Search Results (7,343)

In agricultural production, rapid and accurate detection of peach blossom bloom plays a crucial role in yield prediction, and is the foundation for automatic thinning. The currently available manual operation-based detection and counting methods are extremely time-consuming and labor-intensive, and are prone to human error. In response to the above issues, this paper proposes a natural environment peach blossom detection model based on the YOLOv5 model. First, a cascaded network is used to add an output layer specifically for small target detection on the basis of the original three output layers. Second, a combined context extraction module (CAM) and feature refinement module (FSM) are added. Finally, the network clusters and statistically analyzes the range of multi-scale channel elements using the K-means++ algorithm, obtaining candidate box sizes that are suitable for the dataset. A novel bounding box regression loss function (SIoU) is used to fuse the directional information between the real box and the predicted box to improve detection accuracy. The experimental results show that, compared with the original YOLOv5s model, our model has correspondingly improved AP values for identifying three different peach blossom shapes, namely, bud, flower, and falling flower, by 7.8%, 10.1%, and 3.4%, respectively, while the final mAP value for peach blossom recognition increases by 7.1%. Good results are achieved in the detection of peach blossom flowering volume. The proposed model provides an effective method for obtaining more intuitive and accurate data sources during the process of peach yield prediction, and lays a theoretical foundation for the development of thinning robots. Full article

The biosynthesis of anthocyanins is influenced by external environmental conditions such as light, temperature, and nitrogen level, with nitrogen level being a key factor in anthocyanin synthesis and accumulation. Nitrogen level regulates the transcription factors involved in the anthocyanin synthesis pathway, with low nitrogen levels promoting anthocyanin accumulation, while high nitrogen levels have the opposite effect. Purple potatoes are a type of cultivated crop that is rich in anthocyanins and has unique economic value. Nitrogen fertilizer is crucial to improve the agronomic traits, yield, quality, and anthocyanin content of purple potatoes. In this study, the impact of four different nitrogen concentrations—0 kg/hm² (N0), 90 kg/hm² (N1), 225 kg/hm² (N2) and 360 kg/hm² (N3)—on the agronomic traits, yield, quality, and anthocyanin content of purple potatoes, ‘Huasong 66’, at different stages were investigated by using physiological index measurement and RNA-seq technology. It was found that the purple potato ‘Huasong 66’ was more sensitive to low nitrogen (N1). Under N1 level of nitrogen fertilization, ‘Huasong 66’ possessed the finest agronomic traits, yield, and quality, and the total anthocyanins in the tubers were significantly increased. Furthermore, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis revealed that nitrogen levels in purple potato tubers primarily affect genes related to nutrient transport and metabolism by regulating carbon and nitrogen metabolism, enzyme catalysis and binding, and signal transduction. In addition, nine candidate genes related to the anthocyanin synthesis pathway had been preliminarily screened. These results provide a basis to understand the impact of different nitrogen levels on the tuber yield and anthocyanin synthesis of purple potatoes. Full article

This study focuses on real-time detection of maize crop rows using deep learning technology to meet the needs of autonomous navigation for weed removal during the maize seedling stage. Crop row recognition is affected by natural factors such as soil exposure, soil straw residue, mutual shading of plant leaves, and light conditions. To address this issue, the YOLOv5s network model is improved by replacing the backbone network with the improved MobileNetv3, establishing a combination network model YOLOv5-M3 and using the convolutional block attention module (CBAM) to enhance detection accuracy. Distance-IoU Non-Maximum Suppression (DIoU-NMS) is used to improve the identification degree of the occluded targets, and knowledge distillation is used to increase the recall rate and accuracy of the model. The improved YOLOv5s target detection model is applied to the recognition and positioning of maize seedlings, and the optimal target position for weeding is obtained by max-min optimization. Experimental results show that the YOLOv5-M3 network model achieves 92.2% mean average precision (mAP) for crop targets and the recognition speed is 39 frames per second (FPS). This method has the advantages of high detection accuracy, fast speed, and is light weight and has strong adaptability and anti-interference ability. It determines the relative position of maize seedlings and the weeding machine in real time, avoiding squeezing or damaging the seedlings. Full article

This study aims to present changes in the competitive positions of the dairy farms from EU countries with the highest milk production in 2020. The assessment was based on data from the FADN system for the years 2014–2021 and covered average and large dairy farms from five EU countries: Germany, France, The Netherlands, Italy, and Poland. To assess the competitive positions of dairy farms from the selected EU countries, we developed the Synthetic Measure of Competitive Position based on the resource-based theory of enterprises. The conducted research showed that: (1) average dairy farms in Poland had the lowest production potential resulting from their possessed resources. (2) The highest value of the Synthetic Measure of Competitive Position for 2014–2021 was achieved by average dairy farms from Germany and their position in the ranking strengthened throughout the analyzed period. (3) The same analysis conducted on the group of large dairy farms showed that the competitive position, measured with the Synthetic Measure of Competitive Position, was the highest in the case of Polish dairy farms. Full article

In Canada, approximately 11.2 million metric tons of avoidable food waste (FW) is produced per year. Preservation of a greater proportion of this FW for use as livestock feed would have significant environmental and socioeconomic benefits. Therefore, this study blended discarded fruits, vegetables, and bakery products from grocery stores into silage to assess the ability to preserve their nutritional value and contribute to the feed supply. Two treatments for reducing the water content of FW were evaluated, sun-dried (SD) and passive-dried (PD), and compared to control (C) using laboratory mini-silos over 60 days of ensiling. Although dry matter (DM) was increased by 1–5% for PD and SD, respectively, up to 41.9% of bread products were required to produce a targeted silage DM of 38%. All mature silages were high in crude protein (15.2 to 15.7%), crude fat (6.0 to 6.3%), sodium (0.48 to 0.52%), and sugars (0.95 to 1.53%) and were low in neutral detergent fiber (6.2 to 7.6%) as compared to traditional silages used as livestock feed. Mold and other signs of spoilage were visible on FW, but mycophenolic acid was the only mycotoxin above the limit of detection in material prior to ensiling. Plate counts of molds and yeasts declined (p < 0.001) by 5–7 log colony-forming units (CFU) over 60 days of fermentation and were not detected in mature silage. All silages were aerobically stable over 20 days. This study indicates that FW can produce good-quality silage but approaches other than SD and PD are required for increasing silage DM as insufficient bread products may be available for this purpose in all batches of FW. Full article

In the present study, the effects of different types of sugars and cultivation medium pH levels on the micropropagation of Krymsk 5^® cherry rootstock were investigated. During the proliferation stage, the effects of four sugars (sucrose, fructose, glucose, and sorbitol) both separately and in two combinations were studied, along with the effects of pre-adjusted pH (4.5, 5.0, 5.2, 5.5, 5.8, 6.0, 6.2, or 6.5) on shoot proliferation parameters, growth medium’s post-autoclaving and post-cultivation pH, and their relations. Similarly, during the rooting stage, the effects of four sugars (sucrose, glucose, fructose, or sorbitol) at three concentrations (1% w/w, 2% w/w, or 3% w/w) without any auxin inclusion were studied as well as the effects of two sugars (sucrose or fructose) at six pre-adjusted pH levels (4.8, 5.2, 5.8, 6.2, or 6.5), also in the absence of auxin, on rooting parameters. Explants cultivated in fructose-supplemented growth mediums exhibited superior proliferation performance, characterized by the highest values of shoots per explant, shoot length, and nodes per explant. Generally, the medium’s pH decreased after autoclaving, and proliferation performance was favored by low pH values (either pre-adjusted or post-autoclaving). As far as rooting is concerned, fructose inclusion induced a higher rooting percentage (88%) compared to sucrose. The highest rooting was obtained in fructose-supplemented rooting mediums at concentrations of 2% or 3% w/w (95% rooting in both cases), in the absence of auxins. Post-autoclaving pH in fructose-supplemented rooting mediums was lower and buffered in low pH levels than in sucrose-supplemented ones, and the rooting of explants in all pH combinations with fructose exceeded 75%. In addition, rooting was negatively correlated with the post-autoclaving pH. These findings underscore the significance of both the sugar type and the post-autoclaving pH of the medium in both proliferation and rooting stages, highlighting their possible physiological, biochemical, or hormonal effects. Additionally, rooting without the use of auxin, but with the correct choice of sugar, emerges with both financial and environmental benefits, whereas fructose could be potentially used as a buffering agent. Full article

Common wheat is one of the most important cereal crops in the world. In cultivation, winter, spring, and facultative varieties of this species are known. In wheat agronomy, timely sowing and optimal nitrogen fertilization are particularly crucial practices, as both significantly impact yield and grain quality. In a three-year field experiment, the response of the winter wheat variety RGT Kilimanjaro to two sowing dates (recommended and delayed by 30 days) and varied nitrogen fertilization levels (100 kg ha⁻¹, 150 kg ha⁻¹, and 200 kg ha⁻¹) was investigated. It was shown that the difference in grain yield between 2021 and 2023 amounted to 0.74 kg ha⁻¹. The application of 200 N kg ha⁻¹ significantly increased the Soil Plant Analysis Development (SPAD) index and Leaf Area Index (LAI) compared to the variant with a delayed sowing date and a nitrogen dose of 100 kg ha⁻¹. Yield components (number of spikes per square meter, thousand grain weight) and grain yield were highest when wheat was sown at the recommended date and with the application of either 150 or 200 N kg ha⁻¹. The number of grains per spike significantly varied between the variant with the recommended sowing date and a dose of 200 N kg ha⁻¹ and the variant with a delayed sowing date and a dose of 100 N kg ha⁻¹. The lowest grain yield was obtained at a 30-day late wheat sowing date when applying 100 N kg ha⁻¹. The protein content in the grain was primarily influenced by nitrogen fertilization. Therefore, it can be concluded that delaying the sowing date of winter wheat by 30 days results in a decrease in grain yield but can be compensated by increased nitrogen fertilization. The most favorable economic effects were achieved with the application of 150 N kg ha⁻¹ at the recommended sowing date. Considering that high doses of nitrogen fertilization can have adverse effects on the natural environment, research in this area should be continued. Full article

The parameters of the discrete element simulation model for rice field soils serve as valuable data references for investigating the dynamic characteristics of the walking wheel of high-speed precision seeding machinery in paddy fields. The research specifically targets clay loam soil from a paddy field in South China. Calibration of essential soil parameters was achieved using EDEM_2022 software (and subsequent versions) discrete element simulation software, employing the Edinburgh Elasto-Plastic Adhesion (EEPA) nonlinear elastic-plastic contact model. The tillage layer and plough sub-base layer underwent calibration through slump and uniaxial compression tests, respectively. Influential contact parameters affecting slump and axial pressure were identified through a Plackett–Burman test. The optimal contact parameter combinations for the discrete element model of the tillage layer and plough sub-base layer were determined via a quadratic rotational orthogonal test. The accuracy of the discrete element simulation model’s parameters for paddy field soils was further validated through a comparative analysis of the simulation test’s cone penetration and the field soil trench test. Results indicate that the Coefficient of Restitution, surface energy, Contact Plasticity Ratio, and Tensile Exp significantly influence slump (p < 0.05). Additionally, the Coefficient of Restitution, Contact Plasticity Ratio, coefficient of rolling friction, and Tangential Stiff Multiplier significantly impact axial pressure (p < 0.05). Optimal contact parameters for the plough layer were achieved with a particle recovery coefficient of 0.49, a surface energy of 18.52 J/m², a plastic deformation ratio of 0.45, and a tensile strength of 3.74. For the plough subsoil layer, optimal contact parameters were a particle recovery coefficient of 0.47, a coefficient of interparticle kinetic friction of 0.32, a plastic deformation ratio of 0.49, and a tangential stiffness factor of 0.31. Results from the cone penetration test reveal no significant disparity in compactness between the actual experiment and the simulation test. The calibrated discrete element model’s contact parameters have been verified as accurate and reliable. The findings of this study offer valuable data references for understanding the dynamic characteristics of the walking wheel of the entire machinery in high-speed precision seeding in paddy fields. Full article

The objective of this study was to assess the level of financial security of farms and identify its determinants based on factor analysis. The data used in this research were obtained from the European FADN (Farm Accountancy Data Network). Factor analysis (FA) was employed to reduce the number of variables that potentially determine the financial security of farms. The results indicate that the surveyed entities maintained financial security between 2014 and 2021. This study suggests that it is necessary to examine these factors separately for farms engaged in crop farming and animal production. The results obtained for all farms were less satisfactory than those that took into account the specifics of agricultural production. This study addresses a gap in the literature by including highly correlated variables in the analysis of the determinants of financial security. Factor analysis is used to reduce the number of variables without losing important information. Firstly, seventeen variables related to the financial security of all farms were assigned to six factors. These were income and self-financing of operations; area and subsidies; long-term investments and financial decisions consequences; economic size, taxes, and non-breeding livestocks; investment activity; and inputs, stock, short-term loans, and labor. Then, the determinants of the financial security of farms were examined, taking into account the specialization of activities. For crop-producing farms, six factors were identified, including three that were identical to those for all farms: income and self-financing of operations; long-term investment and financial decisions consequences; and investment activity. In addition, the following items were specified: area, subsidies, non-breeding livestocks, and taxes; economic size, inputs, and labor; and stock and short-term loans. The correlated variables in the case of livestock production combined into factors in a different way. In this case, four factors were distinguished: economic size, non-breeding livestocks, income, and self-financing of operations; operational activities of animal production; long-term investment and financial decisions consequences; and investment activity. Financial security is a complex matter that can be affected by a range of factors related to agricultural activities. Full article

This study aims to address the current situation of the late start of mechanized harvesting technology for the pod pepper, the high damage rate of existing pod pepper harvesters, and the lack of theoretical support for key harvesting components. The Hertz theory is employed to investigate the damage mechanism of collisions between pod pepper and comb fingers. The study analyzes the maximum deformation of pod pepper and the critical speed at which damage occurs during the collision process. Furthermore, it explores the critical relative speed that leads to damage in pod pepper. Orthogonal tests are conducted to analyze the effects of rotational speed, hose thickness, and moisture content on the efficiency of pod pepper picking. The experimental results are then subjected to multifactorial ANOVA to identify the optimal test parameters. The structural and motion parameters of the picking device are optimized based on these conditions. It is determined that the critical relative velocity for damage to pod pepper during a collision with the comb finger is V₀ = 11.487 m s⁻¹. The collision velocities of pod pepper with different hose thicknesses are analyzed using the i-SPEED TR endoscopic high-speed dynamic analysis system to obtain the corresponding collision velocities for different hose thicknesses. The study finds that rotational speed, hose thickness, and the water content of pod pepper affect the damage rate and stem shedding rate. The optimal experimental parameters are determined to be a rotational speed of 705.04 rpm, hose thickness of 3 mm, and water content of the pepper of 71.27%. Full article

Camelina sativa is an annual oilseed crop that requires low inputs. Recently, interest in camelina oil for both human use and biofuel production has increased. Camelina oil extraction is performed through two main methods, namely, mechanical expulsion and solvent extraction. The resulting meals from the oil extraction process show promise as an animal feed due to their high crude protein content. Solvent extraction removes more oil from the seed, which results in a meal that is lower in fat and higher in crude protein concentration than expelled meal (3.52 vs. 13.69% and 41.04 vs. 34.65%, respectively). Solvent-extracted camelina meal has a similar chemical composition to canola meal but less crude protein and more fiber than soybean meal. Camelina meal is also limited by its anti-nutritional factors, mainly glucosinolates. Camelina meal contains 23.10 to 44.90 mmol/kg of glucosinolates, but processing methods may be able to decrease the total glucosinolates. Heat-treating the camelina meal can decrease glucosinolates and remove residual solvent in the solvent-extracted meal. The fungal fermentation of canola meal has also decreased glucosinolates, which could be used in camelina meal as well. The selective breeding of camelina varieties to decrease glucosinolates in the plant is also a solution to the high glucosinolates found in camelina meal. Current feed regulations in the US and Canada limit camelina meal to 10% inclusion in broiler chicken, laying hen, and cattle diets. Full article

Citrus fruits hold pivotal positions within the agricultural sector. Accurate yield estimation for citrus fruits is crucial in orchard management, especially when facing challenges of fruit occlusion due to dense foliage or overlapping fruits. This study addresses the issues of low detection accuracy and the significant instances of missed detections in citrus fruit detection algorithms, particularly in scenarios of occlusion. It introduces AG-YOLO, an attention-based network designed to fuse contextual information. Leveraging NextViT as its primary architecture, AG-YOLO harnesses its ability to capture holistic contextual information within nearby scenes. Additionally, it introduces a Global Context Fusion Module (GCFM), facilitating the interaction and fusion of local and global features through self-attention mechanisms, significantly improving the model’s occluded target detection capabilities. An independent dataset comprising over 8000 outdoor images was collected for the purpose of evaluating AG-YOLO’s performance. After a meticulous selection process, a subset of 957 images meeting the criteria for occlusion scenarios of citrus fruits was obtained. This dataset includes instances of occlusion, severe occlusion, overlap, and severe overlap, covering a range of complex scenarios. AG-YOLO demonstrated exceptional performance on this dataset, achieving a precision (P) of 90.6%, a mean average precision (mAP)@50 of 83.2%, and an mAP@50:95 of 60.3%. These metrics surpass existing mainstream object detection methods, confirming AG-YOLO’s efficacy. AG-YOLO effectively addresses the challenge of occlusion detection, achieving a speed of 34.22 frames per second (FPS) while maintaining a high level of detection accuracy. This speed of 34.22 FPS showcases a relatively faster performance, particularly evident in handling the complexities posed by occlusion challenges, while maintaining a commendable balance between speed and accuracy. AG-YOLO, compared to existing models, demonstrates advantages in high localization accuracy, minimal missed detection rates, and swift detection speed, particularly evident in effectively addressing the challenges posed by severe occlusions in object detection. This highlights its role as an efficient and reliable solution for handling severe occlusions in the field of object detection. Full article

Geographical indications (GIs) mitigate information asymmetry in agri-food transactions by providing consumers with origin and quality information. This paper explores the impact of GIs on rural development in China by examining agricultural output and farmers’ income. Utilizing a large county-level dataset and comprehensive official GI information, this study estimates the impact of GIs on agricultural output and rural income using panel-fixed-effects models. The results reveal that GIs significantly boost agricultural added value and rural per capita disposable income. A series of methods, including difference-in-differences, propensity score matching with difference-in-differences, and double machine learning combined with difference-in-differences using random forests verify the robustness of the results. Moreover, by categorizing GIs based on product types, the analysis reveals heterogeneous effects of different GI categories on agricultural growth and income gains for farmers. The research findings in this paper offer valuable insights to inform policymaking aimed at advancing rural development, raising farmers’ incomes, and promoting sustainable agri-food supply chains. Full article

In the context of addressing the challenge posed by limited fault samples in agricultural machinery rolling bearings, especially when early fault characteristics are subtle, this study introduces a novel approach. The proposed multi-domain fault diagnosis method, anchored in data augmentation, aims to discern early faults in agricultural machinery rolling bearings, particularly within an imbalanced sample framework. The methodology involves determining early fault signals throughout the life cycle, constructing early fault datasets with varying imbalance rates for different fault types, and subsequently employing the Synthetic Minority Oversampling Technique (SMOTE) to balance the fault data. The study then extracts relative wavelet packet energy and time-domain sensitive features (variance, peak to peak) from the original and generated fault data to form a multi-domain fault feature vector. This vector is utilized for fault state recognition using a Support Vector Machine (SVM). Evaluation metrics such as accuracy, recall, and F1 values assess the recognition effectiveness for each rolling bearing state, with the overall model recognition evaluated based on accuracy. The proposed method is rigorously analyzed and validated using the XJTU-SY rolling bearing accelerated life test dataset. Comparative analysis is conducted with non-data enhanced fault feature vectors, specifically the relative energy of the wavelet packet, both with and without time-domain features. Experimental results underscore the superior performance of multi-domain fault features in providing a comprehensive description of signal information, leading to enhanced classification performance. Furthermore, the study demonstrates improved classification accuracy and recall rates for the balanced dataset compared to the imbalanced dataset. This research significantly contributes to an effective identification method for the early fault diagnosis of small sample rolling bearings in agricultural machinery. Full article