seeding unit was established based on the coupling model of the DEM (discrete element method) with MBDs (multi-body dynamics). The process of soil covering and compacting was simulated and analyzed. The comparison between the experimental results and the simulated results showed that the trend was similar, and the two results were close. Thus, the feasibility and applicability of the coupling method were verified. It also provided a new method for the design and optimization of covering and compacting components of a precise seeding monomer.

Soil sensors have a vital role in precision agriculture. In smart agriculture, soil moisture sensors, soil temperature–humidity sensors, soil pH sensors, soil nutrient sensors, soil pollutant and pest sensors, and wearable sensors detect data to improve crop yields and advance agricultural development. This paper summarizes the types and applications of the above sensors. Soil sensors serve as the core technological engine of smart agriculture, and this review also illustrates that the integration of the Internet of Things and sensors—including plant wearable sensors, which indirectly reflect soil conditions through plant physiological signals—can simultaneously measure or infer parameters, e.g., moisture, temperature, pH, and nutrients, that play a crucial role in precision agriculture. This paper concludes with the future prospects and challenges of soil sensors in smart agriculture, emphasizing the need to address bottlenecks in data fusion, model optimization, and cost control, as well as to advance the implementation of smart agriculture through the development of standards and ecological construction.

The implementation of scientific cultivation practices on soda saline–alkali land plays a pivotal role in safeguarding food security and promoting sustainable agro-economic development at the regional scale. However, there exists a critical knowledge gap regarding the optimization of tillage strategies for rain-fed maize (Zea mays L.) cultivation across heterogeneous saline–alkali soil matrices. This study selected meadow alkaline soil, saline meadow soil, and mild saline–alkali soil under the typical micro-landscape morphological characteristics of soda saline–alkali soil in the Songnen Plain as experimental plots. Under three tillage methods, namely no tillage (NT), rotary tillage + no tillage (RT), and subsoiling + rotary tillage + no tillage (SRT), the effects of the tillage methods on the soil physical properties at the seedling stage, root development at the V6 stage, and yield at the R6 stage during the process of cultivating maize in different types of soils were analyzed. The research results showed that compared with NT and RT, the SRT treatment better improved the physical properties, such as penetration resistance and the bulk density in micro-spaces (0–40 cm), of different soil types. The SRT treatment had a positive impact on the root development of maize seedlings in saline meadow soil and meadow alkaline soil. In terms of yield, compared with the NT treatment, the SRT treatment in meadow alkaline soil and saline meadow soil had a positive effect on the plant height, root dry weight, 1000–grain weight, and grain yield of maize. The increases in maize grain yield were 27.94% and 13.24%, respectively. Compared with NT, the differences in the effects of the SRT and RT treatments on maize yield in mild saline-alkali soil were the smallest, being 6.98% and 4.77%, respectively. The relevant results provide guidance on tillage methods and a theoretical basis for improving the properties of different types of soda saline–alkali soils and increasing maize yield.

Olives are a crucial woody oil crop, the harvesting of which predominantly relies on manual labor, which is characterized by high costs, low efficiency, and challenges in ensuring optimal harvesting timing. The development of an automated ripeness-detection system with high recognition accuracy is of paramount importance for advancing automated olive-harvesting technologies. Traditional detection methods are constrained by susceptibility to environmental interference, limited robustness, and inadequate generalization capabilities. Concurrently, existing deep learning-based detection models face issues such as insufficient feature extraction for small targets and difficulties in deployment due to their need for large numbers of parameters. To address these limitations, this study proposes a lightweight algorithm for detection and grading of olive ripeness based on an Improved YOLOv11n framework. The proposed approach employs YOLOv11n as the baseline model, replaces its backbone network with EfficientNet-B0, and integrates the Large-Scale Kernel Attention (LSKA) mechanism and the Bidirectional Feature Pyramid Network (BiFPN). Experimental validation demonstrated that the enhanced model achieved detection accuracy comparable to that of the original model, attaining a mean average precision (mAP) of 0.918. Furthermore, the model size was reduced to 3.7 MB, a 39.3% reduction, while the computational complexity (GFLOPs) was decreased by 2.4 and the inference time per image was reduced by 0.2 ms. The proposed model exhibits significant advantages in terms of lightweight design and improved detection efficiency, demonstrating substantial potential for practical deployment. This study provides a valuable reference for the development of automated olive-harvesting technologies.

Given the lack of accurate and reliable discrete element simulation parameters to study the interactions between soft soil and soil casting components after ginseng land cultivation in Northeast China and the design of ginseng land-specific borders, this paper calibrates the relevant model parameters of ginseng soil using the Hertz–Mindlin with JKR contact model in EDEM to standardize the contact parameters between soil particles and between soil and Q235 steel in soft soil after cultivation in ginseng land. Taking the soil particle accumulation angle as the response value, a Box–Behnken design (BBD) was introduced to establish a regression model for the soil accumulation angle; the surface energy, static friction coefficient, rolling friction coefficient, and coefficient of restoration parameters were obtained, respectively, through the optimization of the model, at which time, the simulated value of the soil accumulation angle was 37°, which is a 4% relative error to the actual measured accumulation angle of 35.5°. Taking the sliding friction angle of the soil on the Q235 steel plate as the response value, the regression model of the soil sliding friction angle was obtained based on the BBD. The static friction factor, rolling friction factor, and coefficient of restitution between the soil particles and the Q235 steel were obtained, respectively. Based on the combination of these parameters, the simulated value of the sliding friction angle was 32.2°, which is a 2% relative error to the measured accumulation angle of 31.5°. To verify the accuracy of the optimized simulation parameters, field and simulation tests of soil-throwing components were conducted. The results show that the maximum relative error between the measured value and the simulation value is 5.6% and 3.4%. The error is within an acceptable range, and the simulation test and field test soil-throwing effects are the same, which verifies the accuracy and reliability of the reference soil parameter calibration. The results of the study can be used for discrete element simulation analysis of the interaction between ginseng loam and touchdown components and their structural optimization.