Search Results (467)

The accuracy of classification and localization of plants on images obtained from the board of an unmanned aerial vehicle (UAV) is of great importance when implementing precision farming technologies. It allows for the effective application of variable rate technologies, which not only saves chemicals but also reduces the environmental load on cultivated fields. Machine learning algorithms are widely used for plant classification. Research on the application of the YOLO algorithm is conducted for simultaneous identification, localization, and classification of plants. However, the quality of the algorithm significantly depends on the training set. The aim of this study is not only the detection of a cultivated plant (soybean) but also weeds growing in the field. The dataset developed in the course of the research allows for solving this issue by detecting not only soybean but also seven weed species common in the fields of Kazakhstan. The article describes an approach to the preparation of a training set of images for soybean fields using preliminary thresholding and bound box (Bbox) segmentation of marked images, which allows for improving the quality of plant classification and localization. The conducted research and computational experiments determined that Bbox segmentation shows the best results. The quality of classification and localization with the application of Bbox segmentation significantly increased (f1 score increased from 0.64 to 0.959, mAP50 from 0.72 to 0.979); for a cultivated plant (soybean), the best classification results known to date were achieved with the application of YOLOv8x on images obtained from the UAV, with an f1 score = 0.984. At the same time, the plant detection rate increased by 13 times compared to the model proposed earlier in the literature. Full article

This work proposes a new method to refill fuel cell electric vehicle hydrogen tanks from a storage system in hydrogen refueling stations. The new method uses the storage tanks in cascade to supply hydrogen to the refueling station dispensers. This method reduces the hydrogen compressor power requirement and the energy consumption for refilling the vehicle tank; therefore, the proposed alternative design for hydrogen refueling stations is feasible and compatible with low-intensity renewable energy sources like solar photovoltaic, wind farms, or micro-hydro plants. Additionally, the cascade method supplies higher pressure to the dispenser throughout the day, thus reducing the refueling time for specific vehicle driving ranges. The simulation shows that the energy saving using the cascade method achieves 9% to 45%, depending on the vehicle attendance. The hydrogen refueling station design supports a daily vehicle attendance of 9 to 36 with a complete refueling process coverage. The carried-out simulation proves that the vehicle tank achieves the maximum attainable pressure of 700 bars with a storage system of six tanks. The data analysis shows that the daily hourly hydrogen demand follows a sinusoidal function, providing a practical tool to predict the hydrogen demand for any vehicle attendance, allowing the planners and station designers to resize the elements to fulfill the new requirements. The proposed system is also applicable to hydrogen ICE vehicles. Full article

This study describes the first complete genomic sequence of an NDM-19 and QnrS11-producing multidrug-resistant (MDR) Escherichia coli isolate collected from a fecal swab from a poultry farm in 2019 in Egypt. The bla_NDM-19 was identified by PCR screening and DNA sequencing. The isolate was then subjected to antimicrobial susceptibility testing, conjugation and transformation experiments, and complete genome sequencing. The chromosome of strain M2-13-1 measures 4,738,278 bp and encodes 4557 predicted genes, with an average G + C content of 50.8%. M2-13-1 is classified under ST167, serotype O101:H5, phylogroup A, and shows an MDR phenotype, having minimum inhibitory concentrations (MICs) of 64 mg/L for both meropenem and doripenem. The genes bla_NDM-19 and qnrS11 are present on 49,816 bp IncX3 and 113,285 bp IncFII: IncFIB plasmids, respectively. M2-13-1 harbors genes that impart resistance to sulfonamides (sul1), trimethoprim (dfrA14), β-lactams (bla_TEM-1B), aminoglycosides (aph(6)-Id, aph(3′)-Ia, aph(3″)-Ib, aac(3)-IV, and aph(4)-Ia), tetracycline (tet(A)), and chloramphenicol (floR). It was susceptible to aztreonam, colistin, fosfomycin, and tigecycline. The genetic context surrounding bla_NDM-19 includes ISAba125-IS5-bla_NDM-19-ble_MBL-trpF-hp1-hp2-IS26. Hierarchical clustering of the core genome MLST (HierCC) indicated M2-13-1 clusters with global ST167 E. coli lineages, showing HC levels of 100 (HC100) core genome allelic differences. Plasmids of the IncX3 group and the insertion sequence (ISAba125) are critical vehicles for the dissemination of bla_NDM and its related variants. To our knowledge, this is the first genomic report of a bla_NDM-19/IncX3-carrying E. coli isolate of animal origin globally. Full article

Smart farming has emerged as a promising solution to address challenges such as climate change, population growth, and limited agricultural infrastructure. To enhance the operational efficiency of smart farms, this paper proposes an integrated system that combines Recurrent Neural Networks (RNNs) and Unmanned Aerial Vehicles (UAVs). The proposed framework forecasts future resource shortages using an RNN model and recent environmental data collected from the field. Based on these forecasts, the system schedules a resource supply plan and determines the UAV path by considering both dynamic energy consumption and priority levels, aiming to maximize the efficiency of the resource supply. Experimental results show that the proposed integrated smart farm framework achieves an average reduction of 81.08% in the supply miss rate. This paper demonstrates the potential of an integrated AI- and UAV-based smart farm management system in achieving both environmental responsiveness and operational optimization. Full article

Remote sensing tools have been proposed to assist with rice crop monitoring but have been developed and validated on ponded rice. This two-year study was conducted on a commercial rice farm with irrigation automation technology aimed to (i) understand how canopy reflectance differs between high-yielding ponded and aerobic rice, (ii) validate the feasibility of using the squared simplified canopy chlorophyll content index (SCCCI²) for N uptake estimates, and (iii) explore the SCCCI² and similar chlorophyll-sensitive indices for grain quality monitoring. Multispectral images were collected from an unmanned aerial vehicle during both rice-growing seasons. Above-ground biomass and nitrogen (N) uptake were measured at panicle initiation (PI). The performance of single-vegetation-index models in estimating rice N uptake, as previously published, was assessed. Yield and grain quality were determined at harvest. Results showed that canopy reflectance in the visible and near-infrared regions differed between aerobic and ponded rice early in the growing season. Chlorophyll-sensitive indices showed lower values in aerobic rice than in the ponded rice at PI, despite having similar yields at harvest. The SCCCI² model (RMSE = 20.52, Bias = −6.21 Kg N ha⁻¹, and MAPE = 11.95%) outperformed other models assessed. The SCCCI², squared normalized difference red edge index, and chlorophyll green index correlated at PI with the percentage of cracked grain, immature grain, and quality score, suggesting that grain milling quality parameters could be associated with N uptake at PI. This study highlights canopy reflectance differences between high-yielding aerobic (averaging 15 Mg ha⁻¹) and ponded rice at key phenological stages and confirms the validity of a single-vegetation-index model based on the SCCCI² for N uptake estimates in ponded and non-ponded rice crops. Full article

Winter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield estimation method based on a convolutional neural network (CNN). A comprehensive two-factor (fertilization × irrigation) controlled field experiment was designed to thoroughly validate the applicability and effectiveness of this method. The experimental design comprised two irrigation treatments, sufficient irrigation (C) at 750 m³ ha⁻¹ and deficit irrigation (M) at 450 m³ ha⁻¹, along with five fertilization treatments (at a rate of 180 kg N ha⁻¹): (1) organic fertilizer alone, (2) organic–inorganic fertilizer blend at a 7:3 ratio, (3) organic–inorganic fertilizer blend at a 3:7 ratio, (4) inorganic fertilizer alone, and (5) no fertilizer control. The experimental protocol employed a DJI M300 RTK unmanned aerial vehicle (UAV) equipped with a multispectral sensor to systematically acquire high-resolution growth imagery of winter wheat across critical phenological stages, from heading to maturity. The acquired multispectral imagery was meticulously annotated using the Labelme professional annotation tool to construct a comprehensive experimental dataset comprising over 2000 labeled images. These annotated data were subsequently employed to train an enhanced CNN model based on ResNet50 architecture, which achieved automated generation of panicle density maps and precise panicle counting, thereby realizing yield prediction. Field experimental results demonstrated significant yield variations among fertilization treatments under sufficient irrigation, with the 3:7 organic–inorganic blend achieving the highest actual yield (9363.38 ± 468.17 kg ha⁻¹) significantly outperforming other treatments (p < 0.05), confirming the synergistic effects of optimized nitrogen and water management. The enhanced CNN model exhibited superior performance, with an average accuracy of 89.0–92.1%, representing a 3.0% improvement over YOLOv8. Notably, model accuracy showed significant correlation with yield levels (p < 0.05), suggesting more distinct panicle morphological features in high-yield plots that facilitated model identification. The CNN’s yield predictions demonstrated strong agreement with the measured values, maintaining mean relative errors below 10%. Particularly outstanding performance was observed for the organic fertilizer with full irrigation (5.5% error) and the 7:3 organic-inorganic blend with sufficient irrigation (8.0% error), indicating that the CNN network is more suitable for these management regimes. These findings provide a robust technical foundation for precision farming applications in winter wheat production. Future research will focus on integrating this technology into smart agricultural management systems to enable real-time, data-driven decision making at the farm scale. Full article

Due to the limitations of the sowing machine performance and rice seed germination rates, missing seedlings inevitably occur after rice is sown in large fields. This phenomenon has a direct impact on the rice yield. In the field environment, the existing methods for detecting missing seedlings based on unmanned aerial vehicle (UAV) remote sensing images often have unsatisfactory effects. Therefore, to enable the fast and accurate detection of missing rice seedlings and facilitate subsequent reseeding, this study proposes a UAV remote-sensing-based method for detecting missing rice seedlings in large fields. The proposed method uses an improved PCERT-DETR model to detect rice seedlings and missing seedlings in UAV remote sensing images of large fields. The experimental results show that PCERT-DETR achieves an optimal performance on the self-constructed dataset, with an mean average precision (mAP) of 81.2%, precision (P) of 82.8%, recall (R) of 78.3%, and F₁-score (F₁) of 80.5%. The model’s parameter count is only 21.4 M and its FLOPs reach 66.6 G, meeting real-time detection requirements. Compared to the baseline network models, PCERT-DETR improves the P, R, F₁, and mAP by 15.0, 1.2, 8.5, and 6.8 percentage points, respectively. Furthermore, the performance evaluation experiments were carried out through ablation experiments, comparative detection model experiments and heat map visualization analysis, indicating that the model has a strong detection performance on the test set. The results confirm that the proposed model can accurately detect the number of missing rice seedlings. This study provides accurate information on the number of missing seedlings for subsequent reseeding operations, thus contributing to the improvement of precision farming practices. Full article

In the context of the “double carbon” goals and energy transformation, the integration of energy and transportation has emerged as a crucial trend in their coordinated development. Wind power prediction serves as the cornerstone technology for ensuring efficient operations within this integrated framework. This paper introduces a wind power prediction methodology based on an NGBoost–GRU fusion model and devises an innovative dynamic charging optimization strategy for electric vehicles (EVs) through deep collaboration. By integrating the dynamic feature extraction capabilities of GRU for time series data with the strengths of NGBoost in modeling nonlinear relationships and quantifying uncertainties, the proposed approach achieves enhanced performance. Specifically, the dual GRU fusion strategy effectively mitigates error accumulation and leverages spatial clustering to boost data homogeneity. These advancements collectively lead to a significant improvement in the prediction accuracy and reliability of wind power generation. Experiments on the dataset of a wind farm in Gansu Province demonstrate that the model achieves excellent performance, with an RMSE of 36.09 kW and an MAE of 29.96 kW at the 12 h prediction horizon. Based on this predictive capability, a “wind-power-charging collaborative optimization framework” is developed. This framework not only significantly enhances the local consumption rate of wind power but also effectively cuts users’ charging costs by approximately 18.7%, achieving a peak-shaving effect on grid load. As a result, it substantially improves the economic efficiency and stability of system operation. Overall, this study offers novel insights and robust support for optimizing the operation of integrated energy systems. Full article

In recent years, global agriculture has encountered several challenges exacerbated by the effects of changes in climate, such as extreme water shortages for irrigation and heat waves. Water-deficit stress adversely affects the morpho-physiology of numerous crops, including soybean (Glycine max L.), which is considered as promising crop in Bangladesh. Seaweed extract (SWE) has the potential to improve crop yield and alleviate the adverse effects of water-deficit stress. Remote and proximal sensing are also extensively utilized in estimating morpho-physiological traits owing to their cost-efficiency and non-destructive characteristics. The study was carried out to evaluate soybean morpho-physiological traits under the application of water extracts of Gracilaria tenuistipitata var. liui (red seaweed) with two varying irrigation water conditions (100% of total crop water requirement (TCWR) and 70% of TCWR). Principal component analysis (PCA) revealed that among the four treatments, the 70% irrigation + 5% (v/v) SWE and the 100% irrigation treatments overlapped, indicating that the application of SWE effectively mitigated water-deficit stress in soybeans. This result demonstrates that the foliar application of 5% SWE enabled soybeans to achieve morpho-physiological performance comparable to that of fully irrigated plants while reducing irrigation water use by 30%. Based on Pearson’s correlation matrix, a simple linear regression model was used to ascertain the relationship between unmanned aerial vehicle (UAV)-derived vegetation indices and the field-measured physiological characteristics of soybean. The Normalized Difference Red Edge (NDRE) strongly correlated with stomatal conductance (R² = 0.76), photosystem II efficiency (R² = 0.78), maximum fluorescence (R² = 0.64), and apparent transpiration rate (R² = 0.69). The Soil Adjusted Vegetation Index (SAVI) had the highest correlation with leaf relative water content (R² = 0.87), the Blue Normalized Difference Vegetation Index (bNDVI) with steady-state fluorescence (R² = 0.56) and vapor pressure deficit (R² = 0.74), and the Green Normalized Difference Vegetation Index (gNDVI) with chlorophyll content (R² = 0.73). Our results demonstrate how UAV and physiological data can be integrated to improve precision soybean farming and support sustainable soybean production under water-deficit stress. Full article

The integration of renewable energy with circular economy strategies offers effective pathways to reduce greenhouse gas emissions while enhancing local energy independence. This study analyses three real-world projects implemented in Spain that exemplify this synergy. LIFE Smart Agromobility converts pig manure into biomethane to power farm vehicles, using anaerobic digestion and microalgae-based upgrading systems. Smart Met Value refines biogas from a wastewater treatment plant in Guadalajara to produce high-purity biomethane for the municipal fleet, demonstrating the viability of energy recovery from sewage sludge. The UNDERGY project addresses green hydrogen storage by repurposing a depleted natural gas reservoir, showing geochemical and geomechanical feasibility for seasonal underground hydrogen storage. Each project utilises regionally available resources to produce clean fuels—biomethane or hydrogen—while mitigating methane and CO₂ emissions. Results show significant energy recovery potential: biomethane production can replace a substantial portion of fossil fuel use in rural and urban settings, while hydrogen storage provides a scalable solution for surplus renewable energy. These applied cases demonstrate not only the technical feasibility but also the socio-economic benefits of integrating waste valorisation and energy transition technologies. Together, they represent replicable models for sustainable development and energy resilience across Europe and beyond. Full article

The continuous and reliable operation of autonomous systems is important for farm management decision making, whether such systems perform crop monitoring using imaging systems or crop handling in pruning and harvesting applications using robotic manipulators. Autonomous systems, including robotic ground vehicles, drones, and tractors, are major research efforts of precision crop management. However, these systems may be less effective or require specific customizations for planting systems in low tunnels, high tunnels, or other environmentally controlled enclosures. In this work, a compact and lightweight crop management platform is developed that uses overhead power cables for continuous operation over row crops, requiring less human intervention and independent of the ground terrain conditions. The platform does not carry batteries onboard for its operation, but rather pulls power from overhead cables, which it also uses to navigate over crop rows. It is developed to be modular, with the top section consisting of mobility and power delivery and the bottom section addressing a custom task, such as incorporating additional sensors for crop monitoring or manipulators for crop handling. This prototype illustrates the infrastructure, locomotive mechanism, and sample usage of the system (crop imaging) in the application of low-tunnel-covered strawberries; however, there is potential for other row crop systems with regularly spaced support structures to adopt this platform as well. Full article

Recent advances in unmanned aerial vehicle (UAV) technology combined with deep learning techniques have greatly improved agricultural monitoring. However, accurately processing images at low resolutions remains challenging for precision cultivation of succulents. To address this issue, this study proposes a novel method that combines cutting-edge super-resolution reconstruction (SRR) techniques with object detection and then applies the above model in a unified drone framework to achieve large-scale, reliable monitoring of succulent plants. Specifically, we introduce MambaIR, an innovative SRR method leveraging selective state-space models, significantly improving the quality of UAV-captured low-resolution imagery (achieving a PSNR of 23.83 dB and an SSIM of 79.60%) and surpassing current state-of-the-art approaches. Additionally, we develop Succulent-YOLO, a customized target detection model optimized for succulent image classification, achieving a mean average precision (mAP@50) of 87.8% on high-resolution images. The integrated use of MambaIR and Succulent-YOLO achieves an mAP@50 of 85.1% when tested on enhanced super-resolution images, closely approaching the performance on original high-resolution images. Through extensive experimentation supported by Grad-CAM visualization, our method effectively captures critical features of succulents, identifying the best trade-off between resolution enhancement and computational demands. By overcoming the limitations associated with low-resolution UAV imagery in agricultural monitoring, this solution provides an effective, scalable approach for evaluating succulent plant growth. Addressing image-quality issues further facilitates informed decision-making, reducing technical challenges. Ultimately, this study provides a robust foundation for expanding the practical use of UAVs and artificial intelligence in precision agriculture, promoting sustainable farming practices through advanced remote sensing technologies. Full article

Accurate and timely monitoring of plant nitrogen content (PNC) is essential for precision agriculture (PA) and food security. While multispectral unmanned aerial vehicle (UAV) imagery has shown promise in PNC estimation, the optimal feature combination methods of spectral and texture features remain underexplored, and model transferability across different agricultural practices is poorly understood. This study aims to present an innovative approach by integrating 40 texture features and 22 spectral features from UAV multispectral images with machine learning (ML) methods (RF, SVR, and XGBoost) for winter wheat nitrogen content prediction. In addition, through analysis of an 8-year long-term field experiment with rigorous data, the results indicated that (1) the RF and XGboost models incorporating both spectral and texture features achieved good prediction accuracy, with R² values of 0.98 and 0.99, respectively, RMSE values of 0.10 and 0.07, and MAE values of 0.07and 0.05; (2) models trained on Farmers’ Practice (FP) data showed superior transferability to Ecological Intensification (EI) conditions (R² = 0.98, RMSE = 0.08, and MAE = 0.05 for XGBoost), while EI-trained models performed less well when applied to FP conditions (R² = 0.89, RMSE = 0.45, and MAE = 0.35 for XGBoost). These findings established an effective framework for UAV-based PNC monitoring, demonstrating that fused spectral–textural features with FP-trained XGboost can achieve both high accuracy and practical transferability, offering valuable decision-support tools for precision nitrogen management in different farming systems. Full article

This study presents a new intelligent aquatic farming surveillance system that tackles real-time monitoring challenges in the industry. The main technical break-throughs of this system are evident in four key aspects: First, it achieves the smooth integration of remotely operated vehicles (ROVs), sensors, and real-time data transmission. Second, it uses a mobile communication architecture with buoy relay stations for distributed edge computing. This design supports future upgrades to Beyond 5G and satellite networks for deep-sea applications. Third, it features a multi-terminal control system that supports computers, smartphones, smartwatches, and centralized hubs, effectively enabling monitoring anytime, anywhere. Fourth, it incorporates a cost-effective modular design, utilizing commercial hardware and innovative system integration solutions, making it particularly suitable for farms with limited resources. The data indicates that the system’s 4G connection is both stable and reliable, demonstrating excellent performance in terms of data transmission success rates, control command response delays, and endurance. It has successfully processed 324,800 data transmission events, thoroughly validating its reliability in real-world production environments. This system integrates advanced technologies such as the Internet of Things, mobile communications, and multi-access control, which not only significantly enhance the precision oversight capabilities of marine farming but also feature a modular design that allows for future expansion into satellite communications. Notably, the system reduces operating costs while simultaneously improving aquaculture efficiency, offering a practical and intelligent solution for small farmers in resource-limited areas. Full article

Background: Soybean is an important global crop in food security and agricultural economics. Accurate estimation of soybean pod counts is critical for yield prediction, breeding programs, precision farming, etc. Traditional methods, such as manual counting, are slow, labor-intensive, and prone to errors. With rapid advancements in artificial intelligence (AI), deep learning has enabled automatic pod number estimation in collaboration with unmanned aerial vehicles (UAVs). However, existing AI models are computationally demanding and require significant processing resources (e.g., memory). These resources are often not available in rural regions and small farms. Methods: To address these challenges, this study presents a set of lightweight, efficient AI models designed to overcome these limitations. By integrating model simplification, weight quantization, and squeeze-and-excitation (SE) self-attention blocks, we develop compact AI models capable of fast and accurate soybean pod count estimation. Results and Conclusions: Experimental results show a comparable estimation accuracy of 84–87%, while the AI model size is significantly reduced by a factor of 9–65, thus making them suitable for deployment in edge devices, such as Raspberry Pi. Compared to existing models such as YOLO POD and SoybeanNet, which rely on over 20 million parameters to achieve approximately 84% accuracy, our proposed lightweight models deliver a comparable or even higher accuracy (84.0–86.76%) while using fewer than 2 million parameters. In future work, we plan to expand the dataset by incorporating diverse soybean images to enhance model generalizability. Additionally, we aim to explore more advanced attention mechanisms—such as CBAM or ECA—to further improve feature extraction and model performance. Finally, we aim to implement the complete system in edge devices and conduct real-world testing in soybean fields. Full article