Search Results (156)

Yellow rust (Puccinia striiformis) is a common wheat disease that significantly reduces yields, particularly in seasons with cooler temperatures and frequent rainfall. Early detection is essential for effective control, especially in key wheat-producing regions such as Southern Dobrudja, Bulgaria. This study presents a UAV-based approach for detecting yellow rust using only RGB imagery and deep learning for pixel-based classification. The methodology involves data acquisition, preprocessing through histogram equalization, model training, and evaluation. Among the tested models, a UnetClassifier with ResNet34 backbone achieved the highest accuracy and reliability, enabling clear differentiation between healthy and infected wheat zones. Field experiments confirmed the approach’s potential for identifying infection patterns suitable for precision fungicide application. The model also showed signs of detecting early-stage infections, although further validation is needed due to limited ground-truth data. The proposed solution offers a low-cost, accessible tool for small and medium-sized farms, reducing pesticide use while improving disease monitoring. Future work will aim to refine detection accuracy in low-infection areas and extend the model’s application to other cereal diseases. Full article

Functional flours, high in bioactive compounds, have garnered increasing attention, driven by consumer demand for alternative ingredients and the nutritional limitations of wheat flour. This study explores the thermal stability of phenolic compounds in various functional flours using visible, near and shortwave-infrared (Vis–NIR–SWIR) spectroscopy (350–2500 nm), integrated with machine learning (ML) algorithms. Random Forest models were employed to classify samples based on flour type, baking temperature, and phenolic concentration. The full spectral range yielded high classification accuracy (0.98, 0.98, and 0.99, respectively), and an explainability framework revealed the wavelengths most relevant for each class. To address concerns regarding color as a confounding factor, a targeted spectral refinement was implemented by sequentially excluding the visible region. Models trained on the 1000–2500 nm and 1400–2500 nm ranges showed minor reductions in accuracy, suggesting that classification is not solely driven by visible characteristics. Results indicated that legume and wheat flours retain higher total phenolic content (TPC) under mild thermal conditions, whereas grape seed flour (GSF) and olive stone flour (OSF) exhibited notable thermal stability of TPC even at elevated temperatures. These first findings suggest that the proposed non-destructive spectroscopic approach enables rapid classification and quality assessment of functional flours, supporting future applications in precision food formulation and quality control. Full article

Crop disease identification is a pivotal research area in smart agriculture, forming the foundation for disease mapping and targeted prevention strategies. Among the most prevalent global wheat diseases, powdery mildew—caused by fungal infection—poses a significant threat to crop yield and quality, making early and accurate detection crucial for effective management. In this study, we present QY-SE-MResNet34, a deep learning-based classification model that builds upon ResNet34 to perform multi-class classification of wheat leaf images and assess powdery mildew severity at the single-leaf level. The proposed methodology begins with dataset construction following the GBT 17980.22-2000 national standard for powdery mildew severity grading, resulting in a curated collection of 4248 wheat leaf images at the grain-filling stage across six severity levels. To enhance model performance, we integrated transfer learning with ResNet34, leveraging pretrained weights to improve feature extraction and accelerate convergence. Further refinements included embedding a Squeeze-and-Excitation (SE) block to strengthen feature representation while maintaining computational efficiency. The model architecture was also optimized by modifying the first convolutional layer (conv1)—replacing the original 7 × 7 kernel with a 3 × 3 kernel, adjusting the stride to 1, and setting padding to 1—to better capture fine-grained leaf textures and edge features. Subsequently, the optimal training strategy was determined through hyperparameter tuning experiments, and GrabCut-based background processing along with data augmentation were introduced to enhance model robustness. In addition, interpretability techniques such as channel masking and Grad-CAM were employed to visualize the model’s decision-making process. Experimental validation demonstrated that QY-SE-MResNet34 achieved an 89% classification accuracy, outperforming established models such as ResNet50, VGG16, and MobileNetV2 and surpassing the original ResNet34 by 11%. This study delivers a high-performance solution for single-leaf wheat powdery mildew severity assessment, offering practical value for intelligent disease monitoring and early warning systems in precision agriculture. Full article

Wheat disease detection is a crucial component of intelligent agricultural systems in modern agriculture. However, at present, its detection accuracy still has certain limitations. The existing models hardly capture the irregular and fine-grained texture features of the lesions, and the results of spatial information reconstruction caused by standard upsampling operations are inaccuracy. In this work, the GDFC-YOLO method is proposed to address these limitations and enhance the accuracy of detection. This method is based on YOLOv11 and encompasses three key aspects of improvement: (1) a newly designed Ghost Dynamic Feature Core (GDFC) in the backbone, which improves the efficiency of disease feature extraction and enhances the model’s ability to capture informative representations; (2) a redesigned neck structure, Disease-Focused Neck (DF-Neck), which further strengthens feature expressiveness, to improve multi-scale fusion and refine feature processing pipelines; and (3) the integration of the Powerful Intersection over Union v2 (PIoUv2) loss function to optimize the regression accuracy and convergence speed. The results showed that GDFC-YOLO improved the average accuracy from 0.86 to 0.90 when the cross-overmerge threshold was 0.5 (mAP@0.5), its accuracy reached 0.899, its recall rate reached 0.821, and it still maintained a structure with only 9.27 M parameters. From these results, it can be known that GDFC-YOLO has a good detection performance and stronger practicability relatively. It is a solution that can accurately and efficiently detect crop diseases in real agricultural scenarios. Full article

Crop height is a key indicator of plant development and growth dynamics, offering valuable insights for temporal crop monitoring. However, modeling its variation across phenological stages remains challenging due to canopy structural changes. This study aimed to predict wheat height throughout the growth cycle by integrating radar remote sensing data with a phenology-informed clustering approach. The research was conducted in three wheat fields in Umbria, Italy, from 30 January to 10 June 2024, using in-field height measurements, phenological observations, and Sentinel-1 acquisitions. Backscatter variables (VH, VV, and CR) were processed using two speckle filters (Lee 7 × 7 and Refined Lee), alongside additional radar-derived parameters (entropy, anisotropy, alpha, and RVI). Fuzzy C-means clustering enabled the classification of observations into two phenological groups, supporting the development of stage-specific linear regression models. Results demonstrated high accuracy during early growth stages (tillering to stem elongation), with R² values of 0.76 (RMSE = 6.88) for Lee 7 × 7 and 0.79 (RMSE = 6.35) for Refined Lee. In later stages (booting to maturity), model performance declined, with Lee 7 × 7 outperforming Refined Lee (R² = 0.51 vs. 0.33). These findings underscore the potential of phenology-based modeling approaches to enhance crop height estimation and improve radar-driven crop monitoring. Full article

As the global food crisis worsens, enhancing crop yields on saline–alkali soils has become a critical measure for ensuring global food security. Wheat (Triticum aestivum L.), one of the world’s most important staple crops, is particularly sensitive to phosphorus availability, making appropriate phosphorus fertilization a key and manageable strategy to optimize yield. Although many studies have explored phosphorus fertilization strategies, most have focused on non-saline soils or generalized conditions, leaving a critical gap in understanding how phosphorus application affects wheat yield, soil nutrient dynamics, and nutrient uptake efficiency under saline–alkali stress. Therefore, further investigation is required to establish phosphorus management practices specifically adapted to saline–alkali environments for sustainable wheat production. To address this gap, the experiment was designed with varying phosphorus fertilizer application rates based on P₂O₅ content (0, 60 kg/hm², 120 kg/hm², 180 kg/hm², and 240 kg/hm²), considering only the externally applied phosphorus without accounting for the inherent phosphorus content of the soil. The results indicated that as the phosphorus application rate increased, the wheat yield first increased and then decreased. The highest yield (6355 kg·hm⁻²) was achieved when the phosphorus application rate reached 120 kg/hm², with an increase of 47.2–63.5% compared to the control (no fertilizer). Similarly, biomass, thousand-grain weight, and the absorption of nitrogen, phosphorus, and potassium in both straw and grains exhibited the same increasing-then-decreasing trend. Mechanistic analysis revealed that phosphorus fertilization enhanced soil alkali–hydrolyzable nitrogen, available phosphorus, and available potassium, thereby promoting nutrient uptake and ultimately improving grain yield. The innovations of this study lie in its focus on phosphorus management specifically under saline–alkali soil conditions, its integration of soil nutrient changes and plant physiological responses, and its identification of the optimal phosphorus application threshold for balancing yield improvement and nutrient efficiency. These findings provide a scientific basis for refining phosphorus fertilization strategies to sustainably boost wheat productivity in saline–alkali environments. Full article

This study investigates the impact of climate variability on wheat production in Algeria’s semi-arid interior plains from 2014 to 2024, aiming to curb the challenges of rainfed wheat cultivation, optimize irrigation, and improve water productivity. The Soil–Water–Atmosphere–Plant (SWAP) model-driven approach refined irrigation scheduling to mitigate climate-induced losses and improve resource efficiency. Using historical climate data, soil properties, and wheat growth observations from the experimental farm of the Technical Institute for Field Crops, the SWAP model was calibrated and validated using one-factor-at-a-time sensitivity analysis, achieving a coefficient of determination (R²) of 0.93 and a Normalized Root Mean Squared Error (NRMSE) of 17.75. Two drought-based irrigation indices, Soil Moisture Drought Index (SMDI) and Crop Water Stress Index (CWSI), guided adaptive irrigation strategies, showing a significant reduction in crop failure during drought periods. Results revealed a strong link between rainfall variability and wheat yield. Adopting a 9-day irrigation interval could increase water productivity to 18.91 kg ha⁻¹ mm⁻¹, enhancing yield stability under varying climatic conditions. The SMDI approach maintained soil moisture during extreme drought, while CWSI optimized water use in normal and wet years. This study integrates SMDI and CWSI into a validated irrigation framework, offering data-driven strategies to enhance wheat production resilience. Findings support sustainable water management and provide practical insights for policymakers and farmers to refine irrigation planning and climate adaptation, contributing to long-term agricultural sustainability. Full article

Pea and lentil flours are added to baked foods, pastas, and snacks to improve nutritional quality and functionality compared to products made solely with refined wheat flour. However, the effect of whole pulses versus their serving size equivalent of flour on blood glucose has not been investigated in persons with altered glycemic response. Health claims for whole pulses are based on a ½ cup amount whereas commercial pulse flour servings are typically a smaller size. The glycemic responses of four treatment meals containing 50 g available carbohydrate as ½ cup whole pulse or the dry weight equivalent of pulse flour were compared with a control beverage (Glucola^®). Eleven adults with type 2 diabetes mellitus (T2DM) and eight adults with metabolic syndrome (MetS) completed the study. Venous blood samples were collected at fasting and at 30 min intervals postprandial for three hours. Changes in net difference in plasma glucose over time from baseline and incremental area under the curve (iAUC) segments were analyzed. All four pulse meals attenuated the iAUC compared to the control from 0 to 120 min for T2DM participants and 0–180 min for MetS participants. Whole pulses produced a lower glycemic response than pulse flours in the early postprandial period for persons with T2DM and during the overall test period for those with MetS. Full article

Previous research on soil bacteria focused on refining the nitrogen (N) rates during the wheat (Triticum aestivum L.) growth cycle. Studies concerning how additional and split N topdressing applications can affect wheat rhizobacteria are limited. To address this, a two-year field experiment took the cultivar ‘Gaoyou 2018’ of winter wheat as the experimental material from October 2020 to June 2022. Six nitrogen application regimes were established, including no nitrogen application (T1), single topdressing applications of 120 kg ha⁻¹ (T2) and 80 kg ha⁻¹ (T3) at the jointing stage, and split topdressing applications combining 80 kg ha⁻¹ at jointing with 40 kg ha⁻¹ at the booting stage (T4), the flowering stage (T5), and 10th day post-anthesis (T6). The delayed impacts of the split topdressing time on the rhizobacteria diversity were observed in the second year, with T4 exhibiting a 10.5% higher Chao1 index and 2% greater Shannon diversity than T6. Results from both years indicated that the dominant bacterial phylum compositions in the winter wheat rhizosphere were similar across the nitrogen treatments. The additional N treatments fostered 22.9–27.9% Bacteroidita abundance but diminished 24.0–35.9% Planctomycetota, compared to the thenon-fertilized control (T1). T6 increased the α-Proteobacteria abundance by 15.7–22.0% versus T4, while the N topdressing redistribution to the booting stage increased the MND1 genus abundance in Proteobacteria by 31.3–62.5% compared to T2. Redundancy analysis identified that the rhizosphere pH and soil moisture content were the predominant environmental drivers shaping the winter wheat rhizobacteria. Preliminary findings revealed that split nitrogen application during the jointing and booting stages of winter wheat improved the edaphic micro-environment and modulated the proliferation of beneficial rhizobacteria. However, this change was not transmitted to the yield variation. These results suggest that short-term N management strategies may enhance ecological benefits by intensifying soil–plant–microbe interactions, yet they lack direct agronomic yield advantages. Long-term trials are required to establish causality between rhizosphere microbial community dynamics and crop productivity under split N management regimes. Full article

The ability to substitute peat use in horticulture with potentially more sustainable alternatives hinges on the local availability of suitable biomass resources and whether these resources can be easily processed to achieve similar agronomic effectiveness to peat. This review estimates potential biomass availability in Ireland by reviewing production statistics and industry reports and identifying current uses and hypothetical processed biomass quantities. Annual estimates of the major biomass resources available in Ireland are 488,935 m³ of woody residues (mainly Sitka spruce pine) and 789,926 m³ of arable straws (from oats, wheat, barley, oil seed rape). The potential major processing pathways for the available biomass are mechanical (extruded, thinscrew, hammer milled, disc refined), carbonization (pyrolysis and hydrothermal carbonization) and composting. This review of the literature indicates that the major challenges to pyrolyzed alternatives in growth media include high alkalinity, high salinity and low water holding capacity. When biomass is processed into fibers, it requires additional processing to address nutrient immobilization (nitrogen and calcium) and the presence of phytotoxic compounds. We discuss possible solutions to these challenges in terms of agronomic management (altering fertigation, irrigation rates etc.), biomass conversion process optimization (changing conditions of processes and applying additives) and novel growth media formulations with various material inputs that complement each other. We conclude that while national alternative biomass resources are available in sufficient volumes to potentially meet growing media requirements, significant further research and demonstration are required to convert these materials to growth media acceptable to both commercial and retail sectors. Research needs to focus on transforming these materials into growth media, and how they will impact agronomic management of crops. Furthermore to this, the optimization of biomass conversion processes and novel formulations incorporating multiple types of biomass need to be the focus as we transition from peat products in professional horticulture. Full article

This study explored the enhancement of antioxidant properties in bread by incorporating ginger powder while reducing wheat flour utilisation through partial replacement with cassava flour, addressing the issue that bread produced from refined wheat flour is low in antioxidants due to the removal of the aleurone layer during processing. The study investigated the effect of cassava flour and ginger powder addition on physicochemical properties (moisture content, water activity, firmness, crumb structure, density, volume, specific volume, and colour), antioxidant capacity (AC) using Ferric reducing antioxidant potential (FRAP), and total phenolic content (TPC) (by using the Folin Ciocalteu method) of bread. Seven bread samples were produced using the Chorleywood method (220 ± 1 °C at 25 min) using cassava flour (10 and 40%) only and with the combination of ginger powder (1 and 3%). The volume, specific volume, and firmness of the bread with 10% cassava flour and ginger powder were similar to the control (100% wheat flour). Breads containing 40% cassava flour had reduced volume and specific volume and increased firmness and density. The TPC and AC increased significantly (p < 0.05) with ginger powder addition. The study showed that 10% cassava flour and 3% ginger powder could be added to bread formulations to improve their phenolic content and antioxidant capacity without significantly affecting their quality. Full article

Remote sensing technologies are essential for monitoring crop development and improving agricultural management. This study investigates the automation of Sentinel-2 satellite data processing to enhance wheat growth monitoring and provide actionable insights for smallholder farmers. The objectives include (i) analyzing vegetation indices across phenological stages to refine crop growth monitoring and (ii) developing a cost-effective user-friendly web application for automated Sentinel-2 data processing. The methodology introduces the “Area Under the Curve” (AUC) of vegetation indices as an independent variable for yield forecasting. Among the indices examined (NDVI, EVI, GNDVI, LAI, and a newly developed RE-PAP), GNDVI and LAI emerged as the most reliable predictors of wheat yield. The findings highlight the importance of the Tillering to the Grain Filling stage in predictive modeling. The developed web application, integrating Python with Google Earth Engine, enables real-time automated crop monitoring, optimizing resource allocation, and supporting precision agriculture. While the approach demonstrates strong predictive capabilities, further research is needed to improve its generalizability. Expanding the dataset across diverse regions and incorporating machine learning and Natural Language Processing (NLP) could enhance automation, usability, and predictive accuracy. Full article

This study investigated the contribution of pulse starches (PSs) to the slowly digestible starch (SDS) properties observed in pulses. Purified pulse starches from 17 commonly consumed pulses were examined, focusing on their digestion kinetics using a pancreatic alpha-amylase (PAA) and rat intestinal acetone powder (RIAP) mixture. Chickpea starch, exhibiting a slow digestibility profile, was incorporated as an ingredient to confer slow digestibility to refined wheat flour bread. Our findings reveal that some PSs exhibited low digestibility when gelatinized (100 °C, 30 min) and retrograded (7 days, 4 °C). Rapid retrogradation was observed in starch from chickpeas, lentils, field peas, adzuki beans, navy beans, large lima beans, and great northern beans. The incorporation of chickpea starch into fortified bread significantly improved its slow digestibility properties. This study reveals the potential of pulse starch as a promising functional ingredient for baked products, related to the faster retrogradation of many pulse-sourced starches. These findings contribute valuable insights into the slow digestibility attributes of pulse starches for developing food products with enhanced nutritional profiles. Full article

This paper presents a novel 5-factor model for agricultural commodity risk premiums, an approach not explored in previous research. The model is applied to the specific cases of corn, soybeans, and wheat. Calibration is achieved using a Kalman filter and maximum likelihood, with data from futures markets and analysts’ forecasts. Risk premiums are computed by comparing expected and futures prices. The model considers that risk premiums are not solely determined by contract maturity but also by the marketing crop years. These crop years, in turn, are influenced by the respective harvest periods, a crucial factor in the agricultural commodity market. Results show that risk premiums vary across commodities, with some exhibiting positive and others negative values. While maturity affects risk premiums’ size, sign, and shape, the crop year plays a critical role, especially in the case of wheat. As speculators in the financial markets demand a positive risk premium, its sign provides insights into whether they are buyers or sellers of futures for each crop year, maturity, and commodity. This research offers valuable insights into grain price behavior, highlighting their similarities and differences. These findings have significant practical implications for market participants seeking to refine their trading and risk management strategies and for future research on the industry structure for each crop. Moreover, this enhanced understanding of risk premiums can be directly applied in the finance and agricultural industries, improving decision-making processes. Full article

Artisan bread, known for its simple recipes, natural ingredients, and traditional techniques, has seen a surge in demand, especially following the COVID-19 pandemic. Small bakeries emphasize extended fermentation processes and prioritize sensory qualities in their products. However, the impact of ingredients on the quality characteristics of artisan bread remains underexplored. Here, a set of breads from artisanal bakeries in Valencia, Spain, was characterized. Bread dough pH, total titratable acidity (TTA), and acid content were influenced by flour type and sourdough use, creating different environments for volatile compound (VOC) generation. Over 50 VOCs, including aldehydes, alcohols, acids, and furans, were identified in crumb and crust samples of most artisan bread samples, compared to fewer than 20 VOCs in control industrial bread, where ketones dominated. Whole flours, such as spelt, durum wheat, or T80, along with the leavening agent, affected the abundance of certain volatiles, particularly in the crust. Additionally, the use of spelt or wheat flour impacted crumb texture, while sourdough improved taste intensity, acidity, and crumb color. Finally, certain sensory attributes were also influenced by the presence of hydrocarbons and furans in the volatile fraction of both crumb and crust. Overall, the results provide new insights into the influence of ingredients on the quality of artisan bread and can help bakers refine recipes while maintaining a natural ingredient list. Hence, the work is substantial for the artisan bread industry and consumers. Full article