AgriEngineering, Volume 7, Issue 9 (September 2025) – 27 articles

This systematic review analyzed a total of 109 scientific articles with the aim of identifying, organizing, and synthesizing academic output related to digital literacy, technology adoption in agricultural sectors, digital skills, and socioeconomic and cultural factors that influence the implementation of emerging technologies. Peer-reviewed academic publications available in open access and written in English were reviewed, complying with the PRISMA protocol guidelines. They came predominantly from Europe, Asia, and Latin America, which allowed for a global perspective. Quantitative, qualitative, and mixed approaches were applied, highlighting the use of surveys, interviews, and bibliometric analysis. Factors affecting the adoption of precision agriculture by smallholder farmers, challenges for the implementation of technologies in rural contexts, and sociocultural barriers to technological innovation were evaluated. The trend focuses on the need for sound public policies, continuous training strategies, technological accessibility, and contextualized approaches to ensure effective technology adoption. In conclusion, a broad and critical overview of the advances, limitations, and challenges surrounding digital literacy and technology adoption is provided as a basis for an in-depth debate on the digital transformation of contemporary agriculture. Full article

Viticulture, a key economic activity in the Mediterranean area, is facing several challenges including soil degradation. Among the sustainable practices available, the management of cover crops in vineyard inter-rows using a roller crimper to create dead mulch is gaining pace as an effective strategy for soil conservation. Nevertheless, the effectiveness of roller crimpers in terminating groundcovers in vineyards may be reduced by pedoclimatic conditions, type of vegetation and roller crimper configuration and operational parameters. This study aimed to evaluate the effectiveness of a roller crimper with two different weight configurations, light (LR) and ballasted (HR), each tested with one (P1) or two passes (P2), in terminating a cover crop mixture in a vineyard. To evaluate the termination performance, plant green cover data were modeled using a one phase exponential decay nonlinear regression. The four systems were also assessed for their ability to conserve soil moisture and their impact on soil compaction. Although the HR + P2 showed the highest termination performance, the system using the HR + P1 obtained comparable results, with k values of 0.07 and 0.11 days⁻¹ and half-life values of 9.50 and 6.09 days in 2023 and 2024, respectively. Given the need to coordinate multiple vineyard operations within short and weather-dependent timeframes, a one-pass approach such as HR + P1 offers operational advantages, providing a practical compromise between efficacy and efficiency. Full article

In the context of soil management, the porous structure present in these systems plays a relevant role due to its capacity to store and transport water, nutrients, gases, and provide root fixation. A detailed and precise analysis of these structures can assist specialists in determining specific agricultural solutions and management practices for each soil, depending on the characteristics of its porous structure. In this regard, this study presents a hybrid method for segmenting porous structures in micro computed tomography (micro CT) images of carbonate rocks, with a focus on applications in agricultural soil analysis and management. Initially, preprocessing steps such as Contrast Limited Adaptive Histogram Equalization (CLAHE) and histogram specification are applied in order to improve image contrast and uniformity. Subsequently, a UNet convolutional neural network is employed to identify pore contours, followed by the application of two geostatistical approaches, ordinary kriging and Universal Kriging, with the purpose of completing segmentation through the interpolation of unclassified regions. The proposed approach was evaluated using the dataset “16 Brazilian Pre Salt Carbonates”, which includes high-resolution micro CT images. The results show that the integration of UNet with ordinary kriging achieved superior performance, with 79.2% IoU, 93.3% precision, 81.7% recall, and 87.1% F1 Score. This method enables detailed analyses of pore distribution and the porous structure of soils and rocks, supporting a better understanding of inherent characteristics such as permeability, porosity, and nutrient retention in soil, thus contributing to more assisted agricultural planning and more efficient soil use strategies. Full article

Climate change significantly intensifies agroforestry workers’ exposure to atmospheric particulate matter (PM), raising occupational health concerns. This review, based on the analysis of 174 technical and scientific sources including articles, standards and guidelines published between 1974 and 2025, systematically analyses the main sources of PM in agricultural and forestry activities (including tillage, pesticide use, harvesting, sowing of treated seeds and mechanized wood processing) and focuses on the substantial contribution of agricultural and forestry machinery to PM emissions, both quantitatively and qualitatively. It highlights how changing climatic conditions, such as increased drought, wind and temperature, amplify PM generation and dispersion. The associated health risks, especially respiratory, dermatological and reproductive, are exacerbated by the presence of toxicants (such as heavy metals, volatile organic compounds and pesticide residues toxic for reproduction) in PM. Despite existing regulatory frameworks, significant gaps remain regarding PM exposure limits in the agroforestry sector. Emerging technologies, such as environmental sensors, AI-based predictive models and drone-assisted monitoring, are proposed for real-time risk detection and mitigation. A multidisciplinary and proactive approach integrating innovation, policies and occupational safety is essential to safeguard workers’ health in the context of increasing climate stress. Full article

Screen filters are widely used to retain suspended solids. Their performance depends not only on the nominal aperture size but also on the structural characteristics of the filter element, including material properties, weave pattern, and filtration rate. Although manufacturers typically specify filtration grade using mesh size or micron rating, these nominal values sometimes fail to reflect actual retention efficiency under field conditions. This study evaluated how filtration rate influences the retention efficiency of inorganic particles in eleven woven screen filter elements with different materials and configurations. Tests were conducted under two filtration rates and using particles of different size classes to determine the actual filtration threshold. The removal efficiency was determined by measuring total suspended solids (TSS). Eight of the eleven filters achieved more than 85% efficiency for at least one particle class, while three failed to meet this criterion. Higher filtration rates tended to reduce particle retention, particularly in synthetic filters. Nylon and polypropylene elements often exceeded their nominal filtration grades but were more sensitive to flow variations. Stainless steel filters exhibited consistent performance aligned with specifications. The findings emphasize the importance of experimental validation and support more informed filter selection based on particle size and hydraulic operating conditions. Full article

Thin-film thermoelectric generators (TFTEGs) emerge as critical components of self-sustaining agricultural systems because they can utilize temperature gradients to generate plant-transpiration-induced thermovoltage signal quantifiable to plant health status. This study examines the latest developments in TFTEG materials, device structures, manufacturing processes, and their integration into agricultural systems such as plant-wearable, canopy-level and stem-clipped TEGs. Key questions addressed include the ideal materials for TFTEG fabrication, their biocompatibility and eco-stability in agricultural settings, recent design and AI-assisted optimization advancements, and future research directions in non-conventional TEG applications. The analysis consolidates evidence from inorganic, organic, and hybrid thermoelectric materials with respect to performance in terms of flexibility, thermal stability, output power, and biocompatibility. Bibliometric analysis was employed to determine dominant research topics and gaps, especially with respect to sustainability and AI-augmented design. The review emphasizes the latest breakthroughs in structural optimization, flexible substrates, encapsulation strategies, and sensor integration for reliability enhancement in field environments. In addition, applications of AI, including neural network-based conditional Generative Adversarial Network, surrogate modeling, and multi-objective optimization, are discussed in relation to the improvement of thin-film TEG design and simulation processes. This study suggests that TFTEGs exhibit great potential in agricultural monitoring and plant wearable applications but material toxicity, mechanical degradation, and integration with AI are still major obstacles. Full article

As a sustainable alternative to conventional fertilizers, rock dusting is an emerging agroecological strategy to improve soil health and nutrient availability. This study aimed to quantify the effects of basalt powder (BP) application on the chemical attributes of a Ferralsol and the morphological responses of young Ilex paraguariensis (yerba mate) plants. The experiment was conducted in a randomized block design with five BP doses (0, 3.8, 7.6, 15.2, and 30.4 Mg ha⁻¹), where resulting soil and plant parameters were statistically analyzed. Results demonstrated that BP significantly increased available calcium, magnesium, and silicon in the soil (p ≤ 0.05) without altering pH or potassium levels. This soil enrichment directly correlated with a significant increase in the number of leaves per plant (p ≤ 0.01), which was strongly associated with soil Mg²⁺ (r = 0.73) and Si (r = 0.40). However, no significant effects were observed on plant height or stem diameter. We conclude that basalt powder acts as an effective slow-release source of Ca, Mg, and Si, primarily stimulating leaf development rather than immediate plant structural growth. This finding is consistent with the gradual nutrient release from silicate rocks and suggests that BP is a viable tool for enhancing soil fertility in yerba mate systems, although long-term evaluation is essential to understand its full agronomic potential. Full article

The operational stability of agricultural tractors is directly influenced by the mass distribution between axles, particularly when using mounted implements with variable loads. This study aimed to evaluate how different masses of a mounted sprayer (550 kg, 850 kg, and 1150 kg) and tire inflation pressures (151.7–193.1 kPa) affect the load distribution between axles, tire contact area, center of gravity (CG) displacement, and tractor lead ratio. A 3 × 4 factorial design was adopted with a statistical analysis of key parameters across 12 experimental combinations. The results demonstrated that increasing implement mass significantly shifted the load toward the rear axle, reducing the front axle load by up to 46% and displacing the CG rearward by more than 11 cm, thereby compromising stability. Tire pressure, as well as the interaction between mass and pressure, also exhibited statistically significant influence on load distribution and CG positioning while modulating the tire contact area. The lead ratio increased linearly with mass, exceeding the recommended 5% threshold when the sprayer was at full capacity. These findings indicate that while the implement mass exerts a dominant effect, tire pressure management represents a statistically relevant factor for stability, requiring integrated management that considers the interaction between ballasting and tire inflation to mitigate operational risks. Full article

Weeds are among the primary factors limiting corn and bean productivity, accounting for up to 30% of yield losses. Although chemical herbicides remain the predominant weed control strategy, their toxicity poses significant risks to human health and the environment. In response, organic agriculture has gained prominence as a more sustainable production system, with an increasing interest in alternative weed management approaches. Plants that produce allelopathic compounds capable of inhibiting the growth of unwanted species have emerged as promising sources of natural bioherbicides. While recent reviews have primarily focused on bioherbicides derived from microorganisms, a notable gap remains regarding the production and application of bioherbicides based on plant extracts. This review addresses this gap by summarizing current knowledge on the use of plant extracts for weed control in corn and bean cultivation. It discusses extraction methods, key plant species and active compounds, target weed species, herbicidal effects, modes of action, and patented technologies. Promising plants include Cuscuta campestris, Cymbopogon citratus, Mentha spp., Eucalyptus spp., and Pinus spp., which are rich in bioactive compounds such as phenolics (i.e., flavonoids), quinones, aldehydes and ketones, lactones, terpenoids (i.e., 8-cineole), and steroids. Plant extract-based bioherbicides show promising potential as sustainable and effective alternatives for weed management in organic agriculture, contributing to reducing the synthetic chemical herbicides, avoiding more resistances of weeds resistance of control, and promoting more environmentally friendly agricultural practices. Full article

This study addresses the problems of poor dynamic stability, high vibration coupling, and inefficient energy use in large-farm manure handling machines. A profiling wheel-based multi-disciplinary approach is proposed in the study. With the rocker arm prototype, double-ball heads, and a hydraulic damping system, a parametric design is built that includes vibration and energy consumption. The simulation results in EDEM2022 and ANSYS2022 prove the structure viability and motion compensation capability, while NSGA-II optimizes the damping parameters (k₁ = 380 kN/m, C = 1200 Ns/m). The results show a 14.7% σ_Fc reduction, 14.3% α_RMS decrease, resonance avoidance (14–18 Hz), Δx (horizontal offset of the frame) < 5 mm, 18% power loss to 12.5%, and 62% stability improvement. The new research includes constructing a dynamic model by combining the Hertz contact theory with the modal decoupling method, while interacting with an automatic algorithm of adaptive damping and a mechanical-hydraulic-control-oriented optimization platform. Future work could integrate lightweight materials and multi-machine collaboration for smarter, greener manure cleaning. Full article

This study introduces an interpretable deep learning pipeline for citrus fruit quality classification using the ViT-Base model vit_base_patch16_224 and Microsoft’s Phi-3-mini LLM. The ViT model, fine-tuned on resized 224 × 224 images with ImageNet weights, classifies fruits into good, damaged, and rotten categories, achieving 98.29% accuracy. For interpretability, Grad-CAM highlights damaged regions, while the Phi-3-mini generates human-readable diagnostic reports. The system runs efficiently on edge devices, enabling real-time, on-site quality assessment. This approach enhances transparency and decision-making, showing strong potential for deployment in the citrus industry. Full article

Integration of IoT and predictive modeling is critical for optimizing microclimate management in urban-agglomeration vertical farming. In this study, we present a hybrid digital twin approach that combines a physical microclimate model with a distributed IoT monitoring system to simulate and control the phytotron environment. A set of heat- and mass-balance equations governing the dynamics of temperature, humidity, and transpiration was implemented and parameterized using a genetic algorithm (GA)—an evolutionary optimization method—with real-time data collected over three intervals (72 h, 90 h, and 110 h) from LoRaWAN sensors (temperature, humidity, CO₂) and Wi-Fi-connected power meters managed by Home Assistant. The optimized model achieved mean temperature deviations ≤ 0.1 °C, relative humidity errors ≤ 2%, and overall energy consumption accuracy of 99.5% compared to measured values. The digital twin reliably tracked daily climate fluctuations and system energy use, confirming the accuracy of the hybrid approach. These results demonstrate that the proposed framework effectively integrates theoretical models with IoT-derived data to deliver precise environmental control and energy-use optimization in vertical farming, while also laying the groundwork for scalable digital twins in controlled-environment agriculture. Full article

In this paper, we present a set of experimental data (SESD) from Capsicum annuum with two different pigmentations, obtained using a self-made computed tomography spectrometer (CTIS), which adapt to the optical model of radiative transfer. An optical model is based on the directional-hemispheric reflectance and transmittance of a turbid medium with plane-parallel layers. To estimate the fruit’s primary pigments (Chlorophyll, Carotenoids, Capsanthin, and Capsorubin), we use the optical model combined with a numerical search and optimization method based on a robust and efficient multi-objective genetic algorithm (GA), allowing us to find the closest solution to the global minimum; and the inverse problem is solved by obtaining the best fit of the analytical function defined in the SESD optical model. Values of pigment concentrations retrieved with the proposed GA show a total difference of 2.51% for green pepper and 5.60% for red pepper compared with those reported in the literature. Full article

This research investigates the physical and mechanical properties of Codonopsis pilosula seedlings to provide fundamental mechanical data to address issues like high damage rates and low efficiency in mechanized transplanting. After precise physical parameter measurements, we classified the seedlings into four types: l-type, Y-type, V-type, and W-type. The l-type was the most common, accounting for a large proportion (80.95%) of the total, with a median length of approximately 270 mm, a median diameter of around 5.0 mm, and an average individual weight of about 2.83 g. Freshly harvested seedlings had an average moisture content and density within the typical range for this species. Using the Box–Behnken design method, we determined that the primary and secondary factors affecting tensile force (F_N) and tensile strength (σ) were sample diameter (D), sample length (L), and loading speed (V). Sample diameter had a significant impact: F_N increased rapidly as the diameter grew, while tensile strength (σ) decreased. The tensile strength of different regions of the seedling (i.e., head, middle, and tail) showed distinct characteristics, with relatively small deviations between theoretical and experimental values. For the whole seedling, errors in tensile force (F_N) and strength (σ) between measured and theoretical values were below 5%. The average Young’s modulus, Poisson’s ratio, and shear modulus were also calculated. These mechanical property indices thus provide crucial references for future related research. Full article

Identifying the botanical origin of honey is essential for ensuring its quality, preventing adulteration, and protecting consumers. Traditional techniques, such as melissopalynology, physicochemical analysis, and PCR, are often labor-intensive, time-consuming, or limited to the detection of only known species, while advanced DNA sequencing remains prohibitively costly. In this study, we aim to develop a deep learning-based approach for identifying pollen grains extracted from honey and captured through microscopic imaging. To achieve this, we first constructed a dataset named VNUA-Pollen52, which consists of microscopic images of pollen grains collected from flowers of plant species cultivated in the surveyed area in Hanoi, Vietnam. Second, we evaluated the classification performance of advanced deep learning models, including MobileNet, YOLOv11, and Vision Transformer, on pollen grain images. To improve performances of these model, we proposed data augmentation and hybrid fusion strategies to improve the identification accuracy of pollen grains extracted from honey. Third, we developed an online platform to support experts in identifying these pollen grains and to gather expert consensus, ensuring accurate determination of the plant species and providing a basis for evaluating the proposed identification strategy. Experimental results on 93 images of pollen grains extracted from honey samples demonstrated the effectiveness of the proposed hybrid fusion strategy, achieving 70.21% accuracy at rank 1 and 92.47% at rank 5. This study demonstrates the capability of recent advances in computer vision to identify pollen grains using their microscopic images, thereby opening up opportunities for the development of automated systems that support plant traceability and quality control of honey. Full article

The assessment of microplastics (MPs) in terrestrial ecosystems has garnered increasing global attention due to their accumulation and migration in soils, which may have potential impacts on soil health, biodiversity, and agricultural productivity. However, research on their distribution and interactions in soil remains limited, especially in tropical regions. This study aimed to characterize MPs extracted from tropical soil samples and relate their abundance to soil and terrain attributes under different land uses (forest, grassland, and agriculture). Soil samples were collected from an experimental farm in Lavras, Minas Gerais, Southeastern Brazil, to determine soil physical and chemical attributes and MP abundance in a micro-watershed. These locations were also used to obtain terrain attributes from a digital elevation model and the normalized difference vegetation index (NDVI). The majority of microplastics found in all samples were identified as polypropylene (PP), polyethylene (PE), polyethylene terephthalate (PET), and vinyl polychloride (PVC). The spatial distribution of MP was rather heterogeneous, with average abundances of 3826, 2553, and 3406 pieces kg⁻¹ under forest, grassland, and agriculture, respectively. MP abundance was positively related to macroporosity and sand content and negatively related to clay content and most chemical attributes. Regarding terrain attributes, MP abundance was negatively correlated with plan curvature, convergence index, and vertical distance to channel network, and positively related to topographic wetness index. These findings indicate that continuous water fluxes at both the landscape and soil surface scales play a key role, suggesting a tendency for higher MP accumulation in lower-lying areas and soils with greater porosity. These conditions promote MP transport and accumulation through surface runoff and facilitate their entry into the soil. Full article

Spatial variability in vine vigour and yield components is a major challenge for vineyard management and consistent grape quality, particularly in hilly landscapes. This study evaluates the impact of on-the-go variable-rate fertilisation (VRA) in reducing within-vineyard variability in an 8.5 hectares commercial vineyard in the Conegliano Valdobbiadene Prosecco DOCG region (Italy). Over two growing seasons, a proximal NDVI sensor (GreenSeeker) guided real-time fertiliser applications without prescription maps. Vine vigour, yield components, and grape quality were evaluated using geostatistical analysis and coefficient of variation (CV) metrics. VRA reduced total spatial variability (sill) by 55% and erratic variance (nugget effect) by 39% for NDVI measurements. Variability in yield components also decrease (−21.1% for cluster number, −6.25% for cluster weight), while grape composition parameters (total soluble solids, titratable acidity, and pH) was not significantly altered despite a slightly higher variability (in titratable acidity and pH), indicating that fertiliser modulation did not compromise grape quality. Nitrogen input was reduced by 50%, highlighting economic and environmental benefits (−302 kg CO₂). These results show that simplified, sensor-based, on-the-go VRA is a practical and sustainable precision viticulture tool, even in small and heterogeneous vineyards typical of the Conegliano Valdobbiadene Prosecco DOCG area. Full article

Electromagnetic induction (EMI) devices have become increasingly popular for their soil bulk properties, soil nutrient status, and use in taking non-invasive soil salinity measurements. However, the high cost of data acquisition (DAQ) systems has been a significant barrier to the widespread adoption of these devices. In this study, we addressed this challenge by developing a cost-effective, easy-to-use, open-source DAQ system, transferable to the end user. This system employs a Raspberry Pi 4 model, paired with various components, to monitor the speed and position of the EM38 (Geonics Ltd, Mississauga, ON, Canada) and compare these with a proprietary CR1000 system. Through our results, we demonstrate that the low-cost DAQ system can successfully extract the analogical signal from the device, which is strongly responsive to the variation in the soil’s physical properties. This cost-effective system is characterized by increased flexibility in software processes and provides performance comparable to the proprietary system in terms of its geospatial data and ECb measurements. This was validated by the strong correlation (R² = 0.98) observed between the data collected from both systems. With our zoning analysis, performed using the Kriging technique, we revealed not only similar patterns in the ECb data but also similar patterns to the Normalized Difference Vegetation Index (NDVI) map, suggesting that soil physical characteristics contribute to variability in crop vigor. Furthermore, the developed web application enabled real-time data monitoring and visualization. These findings highlight that the open-source DAQ system is a viable, cost-effective alternative for soil property monitoring in precision farming. Future enhancements will focus on integrating additional sensors for plant vigor and soil temperature, as well as refining the web application, supporting zone classification based on the use of multiple parameters. Full article

Poultry diseases threaten animal welfare and productivity, especially in cage-free systems where communal environments increase disease transmission risks. Traditional diagnostic methods, though accurate, are often labor-intensive, time-consuming, and not suitable for continuous monitoring. This study aimed to develop a web-based disease screening tool to make this process faster and accurate using fecal images. A publicly available dataset consisting of 6812 PCR-verified images categorized into Coccidiosis, Newcastle Disease (NCD), Salmonella, and Healthy from commercial farms in Tanzania was used in this study. Augmentation was used to address the imbalance present in the dataset, with NCD underrepresented (376 images) compared to other classes (>2000 images). Five YOLOv11 detection models were trained, with YOLO11n selected due to its high mean average precision (mAP@0.5 = 0.881). For classification, EfficientNet-B0 was chosen over the EfficientNet-B1 variant because of its high accuracy (99.12% vs. 98.54% for B1). Despite high class imbalance, B0 had higher precision than B1 for the underrepresented NCD class (0.88 for B1 vs. 1.00 for B0). The system achieved an average total inference time of 25.8 milliseconds, demonstrating real-time capabilities. Field testing, expanding datasets across different regions, and incorporating additional diseases is required to further validate and enhance the robustness of the system. Full article

Erythrina edulis, commonly known as pajuro, is a large leguminous plant native to the Amazon region of Peru. Its seeds are valued for their high protein content and their potential to enhance food security in rural communities. However, the current methods of harvesting and sorting are entirely manual, making the process labor-intensive, time-consuming, and subject to high variability, particularly in industrial contexts. A custom lightweight convolutional neural network (CNN) was developed from scratch and optimized specifically for real-time execution on embedded hardware. The model employs ReLU activation, Adam optimization, and a SoftMax output layer to enable efficient and accurate classification. The system employs a fixed-region segmentation strategy to prevent overcounting and utilizes GPIO-based control on a Raspberry Pi 5 to synchronize seed classification with physical sorting in real time. Seeds identified as defective are automatically removed via a servo-controlled ejection mechanism. The integrated system combines object detection, image processing, and real-time actuation, achieving a classification accuracy exceeding 99.6% and an average processing time of 12.4 milliseconds per seed. The proposed solution contributes to the industrial automation of pajuro sorting and provides a scalable framework for color-based grain classification applicable to a wide range of agricultural products. Full article

Agricultural tractors possess front loaders that are employed for the handling and transportation of materials, but are exposed to mechanical vibrations and shocks from ground undulations and sudden variations in the load. These vibrations are harmful to the durability of the parts, the comfort of the driver, and the longevity of the machine. In this current study, the performance of the hydraulic accumulator to mitigate such vibrations for a Foton 904 wheeled tractor equipped with a TZ10C-824 front loader is studied. Vibration measurements were taken by an experimental Brüel & Kjær 3050-A040 analyzer under various loading configurations (no loading, 180 kg, and 312 kg), with or without a 1.4 L, 50-bar nitrogen gas-charged Fox Opera Mi Italy hydraulic accumulator. Results reveal that maximum accelerations were as much as 6.24 m·s⁻² without an accumulator during testing of a 312 kg load, whereas they were extremely low at 2.66 m·s⁻² when the accumulator was activated. Frequency-domain analysis verified that the main vibrations were within the range of 3–4 Hz, with FFT peak amplitudes dropping from 5.6 m·s⁻² to 2.4 m·s⁻² upon the accumulator’s operation. The observations verify the effectiveness of the accumulator in vibration intensity reduction, absence of high-frequency shock loads, and ride comfort, along with structural safety improvement. The study provides a solid platform for further enhancement in vibration control techniques for agricultural machines and loader system design. Full article

The environmental burden of widely used protein sources in animal feeds, such as soybean and fishmeal, has raised concerns about the sustainability of current livestock production systems. In response, alternative protein sources are being explored, with insect meal emerging as a promising candidate. This study conducted a comparative Life Cycle Assessment (LCA) of four compound pig feed formulations differing in protein composition, incorporating soybean meal, fishmeal, and Tenebrio molitor (insect) meal. The LCA followed ISO 14040/44 standards and applied both mass-based and protein-based functional units (FUs) to examine how FU choice influences environmental outcomes. Results showed that crop-derived ingredients, particularly soybean meal, drove most environmental burdens due to land use change and fertilizer inputs. Replacing soybean with insect meal led to impact reductions in key environmental categories. Insect meal’s scalability, efficient land use, and potential waste valorisation supported its role as a sustainable alternative. The study also highlighted key sustainability issues not assessed by LCA, such as overfishing and ecosystem disruption, associated with fishmeal. Overall, insect meal appeared to be a strong replacement for soybean and fishmeal, with soy substitution proving key to reducing environmental burdens. Finally, the protein-based FU was more relevant given the study’s nutritional focus. Full article

Accurate postharvest quality evaluation of soybeans is essential for preserving product value and meeting industry standards. Traditional inspection methods are often inconsistent, labor-intensive, and unsuitable for high-throughput operations. This study presents a non-destructive soybean classification approach using a simplified reflectance-mode hyperspectral imaging system equipped with a single light source, eliminating the complexity and maintenance demands of dual-light configurations used in prior studies. A spectral–spatial data fusion strategy was developed to classify harvested soybeans into four categories: normal, split, diseased, and foreign materials such as stems and pods. The dataset consisted of 1140 soybean samples distributed across these four categories, with spectral reflectance features and spatial texture attributes extracted from each sample. These features were combined to form a unified feature representation for use in classification. Among multiple machine learning classifiers evaluated, Linear Discriminant Analysis (LDA) achieved the highest performance, with approximately 99% accuracy, 99.05% precision, 99.03% recall and 99.03% F1-score. When evaluated independently, spectral features alone resulted in 98.93% accuracy, while spatial features achieved 78.81%, highlighting the benefit of the fusion strategy. Overall, this study demonstrates that a single-illumination HSI system, combined with spectral–spatial fusion and machine learning, offers a practical and potentially scalable approach for non-destructive soybean quality evaluation, with applicability in automated industrial processing environments. Full article

Soybean (Glycine max L.) is one of the world’s most important sources of plant-based protein, with a protein content exceeding 35–40% (dry basis), along with other essential nutritional benefits. Ideally, soybeans are field-dried to approximately 13% moisture content (wet basis, wb); however, adverse weather conditions can necessitate harvesting at elevated moisture levels sometimes exceeding 20% (wb). In such cases, mechanized drying systems, particularly in northern U.S. regions, become essential for safe storage and quality preservation. This study investigated the effects of drying temperature, airflow rate, and initial moisture content on drying kinetics and kernel integrity using mathematical modeling. Drying behavior was modeled using fractional calculus and compared to the empirical Page model, while kernel cracking and breakage were analyzed using logistic regression. Both fractional and Page models exhibited strong agreement with experimental data (R² = 0.903–0.993). The fractional model achieved superior predictive accuracy, improving RMSE and MAE by 83.7% and 81.2%, respectively, compared to the Page model. Cracking and breakage were more strongly influenced by drying temperature than by initial moisture content, with the greatest quality degradation occurring at high temperatures. Optimal drying conditions were identified as temperatures below 27 °C and initial moisture contents between 19 and 20% (wb), which best preserved kernel quality. Logistic models more accurately predicted breakage than cracking, confirming their effectiveness in assessing mechanical damage during drying. The results affirm the suitability of fractional order models for accurately capturing drying kinetics, while logistic models offer robust performance for evaluating physical quality degradation. These modeling approaches provide a framework for efficient and quality-preserving soybean drying strategies in regions reliant on off-field drying systems. Full article

Monitoring the development of greenhouse crops is essential for optimising yield and ensuring the efficient use of resources. A system for monitoring hemp (Cannabis sativa L.) cultivation under greenhouse conditions using computer vision has been developed. This system is based on open-source automation software installed on a single-board computer. It integrates various temperature and humidity sensors and surveillance cameras, automating image capture. Hemp seeds of the Tiborszallasi variety were sown. After germination, plants were transplanted into pots. Five specimens were selected for growth monitoring by image analysis. A surveillance camera was placed in front of each plant. Different approaches were applied to analyse growth during the early stages: two traditional computer vision techniques and a deep learning algorithm. An average growth rate of 2.9 cm/day was determined, corresponding to 1.43 mm/°C day. A mean MAE value of 1.36 cm was obtained, and the results of the three approaches were very similar. After the first growth stage, the plants were subjected to water stress. An algorithm successfully identified healthy and stressed plants and also detected different stress levels, with an accuracy of 97%. These results demonstrate the system’s potential to provide objective and quantitative information on plant growth and physiological status. Full article

The precise identification of plant diseases is essential for improving agricultural productivity and reducing reliance on human expertise. Deep learning frameworks, belonging to the YOLO series, have demonstrated significant potential in the real-time detection of plant diseases. There are various factors influencing model performance; activation functions play an important role in improving both accuracy and efficiency. This study proposes αSiLU, a modified activation function developed to optimize the performance of YOLOv11n for plant disease-detection tasks. By integrating a scaling factor α into the standard SiLU function, αSiLU improved the effectiveness of feature extraction. Experiments are conducted on two different plant disease datasets—tomato and cucumber—to demonstrate that YOLOv11n models equipped with αSiLU outperform their counterparts using the conventional SiLU function. Specifically, with α = 1.05, mAP@50 increased by 1.1% for tomato and 0.2% for cucumber, while mAP@50–95 improved by 0.7% and 0.2% each. Additional evaluations across various YOLO versions confirmed consistently superior performance. Furthermore, notable enhancements in precision, recall, and F1-score were observed across multiple configurations. Crucially, αSiLU achieves these performance improvements with minimal effect on inference speed, thereby enhancing its appropriateness for application in practical agricultural contexts, particularly as hardware advancements progress. This study highlights the efficiency of αSiLU in the plant disease-detection task, showing the potential in applying deep learning models in intelligent agriculture. Full article

Two-way channel irrigation pumping stations are widely used along rivers for irrigation and drainage. Due to fluctuating internal and external water levels, these stations often operate under ultra-low or near-zero head conditions, leading to poor hydraulic performance. This study employs computational fluid dynamics (CFD) to investigate such systems’ pressure fluctuation and chaotic dynamic characteristics. A validated 3D model was developed, and the wavelet transform was used to perform time–frequency analysis of pressure signals. Phase space reconstruction and the Grassberger–Procaccia (G–P) algorithm were applied to evaluate chaotic behavior using the maximum Lyapunov exponent and correlation dimension. Results show that low frequencies dominate pressure fluctuations at the impeller inlet and guide vane outlet, while high-frequency components increase significantly at the intake bell mouth and outlet channel. The maximum Lyapunov exponent in the impeller and guide vane regions reaches 0.0078, indicating strong chaotic behavior, while negative values in the intake and outlet regions suggest weak or no chaos. This integrated method provides quantitative insights into the unsteady flow mechanisms, supporting improved stability and efficiency in ultra-low-head pumping systems. Full article