Effective pest management is crucial for enhancing agricultural productivity, especially for crops such as sugarcane and wheat that are highly vulnerable to pest infestations. Traditional pest management methods depend heavily on manual field inspections and the use of chemical pesticides. These approaches are often costly, time-consuming, labor-intensive, and can have a negative impact on the environment. To overcome these challenges, this study presents a lightweight framework for pest detection and pesticide recommendation, designed for low-resource devices such as smartphones and drones, making it suitable for use by small and marginal farmers. The proposed framework includes two main components. The first is a Pest Detection Module that uses a compact, lightweight convolutional neural network (CNN) combined with prototypical meta-learning to accurately identify pests even when only a few training samples are available. The second is a Pesticide Recommendation Module that incorporates environmental factors like crop type and growth stage to suggest safe and eco-friendly pesticide recommendations. To train and evaluate our framework, a comprehensive pest image dataset was developed by combining multiple publicly available datasets. The final dataset contains samples with different viewing angles, pest sizes, and background conditions to ensure strong generalization. Experimental results show that the proposed lightweight CNN achieves high accuracy, comparable to state-of-the-art models, while significantly reducing computational complexity. The Decision Support System additionally improves pest management by reducing dependence on traditional chemical pesticides and encouraging sustainable practices, demonstrating its potential for real-time applications in precision agriculture.
Yasmine Bedoui, Zein Kallas, Adrià Menéndez i Molist
et al.
Pricing is an essential element that significantly impacts the supply chain mechanisms. The primary objective of this study is to explore the transmission of producer-to-consumer prices in the Spanish fresh tomato industry. Employing the Threshold Vector Autoregressive model, and subsequently utilizing the Generalized Impulse Response Function, we investigated the nonlinear price adjustments that occur in response to positive and negative shocks affecting both tomato prices of consumers and producers. The findings show a clear pattern of distinct reactions between segments in response to shocks. Specifically, the speed and intensity of consumer price responses to producer price shocks appear to surpass those observed when producer prices respond to consumer price shocks. Furthermore, it is evident from the current research that the behavior of producers has evolved from earlier studies that utilized outdated information, suggesting a more competitive approach. The research identifies a new trend in producer behavior within the supply chain. By analyzing tomato price fluctuations, it advances current knowledge and provides essential market insights to support informed decision-making.
This work presents the development and application of an innovative green supramolecular deep eutectic solvent (SUPRADES)-based DLLME approach for the extraction and quantification of melamine in milk matrices. For this purpose, thymol and nonanoic acid were combined to create a hydrophobic DES, which was then utilized as the extraction solvent. Additionally, a ternary SUPRADES based on a hydrophilic DES composed of choline chloride and ethylene glycol and doped with β-cyclodextrin (β-CD) was prepared and applied as the disperser solvent. Critical parameters were optimized systematically, yielding the following optimal conditions: Extraction solvent volume: 150 μL; disperser solvent: 600 μL; β-CD: 1% (w/v); pH: 7; extraction time: 1 min; and sample solution volume: 5 mL. Interestingly, the salting-out step did not affect the extraction efficiency. The optimized approach showed good linearity (100–900 ng/mL) with R2 = 0.998 when validated with matrix-matched calibration standards. The LOD and LOQ were 27 and 81 ng/mL, respectively, and the enrichment factor was 41. Method accuracy and precision were evaluated through recovery studies using milk samples fortified with melamine at three concentration levels (200, 500, and 800 ng/mL), and the recovery values were obtained in the range of 92–107%, with RSD < 5%. A greenness score of 79 was attained by the method, as quantified by the advanced ComplexMoGAPI. Lastly, this technique was successfully applied to extract and determine melamine in real samples of powdered milk, infant formula, and raw milk with acceptable and satisfactory results.
Introduction: Heavy metal pollution including lead (Pb) has become one of the serious global issues threatening food security, human health, and the ecosystem. Exogenous application of astaxanthin (ATX), a potent natural antioxidant, has been shown to enhance plant tolerance to various abiotic stresses. However, the role of endogenous ATX in alleviating Pb stress and the underlying molecular mechanisms remain poorly understood. Objectives: This study aimed to systematically investigate the effects and mechanism of endogenous ATX in biofortified tobacco (T-ATX) in promoting plant growth, particularly enhancing plant tolerance to Pb toxicity and blocking Pb pollution. Methods: Pot experiments were employed to investigate plant growth and Pb tolerance as well as Pb absorption and translocation in T-ATX and wild-type (SNN) tobacco seedlings subjected to various doses of Pb stress. Multiple physiological and cellular examinations were conducted, followed by integrated omics approaches in this study. Results: T-ATX plants exhibited an increased plant height, root length, leaf area, and biomass compared to SNN under Pb stress. T-ATX displayed higher levels of chlorophyll, photosynthetic efficiency, antioxidant enzyme activities, and non-enzymatic antioxidants, with improved integrity of subcellular structures. Remarkably, Pb content in various organs and Pb translocation coefficient were significantly reduced in T-ATX. Multiple genes and metabolites associated with antioxidant defense mechanisms, detoxification pathways, carotenoid metabolism, Pb ion transport, and plant hormone signal transduction were significantly upregulated in T-ATX tobacco plants. Conclusion: Endogenous ATX enriched in the T-ATX genotype significantly confers plant healthy performance and high tolerance to Pb stress by enhancing the antioxidant defense system, maintaining cellular structural integrity, reducing Pb absorption and translocation, upregulating detoxification and the related signaling pathways. These findings provide new insights into the endogenous ATX-mediated molecular mechanisms to promote plant growth and mitigate Pb toxicity, establishing a foundation for using ATX-fortified crops for green control technology of heavy metal pollution.
Joseph T. Harrington, Vsevolod Cheburkanov, Mykyta Kizilov
et al.
The increasing demands on modern plant and food production due to climate change, regulatory pressures, and the Sustainable Development Goals necessitate advanced photonic technologies for improved sustainability. Deep ultraviolet resonant Raman (DUVRR) spectroscopy offers precise spectral fingerprinting and potential disinfection capabilities, making it a promising tool for agricultural and food sciences. We developed a cost-effective, portable DUVRR spectroscopy system using a mercury (Hg) lamp as the excitation source at 253.65 \unit{\nano\meter}. The system was tested on diverse samples, including alcohol solvents, organic extracts, and industrial chemicals. The DUVRR system successfully resolved sub-1000 \unit{\per\centi\meter} Raman peaks, enabling detailed spectral fingerprints of various constituents and biomarkers. The system's high sensitivity and specificity ensure precise identification of nutritional values and food quality. The DUV light used in the system, defined here as less than 260 \unit{\nano\meter}, demonstrated potential disinfection properties, adding significant value for food safety applications. The highly sensitive detection capability of our DUVRR system at low powers has significant implications for plant and agricultural sciences. The detailed spectral information enhances the evaluation of nutritional values, food quality, and ripening processes. This dually-functional system is highly valuable for precision farming, food production, and quality control. Our DUVRR spectroscopy system provides a highly sensitive, affordable, and portable method for the spectroscopic evaluation and disinfection of food and agricultural samples. Its ability to resolve detailed Raman peaks below 1000 \unit{\per\centi\meter}, combined with DUV light's disinfection capabilities, makes it a promising tool for advancing sustainability and safety in agriculture and food production.
This work presents AgroTrack, a LoRa-based IoT framework for remote livestock monitoring in smart agriculture. The system is designed for low-power, long-range communication and supports real-time tracking and basic health assessment of free-range livestock through GPS, motion, and temperature sensors integrated into wearable collars. Data is collected and transmitted via LoRa to gateways and forwarded to a cloud platform for visualization, alerts, and analytics. To enhance its practical deployment, AgroTrack incorporates advanced analytics, including machine learning models for predictive health alerts and behavioral anomaly detection. This integration transforms the framework from a basic monitoring tool into an intelligent decision-support system, enabling farmers to improve livestock management, operational efficiency, and sustainability in rural environments.
Phi-Hung Hoang, Nam-Thuan Trinh, Van-Manh Tran
et al.
Deploying deep learning models on resource-constrained edge devices remains a major challenge in smart agriculture due to the trade-off between computational efficiency and recognition accuracy. To address this challenge, this study proposes a hybrid knowledge distillation framework for developing a lightweight yet high-performance convolutional neural network. The proposed approach designs a customized student model that combines inverted residual blocks with dense connectivity and trains it under the guidance of a ResNet18 teacher network using a multi-objective strategy that integrates hard-label supervision, feature-level distillation, response-level distillation, and self-distillation. Experiments are conducted on a rice seed variety identification dataset containing nine varieties and further extended to four plant leaf disease datasets, including rice, potato, coffee, and corn, to evaluate generalization capability. On the rice seed variety classification task, the distilled student model achieves an accuracy of 98.56%, which is only 0.09% lower than the teacher model (98.65%), while requiring only 0.68 GFLOPs and approximately 1.07 million parameters. This corresponds to a reduction of about 2.7 times in computational cost and more than 10 times in model size compared with the ResNet18 teacher model. In addition, compared with representative pretrained models, the proposed student reduces the number of parameters by more than 6 times relative to DenseNet121 and by over 80 times compared with the Vision Transformer (ViT) architecture, while maintaining comparable or superior classification accuracy. Consistent performance gains across multiple plant leaf disease datasets further demonstrate the robustness, efficiency, and strong deployment potential of the proposed framework for hardware-limited smart agriculture systems.
Wildlife-induced crop damage, particularly from deer, threatens agricultural productivity. Traditional deterrence methods often fall short in scalability, responsiveness, and adaptability to diverse farmland environments. This paper presents an integrated unmanned aerial vehicle (UAV) system designed for autonomous wildlife deterrence, developed as part of the Farm Robotics Challenge. Our system combines a YOLO-based real-time computer vision module for deer detection, an energy-efficient coverage path planning algorithm for efficient field monitoring, and an autonomous charging station for continuous operation of the UAV. In collaboration with a local Minnesota farmer, the system is tailored to address practical constraints such as terrain, infrastructure limitations, and animal behavior. The solution is evaluated through a combination of simulation and field testing, demonstrating robust detection accuracy, efficient coverage, and extended operational time. The results highlight the feasibility and effectiveness of drone-based wildlife deterrence in precision agriculture, offering a scalable framework for future deployment and extension.
Contact-rich manipulation tasks in agriculture, such as pruning and harvesting, require robots to physically interact with tree structures to maneuver through cluttered foliage. Identifying whether the robot is contacting rigid or soft materials is critical for the downstream manipulation policy to be safe, yet vision alone is often insufficient due to occlusion and limited viewpoints in this unstructured environment. To address this, we propose a multi-modal classification framework that fuses vibrotactile (audio) and visual inputs to identify the contact class: leaf, twig, trunk, or ambient. Our key insight is that contact-induced vibrations carry material-specific signals, making audio effective for detecting contact events and distinguishing material types, while visual features add complementary semantic cues that support more fine-grained classification. We collect training data using a hand-held sensor probe and demonstrate zero-shot generalization to a robot-mounted probe embodiment, achieving an F1 score of 0.82. These results underscore the potential of audio-visual learning for manipulation in unstructured, contact-rich environments.
Reliable access to food is a basic requirement in any sustainable society. However, achieving food security for all is still a challenge, especially for poor populations in urban environments. The project Feed4Food aims to use a federation of Living Labs of urban agriculture in different countries as a way to increase urban food security for vulnerable populations. Since different Living Labs have different characteristics and ways of working, the vision is that the knowledge obtained in individual Living Labs can be leveraged at the federation level through federated learning. With this specific goal in mind, a dashboarding tool is being established. In this work, we present a reusable process for establishing a dashboard that supports local awareness and decision making, as well as federated learning. The focus is on the first steps of this creation, i.e., defining what data to collect (through the creation of Key Performance Indicators) and how to visualize it. We exemplify the proposed process with the Feed4Food project and report on our insights so far.
Dünyada yer kabuğundaki en bol bulunan yedinci element olan sodyum (Na), ayrıştırıcılar, hayvanlar ve bitkiler için önemli ve temel elementlerdendir. Aynı zamanda yaygın olarak bulunan metallerdendir. Bundan dolayı özellikle uzun ömürlü ve büyük biyokütleye sahip ağaçların en büyük organı olan odun kısmında Na birikiminin belirlenmesi önem taşımaktadır. Bu çalışmada özellikle peyzaj çalışmalarında yaygın olarak kullanılan dişbudak (Fraxinus excelsior) gövde organlarında Na’nın organ, yön ve dönem bazında değişimi değerlendirilmiştir. Çalışma sonucunda dış kabuktaki Na konsantrasyonlarının iç kabuk ve odundakinden daha yüksek seviyede olduğu belirlenmiştir. Dış kabuktaki en yüksek değerler ise kentleşme ve trafiğin yoğun olduğu kuzey yönde elde edilirken, özellikle odunlarda Na konsantrasyonlarının genel olarak dar bir aralıkta değişim gösterdiği tespit edilmiştir. Bu sonuçlar havadaki Na kirliliğinin muhtemelen kentsel alanlar ve trafik kaynaklı olduğu ve çalışmaya konu Fraxinus excelsior’un havadaki Na kirliliğinin değişiminin izlenmesi için uygun bir biyomonitor olmadığı şeklinde yorumlanabilir.