Search Results (197)

Intensive pesticide application sustains global agriculture but poses poorly characterized risks to complex soil ecosystems. Here, we quantitatively evaluated pesticide residues and utilized high-resolution environmental DNA (eDNA) metagenomics to decode multi-trophic community responses across a typical major grain-producing region located in China. Among 39 targeted pesticides, 26 were detected with total concentrations ranging from 27.9 to 478.8 ng/g. While herbicides and fungicides dominated the residual mass, insecticides posed the most severe ecological threat. Notably, the neonicotinoid imidacloprid exhibited high-risk levels (RQ = 1.78 ± 1.49) at >61.1% of the sampling sites. eDNA profiling and Procrustes analyses revealed a clear trophic-dependent sensitivity gradient (p < 0.01). Lower-trophic microbial communities were significantly altered in composition; pesticide stress was strongly associated with profound non-target suppression on keystone plant-beneficial bacteria (e.g., Nocardioides). Concurrently, the fungal eDNA profiles indicated that the soil mycobiome harbored an alarming 34.7% of potential phytopathogenic fungi (e.g., Aspergillus and Colletotrichum), intrinsically driving the massive fungicide reliance. In contrast, higher-trophic soil metazoa (Rotifera, 40.4%) and weed communities (e.g., Digitaria sanguinalis) exhibited significant spatial stability, reflecting robust environmental buffering and herbicide-driven ecological escapes. Furthermore, co-occurrence networks decoupled target from non-target toxicities, uniquely revealing that persistent herbicide metabolites (desethylatrazine) induce prolonged legacy toxicities on specific soil fauna. Collectively, this study unveils the deep, cross-kingdom ecological disruptions caused by current pesticide regimes, underscoring the urgency of integrating eDNA biomonitoring to guide precision pest management and safeguard soil health in vital agricultural hubs. Full article

To address the dual challenges of discriminating weeds from rice seedlings for precision weed management operations, such as targeted spraying and robotic weeding, in complex paddy-field scenes and deploying high-precision models on resource-limited edge devices, we propose DGS-Net, a deformable attention, GSConv-based feature fusion, and SEAM-enhanced lightweight network based on YOLOv11n. The backbone incorporates a convolutional block with parallel split attention and deformable attention transformer (C2PSA_DAT) module to improve the extraction of irregular and fine-grained weed features, the neck integrates a VoV-GSCSP module to enable lightweight multi-scale feature fusion for small and densely distributed targets, and a separated and enhancement attention module (SEAM) is placed before the detection head to enhance robustness under leaf occlusion and complex paddy-field background interference. In comparative experiments conducted on the paddy-field dataset under unified training and evaluation settings, DGS-Net achieved 91.7% precision, 86.8% recall, and 92.4% mean average precision (mAP), with a model size of 5.8 MB and a computational cost of 6.2 giga floating-point operations (GFLOPs). Compared with representative lightweight baseline detectors, DGS-Net showed a more favorable balance between detection accuracy and deployment efficiency. In additional edge-device deployment tests using the test set, the model sustained real-time inference at 32.5 FPS and achieved mAP@0.5, precision, and recall of approximately 0.928, 0.919, and 0.867, respectively. Overall, DGS-Net improves irregular feature extraction, enables lightweight multi-scale feature fusion, and increases robustness to occlusion while retaining strong deployability. The method therefore provides practical visual-perception support for precise, real-time crop–weed discrimination and precision weed management in complex paddy-field environments. Full article

Weed control remains a critical challenge in modern crop production, particularly under increasing pressure to reduce chemical inputs and improve environmental sustainability. Recent advances in precision agriculture and robotic systems have enabled site-specific weed management, where interventions are applied selectively based on detected weed locations. While extensive research has focused on improving weed detection algorithms, comparatively less attention has been paid to the characteristics and constraints of different weeding modalities, which ultimately determine field performance. This review presents a systematic analysis of robotic weeding modalities from an actuation-oriented perspective. Specifically, we establish a comprehensive taxonomy of weeding approaches, including mechanical, chemical, thermal, laser-based, electrical, and other emerging methods, and analyze their underlying mechanisms and operational characteristics. Furthermore, we examine the coupling between sensing and actuation, highlighting how different intervention modalities impose distinct requirements on perception outputs. A scenario-based comparison framework is then developed to evaluate the suitability of different modalities across representative agricultural conditions, including pre-emergence control, in-row selective weeding, dense-row crop systems, and large weed situations. Based on this analysis, the limitations of single-modality systems are discussed, and emerging trends toward multi-modality integration and air–ground collaborative weed management are reviewed. Overall, this review shifts the focus from detection-centric approaches to the integration of sensing and actuation in robotic weeding systems and provides a decision-oriented framework to support the design, selection, and deployment of next-generation robotic weed management technologies. Full article

Weeds represent a major constraint in the cultivation of medicinal and aromatic plants (MAPs), causing significant reductions in yield, biomass, and essential oil quality while increasing labor and production costs. Effective weed management is particularly critical during early crop growth, when young plants are most vulnerable to competition. Non-chemical strategies, including cultural practices, mechanical and thermal weeding, mulching, and crop diversification, have proven effective in suppressing weeds, enhancing crop competitiveness, and maintaining yield and quality, especially in organic or low-input systems. Mulching and optimized cultivation strategies consistently provide reliable weed control, improve soil moisture and nutrient use efficiency, and can influence secondary metabolite accumulation. Chemical weed control, including selective pre- and post-emergence herbicides, remains important in slow-growing MAPs but is increasingly constrained by regulatory restrictions and concerns over residues in raw plant material and essential oils. Integrated weed management combining cultural, physical, and reduced chemical approaches offers the most effective solution, balancing efficacy, crop safety, and product quality. Emerging strategies such as bioherbicides, precision agriculture, and robotic systems hold promise but require further research. Advancing weed management in MAPs will depend on interdisciplinary studies, field-scale validation, and technology-driven innovations to support sustainable, high-quality production. Full article

Robotics is increasingly positioned as an enabling technology for precision agriculture, where management actions must be spatially and temporally targeted under constraints on labour, input use, safety, and environmental impact. This review synthesises studies on agricultural field robotics and organises the literature along four complementary axes: task (monitoring, weeding, spraying, and harvesting), platform (UGV, UAV, gantry/fixed-structure, greenhouse robot, and hybrid systems), autonomy-stack module (perception, localisation, planning, control, actuation, safety, and human–robot interaction), and evaluation setting (lab, greenhouse, open-field single season, and open-field multi-season/multi-site). Across these dimensions, this review analyses how platform constraints shape sensing geometry, actuation capability, localisation reliability, energy/endurance, supervision burden, and safety requirements. It further examines enabling technologies that recur across tasks, including vision and multimodal perception under occlusion and illumination variability, localisation and mapping under weak or denied GNSS, uncertainty-aware planning in deformable and partially observed environments, and compliant end-effectors for contact-rich operations. Beyond cataloguing systems, this paper emphasises evaluation practice by synthesising core task-relevant metrics, comparing laboratory and field validation settings, and proposing a reporting checklist and benchmark ladder to improve reproducibility and cross-study comparability. This review identifies recurring bottlenecks in domain shift, long-term autonomy, calibration robustness, crop-safe actuation, and safety assurance near humans, and it concludes with a staged research roadmap linking near-term evaluation reform to longer-term credible multi-site autonomy. Overall, this paper provides a structured framework for interpreting agricultural robotic systems not only by application but also by deployment context, system maturity, and evaluation credibility. Full article

Agricultural robots and unmanned farmland management require real-time and precise parsing of crop leaves at the edge to support variable application of pesticides, seedling condition monitoring, and phenotypic analysis. However, the field environment features drastic changes in light, leaf occlusion, and interference from background weeds, which can cause semantic fragmentation and boundary artifacts in lightweight models. This paper presents ES2-LeafSeg, a lightweight framework for leaf semantic segmentation tailored for edge deployment. The method employs EfficientNetV2 as the backbone encoder and introduces the State Space Semantic Enhancement Module (S2FEM) on skip connection features, modeling long-range dependencies and suppressing local texture noise through SSM pooling in row and column directions. Meanwhile, a cross-scale decoder (CSD) and a global context transformation (GCT) are designed to achieve multi-scale semantic fusion and boundary refinement. On the three-class segmentation task of the SoyCotton dataset, ES2-LeafSeg achieved mIoU of 0.817, mDice of 0.869, Fβw of 0.925, and MAE of 0.011, outperforming multiple classic and recent baselines while maintaining 23.67 M parameters and 49.62 FPS. Ablation experiments further verified the complementary contributions of S2FEM and GCT to regional consistency and boundary quality. Full article

Precision agriculture is a key technology for addressing challenges such as increasing food demand, labour shortages, and the environmental impact of intensive agrochemical use. In this context, selective weed management remains a critical issue due to its direct effect on crop productivity and sustainability. This article presents a simulation-based framework for the design and evaluation of an agricultural robotic module for the detection, classification, and selective intervention of weeds. The proposed system integrates convolutional neural networks and the kinematic model of a 2DOF robot manipulator with 5 links for weed classification and treatment. The system is evaluated in a virtual environment, where camera calibration, perception accuracy, and the performance of the kinematic model are analysed. Quantitative results include detection accuracy, localization error, and intervention success rate under simulated field conditions. The results demonstrate selective weed management and the feasibility of simulation for developing weed control systems, while also identifying the main challenges for real-world deployment. Full article

Under maize–soybean rotation systems, weeds and crops at the seedling stage in dryland fields exhibit high similarity in morphological structure, scale distribution, and spatial arrangement. In addition, complex illumination conditions, occlusion, and background interference further complicate accurate weed discrimination. To address these challenges, this study proposes an improved YOLOv11n-based weed detection method for seedling-stage crops under dryland rotation conditions, aiming to enhance detection accuracy and robustness in UAV-acquired field images. Three key improvements were introduced to enhance model performance: (1) the incorporation of Dynamic Convolution (DynamicConv) to adaptively strengthen feature representation for weeds with varying morphologies and scales in low-altitude remote sensing imagery; (2) the design of a SlimNeck lightweight feature fusion architecture to improve multi-scale feature propagation efficiency while reducing computational cost; (3) the cascaded group attention mechanism (CGA) is integrated into the C2PSA module, thereby improving discrimination capability under complex background conditions. These results represent consistent improvements over baseline models, including YOLOv5, YOLOv6, YOLOv8, YOLOv11, and YOLOv12. Specifically, detection performance for broadleaf weeds and Poaceae weeds reached mAP@0.5 values of 87.2% and 73.9%, respectively. Overall, the proposed method demonstrates superior detection accuracy and stability for seedling-stage weed identification under rotation conditions, providing reliable technical support for variable-rate herbicide application and precision field management. Full article

Weed management, particularly in organic farming, poses a significant challenge due to high manual labor costs and the crop’s low competitive ability. Precision laser technology offers a promising non-chemical alternative. This study evaluates the field performance of a novel robotic system based on a Thulium fiber laser. The validation was conducted on commercial fields of the Westhof Bio GmbH in Friedrichsgabekoog, Germany. The Weeding Success rate of the laser weeding robot was 95% and the Detection Rate 85% for carrots for one weeding cycle. For beetroot, these values are 98% and 88%, respectively, after two weeding cycles. The field trials validate the Thulium fiber laser system as an agronomically effective and economically viable alternative for sustainable weed management. The technology demonstrates the potential to significantly reduce manual labor and reliance on herbicides in challenging crops. Full article

Reliable identification of weed species is essential for effective and sustainable weed management. In this study, we explored the use of hyperspectral imaging to distinguish nine weed species based on their spectral signatures. Although the species showed similarities in their spectral curves due to comparable growing conditions, clear differences emerged related to morphological traits and pigment composition. We analysed the spectral data using five classification algorithms: Random Forest, Support Vector Machine, Artificial Neural Network, Maximum Entropy, and SIMCA. Model performance was assessed using per-class and overall accuracy. Random Forest outperformed the other methods, achieving 93.5% accuracy despite limited and imbalanced training data. This work contributes to the development of a spectral library for weed species and demonstrates the value of machine learning for species identification across different crops and environmental conditions. Expanding such spectral databases can enhance the speed and accuracy of weed monitoring, reduce herbicide reliance, and reduce environmental impact. The proposed approach shows strong potential for integration into precision agriculture and agroecological monitoring systems, supporting more efficient and environmentally responsible farmland management. Full article

Accurate assessment of cotton emergence rates is essential for precision agriculture management, and unmanned aerial vehicle (UAV) imagery provides a scalable means for field-level monitoring. However, cotton seedling detection from UAV images faces persistent challenges: individual seedlings appear as small targets with diverse morphologies across varying flight altitudes; strong plastic film reflections, weeds, and soil cracks introduce substantial background interference; and “missing seedling” targets, which manifest as negative space features, exhibit high similarity to background noise. Existing CNN–Transformer hybrid detection architectures are limited by fixed convolutional receptive fields that cannot adapt to multi-scale target variations, attention mechanisms that lack explicit directional geometric modeling, and interpolation-based upsampling that attenuates high-frequency edge details of small targets. To address these issues, this paper proposes DDF-DETR (Dynamic-Direction-Frequency Detection Transformer), a multi-scale spatial context detection method based on RT-DETR. The method incorporates three components: a Dynamic Gated Mixer Block (DGMB) for adaptive multi-scale feature extraction with background noise suppression, a Direction-Aware Adaptive Transformer Encoder (DAATE) for directional geometric feature modeling at linear computational complexity, and a Frequency-Aware Sub-pixel Upsampling Network (FASN) for high-frequency detail recovery in the feature pyramid. On the self-constructed Xinjiang cotton field dataset, DDF-DETR achieves 83.72% mAP@0.5 and 63.46% mAP@0.5:0.95, representing improvements of 2.38% and 5.28% over the baseline RT-DETR-R18, while reducing the parameter count by 30.6% and computational cost to 42.8 GFLOPs. Generalization experiments on the VisDrone2019 and TinyPerson datasets further validate the robustness of the proposed method for small target detection across different scenarios. Full article

The automated management of invasive weeds is critical for sustainable agriculture, yet the performance of deep learning models in real-world fields is often compromised by two factors: challenging environmental conditions and the high cost of data annotation. This study tackles both issues through a diagnostic-driven, semi-supervised framework. Using a unique dataset of approximately 975 labelled and 10,000 unlabelled images of Guinea Grass in sugarcane, we first establish strong supervised baselines for classification (ResNet) and detection (YOLO, RF-DETR), achieving F1 scores up to 0.90 and mAP50 scores exceeding 0.82. Crucially, this foundational analysis, aided by interpretability tools, uncovered a pervasive “shadow bias,” where models learned to misidentify shadows as vegetation. This diagnostic insight motivated our primary contribution: a semi-supervised pipeline that leverages unlabelled data to enhance model robustness. By training models on a more diverse set of visual information through pseudo-labelling, this framework not only helps mitigate the shadow bias but also provides a tangible boost in recall, a critical metric for minimising weed escapes in automated spraying systems. To validate our methodology, we demonstrate its effectiveness in a low-data regime on a public crop–weed benchmark. Our work provides a clear and field-tested framework for developing, diagnosing, and improving robust computer vision systems for the complex realities of precision agriculture. Full article

The advent of smart farms, enabled by information and communication technologies (ICT) and the Internet of Things (IoT), has improved productivity and sustainable agriculture. However, the large-scale implementation of smart farms is currently hampered by physical constraints. These constraints have led to the concept of open-field smart farming as a viable alternative. In this paradigm, data from unmanned aerial vehicles (UAVs) play a central role in effective and sustainable agricultural management. The quantitative analysis of such data requires highly reliable technological solutions. The objective of this study is to conduct a comparative analysis of image binarization algorithms for UAV-based soybean canopy extraction across growth stages and to contribute to the development of an image labeling methodology. UAVs were used to capture images of soybean fields at different growth stages, and a comparative analysis was performed using binarization image algorithms. The performance of each algorithm was evaluated using Normalized Cross Correlation (NCC) and Mean Absolute Error (MAE). The results indicate that the Excess Green (ExG) and Excess Green minus Excess Red (ExGR) vegetation indices provide accurate and stable soybean canopy extraction across growth stages when combined with Adaptive and Otsu binarization algorithms. These indices are particularly suitable for extracting soybean canopy from UAV-based data, thereby expanding the scope of precision analysis in the agricultural sector and providing data for advancing precision agriculture technology. This study contributes to the standardization and efficient use of UAV-based agricultural data processing. However, since manual weeding was performed prior to image acquisition to ensure that only soybean plants were present, reflecting standard agricultural practices in South Korea, additional validation would be required for application in fields where weeds are naturally present. Full article

The potential withdrawal of glyphosate necessitates a comprehensive evaluation of alternative weed control strategies that balances human health safety with environmental concerns. This study applied a decision-support grid to compare the impacts of glyphosate-based reference strategies against chemical and non-chemical alternatives across four Belgian case studies: pome fruit orchards, grassland renewal, arable weed patches, and railways. The assessment integrated twelve risk indicators including human, environmental and biodiversity risk, and life cycle assessment for global warming potential (GWP) into a Final Scenario Score (FSS). The results indicated that only one alternative strategy, the chemical alternative in local weed patch control, achieved the FSS threshold (<0.75) required to justify substitution (FSS = 0.70). Chemical alternatives in other case studies frequently shifted burdens; for instance, bio-herbicides in railways increased risks to residents and aquatic organisms compared to the reference. Conversely, mechanical and thermal alternatives eliminated chemical toxicity but resulted in GWP increases up to 32 times higher than glyphosate-based practices. These findings demonstrate that chemical substitutes often maintain toxicity risks while non-chemical strategies trade them for increased climate impacts. Consequently, a ban on glyphosate is currently unsupported by the environmental performance of available alternatives in these temperate high-intensity systems. Sustainable progress requires a transition period where optimized conventional strategies remain available within integrated weed management, while innovations in electrification and precision technology are accelerated to resolve current trade-offs. Full article

In recent years, agriculture has begun to transform thanks to the arrival of robots and autonomous vehicles capable of performing complex operations such as weeding and spraying in an intelligent and targeted manner. In fact, new-generation agricultural robots use artificial intelligence (AI), cameras, and sensors to recognise weeds, analyse crop conditions, and apply plant protection products only where necessary, thus reducing waste and environmental impact. Some systems combine drones and ground vehicles to achieve even more accurate results. This systematic review synthesises recent advances in agricultural robotics for weed and pest management through a PRISMA-based approach. Literature was collected from major scientific databases (Scopus, Web of Science, IEEE Xplore, Google Scholar) and complementary sources, leading to the inclusion of 83 eligible studies. The selected evidence was structured into four application domains: (i) weed detection and mapping, (ii) robotic and non-chemical weed control (mechanical and laser-based approaches), (iii) selective/variable-rate spraying for pest and disease management, and (iv) integrated weeding–spraying solutions, including cooperative Unmanned Aerial Vehicle–Unmanned Ground Vehicle (UAV–UGV) systems. Overall, the reviewed studies confirm rapid progress in real-time perception (deep learning-based detection), navigation/localization (e.g., GNSS/RTK, LiDAR, sensor fusion) and targeted actuation (spot spraying and precision interventions), while also revealing persistent limitations: heterogeneous evaluation protocols, limited system-level comparisons in terms of work rate, scalability, costs and robustness under variable field conditions, and an often unclear distinction between prototype platforms and solutions close to commercialization. However, the large-scale spread of these technologies is still hampered by high costs, technical complexity, and cultural resistance. The review highlights how the integration of automation, sustainability, and accessibility is key to the agriculture of the future. Full article