Highlights AI can enhance agricultural safety through predictive models, LLMs, computer vision, and wearables. Machine learning is a tool that has the potential to predict hazards using historical data on injury incidents, weather, and worker behavior. Computer vision and remote sensing applications could be used to detect unsafe conditions for real-time risk mitigation. Wearable AI devices present opportunities to monitor worker health and prevent injuries in agricultural environments. ABSTRACT. Artificial intelligence (AI) has emerged as a transformative tool in various industries, including agriculture, where it has the potential to enhance safety and reduce injury risks. This review explores the application of AI techniques in occupational safety with a special focus on agricultural safety, focusing on predictive modeling, large language models (LLMs), computer vision, and wearable technologies. Due to the limited number of studies that address AI in agricultural safety, research from related fields, such as construction safety, was also considered for its potential applicability. The findings indicate that (1) predictive models that leverage machine learning (ML) algorithms can assess historical data and forecast hazards, enabling proactive safety measures. (2) LLMs can improve injury report analysis by extracting key terms and patterns to identify recurring risks. (3) Computer vision and remote sensing technologies enhance environmental monitoring by detecting real-time unsafe conditions. At the same time, (4) AI-powered wearable devices can track worker health indicators such as heart rate, potentially preventing injuries. A total of 85 studies were analyzed, providing insights into the diverse applications of AI in mitigating occupational hazards, specifically agricultural hazards. This review highlights the current advancements and future research opportunities for AI-driven safety interventions in high-risk occupational environments. Keywords: Agricultural safety, Artificial intelligence, Computer vision, Health, Injury prevention, Large language models, Machine learning, Occupational safety, Predictive modeling, Wearable technology.

Highlights A hybrid CNN–WE model markedly improves the accuracy of barley disease classification. Adaptive weighting enhances decision stability by reducing the influence of weaker classifiers. The proposed ensemble achieves 98.72% accuracy, outperforming individual models. The framework supports accurate barley disease detection and contributes to the next generation of smart agriculture. ABSTRACT. Rhynchosporium commune and Pyrenophora teres are two of the most prevalent barley diseases, and their highly similar visual symptoms make accurate diagnosis and differentiation particularly challenging. Artificial intelligence (AI) and machine learning (ML) methods have been widely applied to plant disease detection; however, their performance often degrades under diverse field conditions and noisy image data. Moreover, reliance on a single model increases vulnerability to its specific limitations, especially when diseases exhibit overlapping visual characteristics. To address these challenges, this study proposes a hybrid model that integrates deep feature extraction using a Convolutional Neural Network (CNN) with a weighted ensemble (WE) of ML classifiers. The CNN-extracted features are fed into four classifiers: Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Random Forest (RF), and Decision Tree (DT), each leveraging distinct strengths in handling complex, nonlinear, and interpretable data. A dynamic weighting strategy is then applied, assigning higher weights to classifiers with superior validation accuracy, and the final prediction is obtained through weighted majority voting. Unlike conventional ensemble methods that treat all classifiers equally, this adaptive weighting enhances decision stability, reduces the influence of weaker models, and significantly improves overall accuracy. Experimental results demonstrate classification accuracies of 82.5% for CNN, 87.3% for k-NN, 83.7% for DT, 91.6% for SVM, and 93.5% for RF, while the proposed WE achieves 98.72% accuracy. Furthermore, the ensemble model attains class-wise precision of 98.5% for R. commune, 97.5% for P. teres, and 98.5% for healthy samples, marking a substantial improvement over individual classifiers. These findings highlight the effectiveness of combining automatic deep feature extraction with adaptive ensemble learning, offering a robust framework for accurate barley disease detection and contributing to the advancement of intelligent plant health monitoring and precision agriculture systems. Keywords: Barley disease classification, Convolutional neural networks, Deep feature extraction, Ensemble classifiers, Machine learning, Weighted ensemble.

Highlights Hot water pretreatment of corn fiber resulted in a high polyhydroxybutyrate (PHB) yield (0.36 g PHB/g sugars). Alkaline pretreatment yielded less glucose and consequently produced less PHB compared to hot water pretreatment. Controlling hydrolysate pH with phosphate buffer during fermentation improved PHB production. The use of acetate buffer during enzymatic hydrolysis led to the highest PHB yield. ABSTRACT. The urgent need to replace petrochemical-based plastics with bioplastics like polyhydroxybutyrate (PHB) has increased over the last few decades. The major restraint in the process is the high substrate cost. The conversion of a cost-effective carbon source from lignocellulosic biomass to PHB could solve that problem and make biorefineries more economical. In this study, a cheap carbon source, corn fiber (CF), was used to produce PHB. Corn fiber hydrolysate was produced by pretreating CF followed by enzymatic hydrolysis. Glucose and xylose are the main sugars present in corn fiber hydrolysate. Paraburkholderia sacchari DSM 17165 is a well-known PHB-producing organism that can ferment these monomeric sugars to PHB. Pretreatment methods, the buffer used during enzymatic hydrolysis, and pH during batch fermentation have a substantial effect on PHB yield. This study explored the effect of two pretreatment strategies, liquid hot water (LHW) pretreatment and alkaline pretreatment, and several pH control strategies on PHB yields. The highest PHB yield of 0.36 g PHB/g sugars was obtained with LHW pretreatment, acetate buffer in enzymatic hydrolysis, and using phosphate buffer as pH control during fermentation as compared to the PHB yield of 0.36 g PHB/g sugars in control. Keywords: Biodegradable, Bioplastic, Corn fiber.

Highlights Agricultural irrigation systems are evolving fast to meet sustainability and profitability pressures. Relying on complex cyber-enabled networks, they are vulnerable to malicious cyberattacks. Malicious cyberattacks on irrigation infrastructure can cause ripple effects across connected sectors. There is a strong need for research and education efforts to secure agricultural irrigation systems. Keywords: Cybersecurity, Energy security, Irrigation, Precision agriculture, Sensors, Water security.

Highlights The effectiveness of five different swine manure treatments for mitigating antimicrobial risk factors was compared. Anaerobic digestion and liming were found to be the most effective treatments, especially for reducing growth of cells on tetracycline. Inconsistent outcomes across treatments highlight the complex interplay of antibiotic residues, resistance genes, and microbial growth, and highlight these relationships as targets for further investigation. ABSTRACT. Swine manure is typically applied to agricultural land at agronomic rates, providing essential nutrients to crops and enhancing soil fertility. While providing nutrients, manure can also introduce pathogens and other contaminants, including antibiotic residues and antibiotic-resistant bacteria (ARB) and genes (ARGs), into the environment with subsequent threats of transfer to humans through the food chain. There are various manure management strategies that may be considered before land application to potentially mitigate the risks of antimicrobial resistance exposure. In a laboratory manure slurry incubation study, the effectiveness of five different manure treatment practices was evaluated. These practices included aeration, anaerobic digestion (AD), heat, liming, and solid-liquid separation (SLS), and were assessed for their ability to reduce antibiotics, antibiotic-resistant bacteria (ARBs), and antibiotic resistance genes (ARGs). This study focused primarily on the impacts on tetracycline (TET), TET-resistant populations, and TET-resistant genes. Additionally, we evaluated the impacts of manure treatments on macrolide (MAC) resistance. We compared the effects of manure treatment on phenotypic resistance of TET, the concentration of TET and MAC residues, and copies of several TET- and MAC-resistant genes. For TET-resistant ARB, our results indicate that AD and liming are the most effective among all treatments. Liming was able to rapidly reduce TET-resistant ARB. Comparing ARGs and antibiotic residuals, we found AD to be the most effective treatment in reducing TET-resistant genes (tetO, tetM, and ermB) and total TET and MAC residues. This research provides valuable insights that can be used to recommend best management practices to farmers and policymakers to reduce dissemination of antimicrobial resistance through environmental pathways. Keywords: Aeration, Anaerobic digestion, Antibiotic microbial resistance, Liming, Macrolides, Manure treatment, Solid-liquid separation, Tetracycline.

HighlightsFound evidence for drag reduction in comminuted wood chip slurry and quantified it.Fine wood chip slurries show flow behavior like agricultural residue slurries.Established upper and lower limits in the drag reduction regime for fine wood chip slurries.Identified three flow regimes in fine wood chip slurries, akin to pulp fiber and agri-residue slurries.Abstract. Pipeline hydro-transportation of forest residues helps in reducing the biomass feedstock's delivered cost compared to truck transport. This can subsequently help in establishing large-scale biorefineries. There is limited research on wood chips and water slurry transport through pipelines. In addition, there is no study on the comparison of flow regimes of wood chips and agricultural residue slurries. This research experimentally investigated the flow behavior of slurries made of milled wood chips and water. Experiments were carried out in a 25.5 m long, 50 mm diameter closed-circuit pipe loop test setup to measure horizontal pressure gradients. Pressure gradients were measured for wood particle sizes ranging from 1.3 to 3.2 mm, saturated mass concentrations ranging from 5% to 35%, and bulk velocities ranging from 0.5 to 5.0 m/s. The findings indicate evidence of drag reduction behavior in wood residue slurries with small particle sizes (< 2.6 mm) and aspect ratios (4–6). A 22% decrease in pressure drop was obtained, compared to water, when pumping 1.3 mm wood residues at a bulk velocity of 3.4 m/s and a saturated mass concentration of 25%. Comparing pressure drop values from tests on earlier research on agricultural residue slurry suggests similar flow behavior. However, the maximum drag reduction in wood residue slurries was 33% lower than that reported for agricultural residues. The findings from this study will be crucial in refining wood residue hydro-transport for cost-effective biomass conversion and for the development of large-scale biorefineries on woody biomass. Keywords: Biomass slurry, Drag-reduction, Flow regimes, Forest residues, Hydro-transport, Toms effect.

Highlights A center frame hydraulic lift suspension for an agricultural self-propelled sprayer was instrumented and tested to further understand center frame and boom dynamics. Hydraulic accumulator precharge, volume, and system flow rate variables were manipulated to quantify the effect on lift suspension performance. The default accumulator precharge (83 bar) and orifice diameter (6 mm) provided the best overall performance for this suspension system across a multitude of drive profiles and specific field events. ABSTRACT. Improving the accuracy of fertilizer and herbicide application for self-propelled sprayers is an important part of modern precision agriculture. Multiple efforts across the private and public sectors have been made to improve boom height stability. Through various mechanical linkages and suspension systems, boom systems have been designed to be less coupled to the vehicle’s chassis, thus further mitigating unwanted dynamics from reaching the boom system and therefore providing a more stable boom platform. The suspension system studied in this research is a center frame lift assembly, which is intended to reduce the vertical coupling of the booms to the chassis. This lift system is composed of two mechanical lift arms, two hydraulic cylinders, and a hydraulic accumulator. Features of the accumulator were manipulated to better understand the lift assembly’s behavior. This included the accumulator’s precharge pressure, volume, and inclusion of an orifice in the hydraulic schematic that connects the accumulator to other components. Tests were conducted for a range of field profiles, speeds, and boom target heights, and a virtual simulation model was developed to aid in the development of the overall test matrix. The initial objective of this study was to characterize the suspension system across its entire operating range, as well as explore how manipulating the precharge affected system performance. A second set of testing was done for different accumulator volumes and orifice diameters. The data pertaining to the various levels in precharge revealed that the lowest precharge setting of 83 bar (1200 psi), also with a corresponding 2 L accumulator volume, was optimal for this suspension system. The second set of tests showed that the largest orifice diameter of 6 mm, from the possible 2, 4, and 6 mm configurations, yielded the best performance across test configurations. Regarding the changes in volume between 2, 4, 6, and 8 L, larger volumes were best for high-amplitude field events, while the smallest volume, 2 L, generally proved to be best for normal field operation. Keywords: Accumulator, Boom, Hydraulics, Lift system, Orifice, Pressure, Self-propelled sprayer, Suspension.

HighlightsA feature pyramid network with Scaling Feature Fusion and Enhanced Expansion Feature module is constructed to overcome the shortcomings of feature pyramids for small target detection.Noise addition, cropping, and other data augmentation methods for expanding data sets.Multi-channel Denoising Feature Fusion is constructed in the detection module to solve the inconsistencies inside the feature pyramid.Combine with YOLOv5's Backbone to complete the feature anchor box selection and detection can quickly and accurately complete the grape leaf disease detection.ABSTRACT.Grape leaf diseases all over the world cannot be ignored; it is one of the important causes of agricultural economic damage. In order to control the cost of manual detection of grape diseases and to overcome the impact on detection accuracy due to the large variation of target scales during automatic detection of grape leaves, the feature pyramid method is commonly used to solve this problem, but it may destroy the feature consistency of grape leaves at different scales. In addition, in practical applications, the commonly used methods are difficult to improve the detection accuracy of multi-scale grape leaves while ensuring detection. In this paper, we apply the improved YOLOv5 algorithm, which is used to detect the images of grapevine powdery mildew, grape mosaic virus disease, and grape downy mildew, as well as the images of healthy grape leaves. The proposed algorithm is based on the improved feature pyramid network SE-FPN, which added Scaling Feature Fusion (SFF) to enhance feature map information and Enhanced Expansion Feature (EEF) to improve multi-scale accuracy prediction. And replacing the original Path Aggregation Network (PANet) detection module with the Multi-channel Denoising Feature Fusion (MDFF) network improves the scale invariance of features and reduces the inference cost. By experimentally comparing the original YOLOv5 network and the YOLOv5 network with other improved methods applied, considering the following metrics: mean Average Precision (mAP), accuracy, recall, and mean target detection loss, mean classification loss, and runtime of the validation set, the results conclude that the improved model proposed in this paper performs the best, which increases the accuracy by 5.96% and the recall by 4.69% compared to the original YOLOv5 model. The algorithm provides good technical support for real-time detection and control of grapevine diseases. Keywords: Detection module, Disease identification, Feature pyramid network, Grape leaf disease, YOLO.

HighlightsThe components in the hard lower stem of asparagus after drying and roasting were analyzed.The fructose and sucrose contents were increased by drying but reduced by roasting.The increase or decrease in some free amino acids was caused after drying.Characteristic volatile compounds could be added by drying and roasting.Abstract. Asparagus (Asparagus officinalis L.) has a characteristic flavor and useful components, although the lower stem is not suitable for eating because it has a fibrous skin-like wood that is usually discarded. Therefore, useful components were analyzed to effectively use the hard lower stem of asparagus by drying and roasting. The rutin content was decreased significantly by drying and roasting. The ascorbic and folic acid contents were concentrated by drying but decreased by roasting. The fructose and glucose contents were increased by drying but significantly reduced by roasting. The sucrose content was increased by drying and roasting. The contents of some free amino acids were concentrated by drying but disappeared by roasting. Furthermore, characteristic volatile compounds derived from the Maillard reaction were caused by drying and roasting. Most of the useful components in the hard lower stem of asparagus can be concentrated by drying, and characteristic volatile compounds can be added by drying and roasting. Therefore, it is promising that the asparagus stem, an unused resource, can be utilized as a useful food material by drying and roasting. Keywords: Asparagus stem, Drying, Maillard reaction, Roasting, Volatile compound.

HighlightsEfficacy of electrostatically charged spray applications depends upon charge-to-mass ratio.Chargeability for electrostatic nozzles, TXVS-2, and TXVK-3, 4, 6 increased as airspeed increased.Droplet size increased with nozzle orifice size and decreased with airspeed and spray pressure.Chargeability was lower for nozzles with higher flowrate.An Excel-based model provides droplet size and charge-to-mass ratio data for aerial applicators.ABSTRACT. Optimizing electrostatically charged aerial sprays of pest control products on field crops by fixed-wing aircraft is required to incur beneficial advantages such as improved deposits, increased plant canopy penetration, and a wrap-around effect associated with this technology. A spray mixture of tap water and a non-ionic surfactant was atomized through four electrostatic nozzles, TXVS-2, TXVK-3, 4, and 6, at seven sets of airspeed and nozzle spray pressure combinations in a high-speed wind tunnel to determine spray chargeability. Using the parameter estimates (airspeed, nozzle orifice, liquid spray pressure, spray droplet spectra, and flowrate), a response surface model was developed and incorporated into a Microsoft Excel-based app, which can be installed and run on a smartphone. The goodness-of-fit of the model showed that the R2 values for the spray droplet spectra used to build the model ranged from 0.941 to 0.985, which indicates that the measured values closely approximated the modeled values. This model can help aerial applicators maximize the chargeability of electrostatically charged aerial sprays and conform with label requirements specified for the application of crop protection chemicals. This may help improve efficacy and mitigate off-target movement of crop protection products. Keywords: Airspeed, Charge-to-mass ratio, Electrostatic nozzles, Liquid spray pressure, Modeling, Spray charge, Spray droplet spectra.