Search Results (2,077)

Accurate tomato maturity detection is critical for optimizing key agricultural operations in precision agriculture, including harvesting, grading, and quality control. Despite advances in deep learning and machine vision, reliable detection in real-world environments remains challenging due to cluttered backgrounds, dense fruit clustering, and subtle color differences between maturity stages. In response to these challenges, we present TAA-YOLOv8, an attention-enhanced detection architecture integrating a novel Tomato-Adaptive Attention (TAA) module that performs sequential channel–spatial feature refinement using an adaptive 1D convolution for channel recalibration and a balanced 5 × 5 spatial kernel for improved localization, enhancing discriminative representation while preserving computational efficiency. The framework is evaluated on three datasets representing diverse agricultural environments: a newly introduced Cross-Regional Tomato dataset collected from open-field farms in Bangladesh and greenhouse facilities in Japan, and two public benchmarks, Laboro Tomato and Tomato Plantfactory. TAA-YOLOv8m outperforms baseline YOLOv8m, achieving mAP@50–95 improvements of +9.29%, +9.00%, and +6.65% with F1-scores of 0.968, 0.976, and 0.955, respectively. It further surpasses attention-enhanced variants and RT-DETR-L, and remains competitive with YOLOv11m. Gradient-Weighted Class Activation Mapping (Grad-CAM) shows concentrated fruit-centered activations, providing transparent decision-making evidence and supporting stakeholder confidence in practical deployment within vision-based agricultural management systems. Full article

Crop leaf disease segmentation in complex natural environments remains challenging because lesion regions often exhibit substantial scale variation, blurred boundaries, and severe background interference. To address these issues, this study proposes a Multi-Scale Feature Rectification Network (MFR-Net) for crop leaf disease segmentation. The proposed network adopts an EfficientNetV2-S-based encoder to extract hierarchical features, incorporates a hybrid attention mechanism to enhance lesion-sensitive spatial and channel representations, introduces a Cross-Window Atrous Spatial Pyramid Pooling (CWASPP) module to strengthen multi-scale contextual modeling, and employs a Feature Rectification Module (FRM) in the decoder to alleviate semantic inconsistency during cross-level feature fusion. Experiments on a Kaggle-derived benchmark constructed from the unaugmented data folder of the public Leaf Disease Segmentation Dataset, containing 588 diseased-leaf images and 588 corresponding binary lesion masks, showed that MFR-Net achieved the highest mIoU of 74.27% and the highest Recall of 87.61% among the compared methods, and maintained competitive Dice performance (84.25%) with 25.10 M parameters and 37.55 G FLOPs. Ablation results further confirmed the effectiveness of the proposed design, with CWASPP providing the most notable individual contribution. Additional experiments were conducted on an independent Apple Leaf Dataset comprising 3197 image–mask pairs, collected under mixed controlled and natural field-like imaging conditions. The results showed competitive performance under a different data distribution, and robustness evaluation further verified stable performance under severe noise, blur, darkness, and contrast variation. All experiments were implemented in PyTorch 2.11.0 (CUDA 12.8) on a workstation equipped with an NVIDIA GeForce RTX 4060 Ti GPU (8 GB). These results indicate that MFR-Net provides an effective and robust solution for crop leaf disease segmentation in complex agricultural scenarios. Full article

The current model of agricultural development, largely focused on the intensification of production, causes increased pressure on the natural environment and, at the same time, does not guarantee sufficient food supplies in the era of global demographic expansion. In light of current environmental changes and the escalating food shortage, the modern agricultural paradigm must strive to achieve a balance between productivity and the quality of agricultural products produced within an environmentally responsible production system. A promising and sustainable tool for future agriculture is a biorational model of agricultural production based, among other things, on the biological protection of agricultural products. The study aimed to assess the effectiveness of biological control agents containing entomopathogenic nematodes in controlling pests from the class Gastropoda. The tests showed that these preparations inhibited the feeding intensity of the analyzed pests. Among the insecticidal nematodes, the biological product containing S. carpocapsae at doses of 2000 and 4000 LJ/m² demonstrated the highest effectiveness (mass loss: A. distinctus: 0.61 g, 0.58 g; D. reticulatum: 0.60, 0.71 g). The research conducted indicates that preparations containing entomopathogenic nematodes have the potential to reduce damage caused by slugs in crops. Full article

Tracking agrivoltaic (TAV) systems represent a significant form of agrivoltaics, which optimize solar energy capture through the dynamic adjustment of photovoltaic (PV) panel tilt angles. However, there is limited research on the effects of TAV systems on the three-dimensional spatial distribution of the light environment within PV arrays and their impacts on agricultural production. Therefore, a comparative experiment was conducted between wheat production under a TAV system and traditional open-field cultivation. Solar radiation intensity sensors were deployed to continuously monitor the dynamic changes in solar radiation under and between the PV panels throughout the entire growth period. Simultaneously, a light environment model for the TAV system was constructed, and the photosynthetic parameters of wheat leaves, as well as yield, were measured. The results indicated that the light environment within the system exhibited significant gradient attenuation, with average light capture rates of 43.2% and 46.1% for the inter-panel and under-panel measurement points, respectively. The model results confirmed that the synergistic adjustment of panel tilt angle and solar altitude angle significantly affected the shading effects, leading to notable spatiotemporal heterogeneity in the light environment during the winter solstice, spring equinox, and summer solstice. This heterogeneity showed as regular variations in shadows and radiation, collectively forming a dynamic light–thermal environment that influences crop growth. Wheat yields under and between the panels decreased by 11.5% and 6.6%, respectively, compared to the open-field control, with yields of 4625.9 kg·hm⁻² and 4883.6 kg·hm⁻². Additionally, the photosynthetic characteristics of the leaves effectively reflected the yield differences. Overall, the comprehensive benefit assessment demonstrates that the TAV system can effectively mitigate the reduction in wheat yield in PV farmlands. This study provides a theoretical basis for optimizing the light environment in AV systems. Full article

Fertilizer coating is an emerging strategy in fertilizer management in the quest to decrease their loss and environmental impact. Nitrous oxide (N₂O) is a significant greenhouse gas, and agricultural soils happen to be an important anthropogenic source of N₂O gases, mainly because of the use of nitrogen (N) fertilizers such as urea. This study examined the effects of double urea coating with nano-sulfur (NS) and organic materials; lignite, biochar and compost on N₂O fluxes from silt loam and sandy loam soils. N₂O fluxes were measured using an N₂O analyzer in a controlled environment for a period of 26 days. Cumulative N₂O fluxes were calculated for different treatments (nano-sulfur; NS, NS + lignite, NS + biochar, and NS + compost) as coatings on urea fertilizer with propagated uncertainties. Sandy loam soil had higher maximum N₂O emission (155.64 µg N m⁻² h⁻¹) compared to silt loam soil (24.47 µg N m⁻² h⁻¹). Uncoated urea and urea + NS coating resulted in higher N₂O emissions in both soils. Meanwhile, NS + organic second layer coatings decreased the N₂O fluxes, especially in sandy loam soil. The second organic layer coatings lowered the N₂O emissions with relatively lower effects in silt loam soil (3.8–7.0%) and a higher reduction in sandy loam soil (35.2–41.5%). Among the second organic coating materials, NS + lignite performed best, followed by NS + biochar and NS + compost. The results indicate that the urea coating as fertilizer management strategy as well as soil texture have considerable effects on fertilizer-induced N₂O emissions. The present study does not address the individual effects of organic coatings on N₂O emissions; furthermore, the characterization of the size distribution and morphology of the synthesized nano-sulfur, as well as the physicochemical properties (e.g., particle size, pH, C/N ratio, elemental composition) of the lignite, biochar, and compost coating materials, are omitted. The results of these analyses, together with the physical and chemical characterization of the produced organo-mineral fertilizers, will be presented in a forthcoming paper. Full article

Land-use planning in ecologically sensitive landscapes requires balancing biodiversity conservation, ecosystem service provision, agricultural production, settlement expansion, and infrastructure demand within a single spatial system. This challenge is particularly significant in Mediterranean environments, where long-term land transformations and increasing development pressures intensify conflicts among competing land-use priorities. Accordingly, the present study develops an integrated spatial zoning and decision-support framework for Osmaniye Province, southern Türkiye. The framework integrates fuzzy multi-criteria evaluation, CatBoost-based machine learning, SHAP-based interpretability, and NSGA-II multi-objective optimization. The workflow followed a sequential decision process in which an expert-derived zoning surface was first established through fuzzy evaluation, reconstructed from continuous spatial predictors using CatBoost, interpreted through SHAP, and refined through NSGA-II under explicit spatial constraints. By using the expert-derived zoning surface as the learning target, the CatBoost stage aimed to evaluate the internal consistency and spatial learnability of the planning logic within a present-day zoning context. The results indicated that the integrated framework distinguished conservation, controlled-use, and development priorities while identifying the key environmental and anthropogenic drivers shaping class-specific zoning outcomes. The final zoning structure allocated 37.9% of the study area to conservation, 43.6% to controlled use, and 18.5% to development. The study shows that by including a transitional zone with varying proportions of conservation, controlled use, and development, a more balanced distribution among the three goals can be achieved compared to a fixed partition into these three zones. The findings further demonstrate that this approach is more effective than current zoning, which does not accommodate such trade-offs. Full article

Kale is widely recognized as a nutritional superfood. This study investigated the impact of carbon dioxide (CO₂) concentrations (400, 800, and 1200 µmol mol⁻¹) on the growth, yield, physiological responses, and nutritional contents of two kale cultivars (‘Curly Kale’ and ‘Red Ursa’) grown in a plant factory. A completely randomized design was used to evaluate these parameters. Based on the results, increasing the CO₂ concentration to 1200 µmol mol⁻¹ significantly enhanced stem height, shoot, and root fresh weight and dry weight in ‘Curly Kale’ and ‘Red Ursa’, compared to the other CO₂ concentrations. Increasing CO₂ concentration to 1200 µmol mol⁻¹ significantly enhanced net photosynthesis rate, stomatal conductance, transpiration rate, and water use efficiency in ‘Curly Kale’. In addition, compared to ambient CO₂, the increase in the CO₂ concentration to 800 µmol mol⁻¹ significantly increased the vitamin C, soluble protein, and total phenolic contents, while reducing the nitrate accumulation in both cultivars. However, further elevation to 1200 µmol mol⁻¹ CO₂ markedly decreased the vitamin C content and total amino acids, including both the essential and non-essential amino acids. Among the tested concentration gradients, 800 µmol mol⁻¹ CO₂ was identified as the most cost-effective level for maintaining nutrient density, whereas 1200 µmol mol⁻¹ CO₂ increased unit production costs for ‘Red Ursa’ due to a lack of significant yield returns. In conclusion, enriching the CO₂ concentration to 800 µmol mol⁻¹ provided a balance between improved growth, photosynthetic performance, and optimal nutritional quality, while ensuring economic feasibility and preserving the superfood identity of kale. Full article

The field inspection and ripeness detection of tomatoes in China remain heavily dependent on manual labor, while existing robotic solutions often exhibit limited functionality, poor environmental adaptability, prohibitive hardware costs, and unstable positioning accuracy. To address these limitations, this study proposes an intelligent tomato inspection robot that seamlessly integrates real-time ripeness recognition with precise spatial localization. Built upon a Raspberry Pi 5 core controller, the robot employs a lightweight, layered modular architecture designed to flexibly navigate complex agricultural environments. A comprehensive, multi-dimensional image dataset of tomato ripeness was constructed to train a three-category detection model based on the YOLOv8n architecture. Following 413 training epochs, the model demonstrated exceptional performance, achieving an overall mAP@0.5 of 87.8% and an mAP@0.5:0.95 of 72.7% on the held-out test dataset. In field inspections, the system achieved detection precisions of 82.22% for immature tomatoes, 92.66% for half-ripened tomatoes, and 100% for fully ripe tomatoes, successfully identifying all ripe tomatoes and satisfying the practical demands of field inspection. Furthermore, the integration of an Ultra-Wideband positioning system yielded an overall Root Mean Square Error of 0.231 m, successfully confining positioning errors to within 0.24 m to fully satisfy the stringent localization demands of crop-level inspection. Field evaluations confirmed that under optimal configurations, the robot can efficiently inspect a 50-m planting row in 10 min (±1 min) and maintains a continuous operational battery life of 2 h (±10 min). The core contribution of this work is the system-level integration and optimization of technologies for greenhouse agriculture. This integrated design achieves low hardware cost and high deployment flexibility, addressing longstanding challenges of labor-intensive inspection and delayed harvesting, and delivering a practical solution for intelligent tomato plantation management. Full article

Optimizing plant density and vegetative growth duration is important for improving productivity in controlled-environment medicinal cannabis cultivation. Although both factors strongly influence canopy development and yield, their combined effects under modern high-intensity LED lighting, and particularly their consequences for cannabinoid uniformity across the canopy, remain insufficiently characterized. This study examined how planting density and vegetative duration influence plant growth, yield, and cannabinoid concentration in Cannabis sativa L. (strain ‘Fat Banana’) grown under controlled environment conditions, high-intensity LED lighting and precision fertigation. Two vegetative durations (10 and 28 days) were evaluated in separate but identical controlled-environment chambers under broad-spectrum high-intensity LED lighting and automated precision fertigation on rockwool substrate. The 10-day regime compared 8, 14 and 18 plants m⁻²; the 28-day regime compared 6, 8 and 10 plants m⁻². Each combination was replicated across two independent cultivation cycles, and because density levels differed between regimes, direct between-regime comparisons were restricted to the shared density of 8 plants m⁻². Extending the vegetative phase from 10 to 28 days increased plant height, stem diameter and internodal length. Area-based yield increased strongly with density, reaching 1091 g m⁻² at 18 plants m⁻² under the 10-day regime and 1009 g m⁻² at 10 plants m⁻² under the 28-day regime. Apical biomass exceeded basal biomass, but total THC concentration did not differ significantly among planting densities, vegetative durations or canopy positions. Higher planting densities combined with shorter vegetative periods can therefore increase area-based productivity while maintaining stable THC concentration under high-intensity LED cultivation. Full article

Reliable potato quality monitoring during postharvest handling requires compact sensing systems that can acquire chemically relevant information while operating on irregular tuber surfaces. In this study, a Flexible Spectral Sensing Gripper (FSSG) was developed by integrating a low-cost 12-channel visible/near-infrared (Vis/NIR) spectral sensor array, electronic components, and an ESP32-S microcontroller onto a flexible printed circuit (FPC) substrate encapsulated with PDMS. By embedding the sensing units into the grasping interface, the FSSG enables conformal, multi-point spectral acquisition during potato handling, reducing optical-coupling uncertainty associated with unstable contact. Spectral reflectance data were collected from potato tubers, and dry matter content (DMC) and starch content (SC) were determined by standard chemical analysis as reference values. Multiple linear regression (MLR) and partial least squares regression (PLSR) models were compared under Norm, SNV, MSC, SNV-Norm, and MSC-Norm preprocessing conditions, and support vector machine (SVM) classification was used to distinguish healthy and artificially induced deteriorated samples. Normalization combined with MLR provided the best performance among the evaluated regression approaches, achieving cross-validation coefficients of determination ($R_{CV}^2$) of 0.847 and 0.817 and RPD values of 2.557 and 2.345 for DMC and SC, respectively. The SVM model achieved 98.67% accuracy for healthy versus artificially induced deteriorated potato samples. Overall, the FSSG demonstrates the value of combining gripper-integrated spectral sensing with interpretable chemometric modeling for potato quality screening. The FSSG enables real-time non-destructive quality prediction and disease-detected classification of potatoes, improves sorting accuracy and production efficiency, and provides general sensing solutions for controlled-environment agriculture, cold-chain logistics, and value-added processing of agricultural products. Full article

Agriculture plays a relevant role in the food supply chain but is also a major contributor in terms of emissions. A possible solution to reduce its impact is to replace traditional machinery with innovative systems, such as agricultural rovers. In the proposed research, a case study of an agricultural rover, specifically designed to operate in orchards, is presented. The powertrain features a Li-ion battery pack as the primary energy source and a fuel cell system operating as a range extender unit. Hydrogen is stored on board using a metal hydride tank to enhance compactness. Once the traction and range extender power output control strategies were defined, experimental tests in a closed warehouse were performed. During the tests, the rover was manually controlled using a joystick, since the main focus was to evaluate the powertrain behavior rather than to test the autonomous driving algorithm. During the tests, different maneuvers in narrow spaces were performed. The results showed that the rover successfully accomplished the tasks and the range extender unit can effectively extend the rover autonomy up to +150% compared to the pure battery solution. This result was obtained considering a 15 min test carried out in an indoor environment with a polished concrete floor. Full article

The temperature management models for solar greenhouses exhibit strong regional dependency. Their application in non-target environments often faces significant limitations, frequently resulting in severe temperature control deviations. To address this challenge, seven solar greenhouses located in Lingyuan (Liaoning Province) and Yinan (Shandong Province) were utilized as experimental platforms. Using real-time environmental data collected by the NEUT-80S IoT monitoring system, backpropagation (BP) neural network models were trained and validated. Multiple stepwise regression analysis identified total solar radiation and sunshine duration as the primary determinants of cucumber yield. Based on these findings, a dynamic weight matrix was constructed using a solar radiation clustering algorithm. By integrating similarity distance and similarity coefficient, a microclimate similarity determination logic was established, leading to the proposal of an automatic model selection strategy with an 11-day update cycle. Quantitative validation demonstrated that when the threshold conditions—a similarity coefficient (R) ≥ 0.6 and a similarity distance (D) ≤ 0.85—are met, triggering the optimally matched model significantly improves the simulation goodness-of-fit (R²) from 0.6716 in the unmatched state to 0.9851. This strategy effectively achieves the cross-regional adaptation of high-yield temperature management models, providing robust technical support for the advancement of precision protected agriculture. Full article

This study evaluated the performance of thermochromic windows as dynamic envelopes for smart greenhouses, focusing on the light environment and cooling load under peak summer conditions. Four covering materials, glass, Low-E glass, polycarbonate, and thermochromic windows, were compared using EnergyPlus (v9.2.0) simulation for an 8-span greenhouse with a floor area of 1008 m² in Gwangju, South Korea, on a representative summer day of 21 July. Thermochromic properties were modeled with temperature-dependent SHGC variations from 0.521 at 25 °C to 0.425 at 85 °C. Results showed that thermochromic windows reduced noon illuminance by 75% compared to conventional glass, from 26,482 lux to 6628 lux, while maintaining adequate light levels above the compensation point for tomato and paprika cultivation. Simultaneously, peak cooling load decreased by 13.1%, from 537,929 W to 467,477 W, outperforming Low-E glass at 9.2% and polycarbonate at 7.0%. At peak hours of 1:00 p.m., when the glass surface temperature reached 60.5 °C, the thermochromic glazing reduced transmitted solar radiation by 37.8% per unit area compared to conventional glass. This study demonstrates that thermochromic windows effectively balance photosynthetic light provision and cooling energy reduction in smart greenhouses, offering a viable design solution for controlled environment agriculture under extreme summer conditions. Full article

Understanding how plants respond to high-energy ionizing radiation is essential for developing resilient crops for controlled-environment agriculture and future space exploration. This study investigates whether carbon-ion (¹²C) irradiation of dry seeds can modulate early development in lettuce (Lactuca sativa L.) and induce dose-dependent responses relevant to controlled-environment agriculture and space farming. Dry seeds of red- and green-leaf morphotypes were exposed to increasing radiation doses (0.3, 1, 10, 20, and 25 Gy) and evaluated for germination, early growth, anatomical traits, and polyphenol content. While germination remained unaffected, seedling growth showed a hormetic response: low doses (0.3–1 Gy) promoted elongation of roots and hypocotyls, whereas higher doses (10–25 Gy) progressively inhibited growth. Anatomical changes in vascular traits and increased polyphenol levels at low doses indicated structural and metabolic adaptations enhancing early stress resistance. Notably, the two morphotypes responded differently: red-leaf lettuce exhibited stronger early vigor, higher biomass accumulation, and relatively greater anatomical stability, particularly at low to moderate doses, while the green-leaf type showed earlier and more pronounced growth inhibition, likely associated with differences in phenolic metabolism and resource allocation. These findings suggest that carbon-ion irradiation induces a hormetic response capable of boosting early vigor and triggering acclimatory processes in lettuce, with morphotype-specific differences underscoring its potential for optimizing crop performance in controlled environments and future extraterrestrial agriculture. Full article