Search Results (282)

Soybean (Glycine max (L.) Merr.) is an essential legume crop in Thailand, valued for its high protein content and economic significance. However, weed competition can reduce yields by up to 82% if not managed effectively. This study evaluates the efficacy of post-emergence herbicides for weed control and their impact on soybean yield. A field experiment was conducted during the 2023 rainy and 2024/2025 dry seasons at Khon Kaen University using a split-plot design with four replications. Weed management treatments included hand weeding, an untreated control, and three herbicides, fluazifop-P-butyl + fomesafen, clethodim + fomesafen, and quizalofop-P-tefuryl + fomesafen, applied to two soybean varieties (Morkhor60 and CM60). Quizalofop-P-tefuryl + fomesafen was found to be the most effective herbicide, achieving 87.66% weed control efficiency (WCE) in the dry season and 72.43% in the rainy season. Hand weeding produced the highest yield (1324.00 kg ha⁻¹), followed by quizalofop-P-tefuryl + fomesafen (1148.90 kg ha⁻¹). Morkhor60 outperformed CM60 in yield and growth performance. These findings highlight the importance of selecting suitable herbicide treatments to optimize weed control and enhance soybean productivity under different seasonal conditions. Full article

In resource-constrained edge agricultural environments, the accurate recognition of toxic weeds poses dual challenges related to model lightweight design and the few-shot generalization capability. To address these challenges, a multi-strategy recognition framework is proposed, which integrates a lightweight backbone network, a pseudo-labeling guidance mechanism, and a contrastive boundary enhancement module. This approach is designed to improve deployment efficiency on low-power devices while ensuring high accuracy in identifying rare toxic weed categories. The proposed model achieves a real-time inference speed of 18.9 FPS on the Jetson Nano platform, with a compact model size of 18.6 MB and power consumption maintained below 5.1 W, demonstrating its efficiency for edge deployment. In standard classification tasks, the model attains 89.64%, 87.91%, 88.76%, and 88.43% in terms of precision, recall, F1-score, and accuracy, respectively, outperforming existing mainstream lightweight models such as ResNet18, MobileNetV2, and MobileViT across all evaluation metrics. In few-shot classification tasks targeting rare toxic weed species, the complete model achieves an accuracy of 80.32%, marking an average improvement of over 13 percentage points compared to ablation variants that exclude pseudo-labeling and self-supervised modules or adopt a CNN-only architecture. The experimental results indicate that the proposed model not only delivers strong overall classification performance but also exhibits superior adaptability for deployment and robustness in low-data regimes, offering an effective solution for the precise identification and ecological control of toxic weeds within intelligent agricultural perception systems. Full article

The increasing implementation of drift-reduction regulations in agriculture has driven the widespread adoption of drift-reducing spray nozzles. However, concerns remain about their impact on the biological efficacy of foliar-applied herbicides, particularly at early weed growth stages. This study evaluated the bio-efficiency of various drift-reducing flat-fan nozzles across three weed species (Chenopodium album, Solanum nigrum, and Echinochloa crus-galli), two growth stages, and six herbicides differing in mode of action and formulation properties. Dose–response bioassays were conducted using eight nozzle–pressure combinations under controlled greenhouse conditions. Spray characteristics, including droplet size distribution, coverage, contact angle, and surface tension, were quantified to elucidate interactions affecting herbicide efficacy. The results showed that nozzle effects were more pronounced for high-surface-tension formulations and poorly wettable weed targets. Several coarser droplet drift-reducing nozzles (e.g., ID3, APTJ) showed inferior performance in controlling small C. album and S. nigrum targets with bentazon and erectophile E. crus-galli targets with cycloxydim. At the same time, nozzle choice was less critical for tembotrione and nicosulfuron spray solutions, which have low surface tension. Across weed species, growth stages, and herbicides, nozzles producing finer, slower droplets demonstrated superior and more consistent performance compared to those producing larger, faster droplets. These findings offer science-based guidance for selecting nozzle types that balance drift mitigation with effective weed control under current and future regulatory constraints. Full article

In automated orchard operations, the straight-line locomotion stability of ground-based weeding robots is critical for ensuring path coverage efficiency and operational reliability. To address the response lag and high-frequency oscillations often observed in conventional PID and fixed-lookahead Pure Pursuit controllers, this study proposes an adaptive lookahead Pure Pursuit method incorporating angular velocity feedback. By dynamically adjusting the lookahead distance according to real-time attitude changes, the method enhances coordination between path curvature and robot stability. To enable systematic evaluation, three time-series-based metrics are introduced: mean absolute yaw error (MAYE), peak-to-peak fluctuation amplitude, and the standard deviation of angular velocity, with overshoot occurrences included as an additional indicator. Field experiments demonstrate that the proposed method outperforms baseline algorithms, achieving lower yaw errors (0.61–0.66°), reduced maximum deviation (≤3.7°), and smaller steady-state variance (<0.44°²), thereby suppressing high-frequency jitter and improving turning convergence. Under typical working conditions, the method achieved a mean yaw deviation of 0.6602°, a fluctuation of 5.59°, an angular velocity standard deviation of 10.79°/s, and 155 overshoot instances. The yaw angle remained concentrated around the target orientation, while angular velocity responses stayed stable without loss-of-control events, indicating a favorable balance between responsiveness and smoothness. Overall, the study validates the robustness and adaptability of the proposed strategy in complex orchard scenarios and establishes a reusable evaluation framework, offering theoretical insights and practical guidance for intelligent agricultural machinery optimization. Full article

Corn, as a globally significant food crop, faces significant yield reductions due to competitive growth from weeds. Precise detection and efficient control of weeds are critical technical components for ensuring high and stable corn yields. Traditional deep learning object detection models generally suffer from issues such as large parameter counts and high computational complexity, making them unsuitable for deployment on resource-constrained devices such as agricultural drones and portable detection devices. Based on this, this paper proposes a lightweight corn weed detection model, AGRI-YOLO, based on the YOLO v11n architecture. First, the DWConv (Depthwise Separable Convolution) module from InceptionNeXt is introduced to reconstruct the C3k2 feature extraction module, enhancing the feature extraction capabilities for corn seedlings and weeds. Second, the ADown (Adaptive Downsampling) downsampling module replaces the Conv layer to address the issue of redundant model parameters; The LADH (Lightweight Asymmetric Detection) detection head is adopted to achieve dynamic weight adjustment while ensuring multi-branch output optimization for target localization and classification precision. Experimental results show that the AGRI-YOLO model achieves a precision rate of 84.7%, a recall rate of 73.0%, and a mAP50 value of 82.8%. Compared to the baseline architecture YOLO v11n, the results are largely consistent, while the number of parameters, G FLOPs, and model size are reduced by 46.6%, 49.2%, and 42.31%, respectively. The AGRI-YOLO model significantly reduces model complexity while maintaining high recognition precision, providing technical support for deployment on resource-constrained edge devices, thereby promoting agricultural intelligence, maintaining ecological balance, and ensuring food security. Full article

Studies exploring the competitive interactions between common beans and weeds are essential to adopt more efficient management strategies in the field, thereby reducing production costs. This study aimed to evaluate the competitive ability of bean cultivars in the presence of sourgrass (Digitaria insularis), using different plant proportions in associations. The experiments were conducted in a greenhouse, arranged in a randomized block design with four replications, from October 2020 to February 2021. Treatments were organized in the following plant proportions of beans and sourgrass: 100:0, 75:25, 50:50, 25:75, and 0:100%. The competitiveness analysis was carried out using replacement series diagrams and relative competitiveness indices. At 50 days after emergence (DAE), measurements were taken for leaf area, plant height, gas exchange, shoot dry mass, and nutrient concentration in bean leaves. The results show that interference between common bean cultivars and sourgrass involves equivalent competition mechanisms. Increasing sourgrass density negatively affects physiological traits and gas exchange in beans by about 10%. Beans show about 15% higher relative growth than sourgrass, based on competitiveness indices. Nutrient levels vary by cultivar and competitor ratio. Intercropping harms species more than intraspecific competition. Further field studies should determine critical control stages and economic impacts, aiding weed management decisions in bean production. Full article

Accurate normalization is crucial for reliable gene expression quantification and depends on stably expressed housekeeping genes (HKGs) as internal controls. However, HKGs expression varies with developmental stage, tissue type, and treatments, potentially introducing bias and compromising data accuracy. Thus, validating candidate reference genes under defined conditions is essential. Reynoutria, also known as giant Asian knotweeds, is a Polygonaceae family genus of several medicinal plants producing a diverse array of specialized metabolites of pharmacological interest. Outside their native range, these plants are also noxious invasive weeds, causing significant environmental and economic threats. Research on stable reference genes in these species is limited, with a primary focus on R. japonica. To enable accurate gene expression analysis related to specialized metabolism and natural product biosynthesis, we aimed to identify the most stable reference genes across the most common species: R. japonica Houtt., R. sachalinensis (F. Schmidt) Nakai, and their hybrid—R. × bohemica Chrtek & Chrtková. In this study, we evaluated twelve candidate HKGs (ACT, TUA, TUB, GAPDH, EF-1γ, UBQ, UBC, 60SrRNA, eIF6A, SKD1, YLS8, and NDUFA13) across three tissue types (rhizomes, leaves, and flowers) from three Reynoutria species sampled at peak flowering. Primer specificity and amplification efficiency were confirmed through standard-curve analysis. We assessed expression stability using ΔCt, geNorm, NormFinder, and BestKeeper, and generated comprehensive rankings with RefFinder. Our integrated analysis revealed organ- and species-dependent stability differences, yet identified up to three reference genes suitable for interspecific normalization in Reynoutria. This represents the first systematic, comparative validation of HKGs across closely related knotweed species, providing a robust foundation for future transcriptomic and functional studies of their specialized metabolism and other biological processes. Full article

Rice membrane-covered cultivation offers notable agronomic advantages, including effective weed suppression and improved moisture retention. However, current mechanized approaches remain constrained by high labor requirements, low operational efficiency, and the inherent fragility of biodegradable membranes. To address these limitations, this study integrates a high-speed synchronous membrane-covering device, governed by a PSO-Fuzzy PID control algorithm, into a conventional rice transplanter. This integration enables precise coordination between membrane-laying and transplanting operations. The mechanical properties of the membranes were analyzed, and a tension evaluation model was developed considering structural parameters and roll diameter variation. Experimental tests on three biodegradable membranes revealed an average thickness of 0.012 mm, a longitudinal tensile force of 0.57 N, and a tensile strength of 2.85 N/mm. The PSO algorithm was employed to optimize fuzzy PID parameters (K = 5.3095, K_p = 10.6981, K_i = 0.0100, K_d = 8.2892), achieving adaptive synchronization between membrane output speed and transplanter travel speed. Simulation results demonstrated that the PSO-Fuzzy PID reduced rise time by 53.13%, stabilization time by 90.58%, and overshoot by 3.3% compared with the conventional PID. In addition, a dedicated test bench for the membrane-covering device was designed and fabricated. Orthogonal experiments determined the optimal parameters for the speed-measurement system: a membrane pressure of 5.000 N, a roller width of 28.506 mm, and a placement angle of 0.690°. Under these conditions, the minimum membrane-stretching tension was 0.55 N, and the rotational speed error was 0.359%. Field tests indicated a synchronization error below 1.00%, a membrane-width variation rate below 1.50%, and strong anti-interference capability. The proposed device provides an effective solution for intelligent and fully mechanized rice transplanting. Full article

Maize, as a critical crop for China’s food security, is constantly challenged by weed infestations and environmental risks associated with herbicide overuse. Improving herbicide utilization efficiency through equipment optimization and intelligent control during spraying has become an essential strategy for weed management in Chinese maize fields. However, most current sprayers fail to achieve coordinated control of spray volume and nozzle parameters, and their performance is typically evaluated using single indices, such as the coefficient of variation (CV) for spray uniformity and deposition density. In this study, a split-split-plot experiment was conducted in 2022–2023 to assess the feasibility of herbicide reduction using intelligent variable-rate boom sprayers in summer maize fields on the North China Plain (NCP). The key variables included spray volume (225 vs. 180 L/ha), nozzle type (AI11003VS/LECHLER11003 in 2022; TTI11004/LECHLER11004 in 2023), and herbicide dose (recommended, −15%, and −30% reduction). Results showed that the coefficients of variation for droplet coverage and density remained below 12% for all treatments (n = 4), indicating stable spray performance. A higher spray volume (225 L/ha) significantly improved deposition uniformity (p < 0.01). In 2022, herbicide input could be reduced by 15–30% while maintaining efficacy above 90% when applied at the 3–4 leaf stage of dominant weeds. However, in 2023, efficacy dropped to 72.67% when the herbicide was applied at a 30% reduced dose with 180 L/ha and when dominant weeds had reached the 5–6 leaf stage or higher, indicating an agronomic risk. Reduced herbicide input decreased maize injury by 47–53%. Only the 30% reduced-dose treatment significantly increased maize yield by 3.05% in 2022 and 2.62% in 2023 compared to the control (both p < 0.05). Spray volume significantly influenced droplet deposition and weed control efficacy; thus, caution is warranted regarding herbicide reduction for later weed growth stages. This study demonstrates that real-time variable-rate boom sprayers, optimized for spray volume and nozzle type, can reduce herbicide use without compromising weed control efficacy or maize yield, providing both theoretical support and practical guidance for sustainable herbicide management in summer maize fields on the NCP. Full article

Melissa officinalis L. (Lamiaceae) is a perennial plant species widely used in the pharmaceutical and food industries, particularly valued for its sedative properties. This study investigates the impact of synthetic mulch film and planting density as two experimental factors on agronomic performance, raw material quality, and economic efficiency in lemon balm production. The experiment was conducted at three locations in Serbia (L1: Bačko Novo Selo, L2: Bavanište, L3: Vilandrica) from 2022 to 2024, using two planting densities on synthetic mulch film (F1: 8.3 plants m⁻²; F2: 11.4 plants m⁻²) and a control treatment without mulch (C). The synthetic mulch film used was a synthetic black polypropylene film (Agritela Black, 90 g/m²), uniformly applied in strips across the cultivation area, covering approximately 78% of the soil surface. The results showed consistent increases in morphological parameters and yield across the years. Plant height in F1 and F2 treatments ranged from 65 to 75 cm, while in the control it reached up to 50 cm (2022–2024). Fresh biomass yield varied from 13.4 g per plant (C) to 378.08 g per plant (F2), and dry biomass yield from 60.3 g (C) to 125.4 g (F2). The highest essential oil content was observed in F2 (1.2% in 2022), while the control remained at 0.8%. The F2 treatment achieved complete weed suppression throughout the experiment without the use of herbicides, demonstrating both agronomic and ecological advantages. Economic evaluation revealed that F2 generated the highest cumulative profit (€142,164.5) compared to the control (€65,555.3). Despite higher initial investment, F2 had the most favorable cost–benefit ratio in the long term. This study highlights the crucial influence of mulching and planting density on optimizing lemon balm production across diverse climatic and soil conditions, while also underscoring the importance of sustainable, non-chemical weed management strategies in lemon balm cultivation. Full article

Soybean production in Thailand faces significant challenges from malignant weed competition, potentially reducing yields by up to 37% and incurring annual economic losses of approximately USD 3.8 billion. Pre-emergence herbicides are critical for integrated weed management, but their efficacy varies depending on local conditions and soybean varieties. This study evaluates the performance of three pre-emergence herbicides, pendimethalin (1875 g a.i. ha⁻¹), s-metolachlor (900 g a.i. ha⁻¹), and flumioxazin (125 g a.i. ha⁻¹), on weed control efficiency (WCE), soybean growth, phytotoxicity, and yield in Northeast Thailand using a randomised complete block design with two varieties (CM60 and Morkhor60) across rainy (2023) and dry (2024/2025) seasons. Herbicide performance varied seasonally: s-metolachlor showed optimal rainy season results (61.54% weed control efficiency at 63 days after herbicide application (DAA), with a yield of 1036 kg ha⁻¹), while flumioxazin excelled in dry conditions (64.32% WCE, <4% phytotoxicity, and 1243 kg ha⁻¹ yield). Pendimethalin performed poorly under wet conditions but improved in drier weather. Among five dominant weed species, Cyperus rotundus proved the most resilient. CM60 demonstrated superior herbicide tolerance and yield stability, particularly under rainy conditions. These results emphasise that season-specific herbicide selection and variety matching are crucial for herbicide resistance management and effective weed control in Thailand’s rainfed soybean systems. Full article

Sugarcane is mostly planted in rows, and the accurate identification of crop rows is important for the autonomous navigation of agricultural machines. Especially in the elongation period of sugarcane, accurate row identification helps in weed control and the removal of ineffective tillers in the field. However, sugarcane leaves and stalks intertwine and overlap at this stage. They can form a complex occlusion structure, which poses a greater challenge to target detection. To address this challenge, this paper proposes an improved target detection method, SugarRow-YOLO, based on the YOLOv11n model. The method aims to achieve accurate sugarcane identification and provide basic support for subsequent sugarcane row detection. This model introduces the WTConv convolutional modules to expand the sensory field and improve computational efficiency, adopts the iRMB inverted residual block attention mechanism to enhance the modeling capability of crop spatial structure, and uses the UIOU loss function to effectively mitigate the misdetection and omission problem in the region of dense and overlapping targets. The experimental results show that SugarRow-YOLO performs well in the sugarcane target detection task, with a precision of 83%, recall of 87.8%, and mAP₅₀ and mAP_50-95 of 90.2% and 69.2%. In addition to addressing the problem of large variability in row spacing and plant spacing of sugarcane, this paper introduces the DBSCAN clustering algorithm and combines it with a smooth spline curve to fit the crop rows in order to realize the accurate extraction of crop rows. This method achieved 96.6% in the task, with high precision in sugarcane target detection and demonstrates excellent accuracy in sugarcane row fitting, offering robust technical support for the automation and intelligent advancement of agricultural operations. Full article

Weeds compete with crops for resources, posing multiple negative impacts for agricultural production systems and triggering degradation of ecosystem services (e.g., alterations in the soil microbial community structure). Under the guidance of green plant protection, the development of efficient biocontrol strains with environmentally friendly characteristics has become a crucial research direction for sustainable agriculture. This study aimed to develop a fungal bioherbicide by isolating and purifying a pathogenic fungal strain (JZ-5) from infected redroot pigweed (Amaranthus retroflexus L.). The strain exhibited pathogenicity rates ranging from 23.46% to 86.25% against six weed species, with the most pronounced control efficacy observed against henbit deadnettle (Lamium amplexicaule L.), achieving a pathogenicity rate of 86.25%. Through comprehensive characterization of cultural features, morphological observations, and molecular biological identification, the strain was taxonomically classified as Fusarium oxysporum. Scanning electron microscopy revealed that seven days post-inoculation, F. oxysporum JZ-5 formed dense mycelial networks on the leaf surfaces of cluster mallow (Malva verticillata L.), causing severe tissue damage. Safety assessments demonstrated that the spore suspension (10⁴ spores/mL) had no adverse effects on three crops: hulless barley (Hordeum vulgare var. coeleste L.), wheat (Triticum aestivum L.), and potato (Solanum tuberosum L.). These findings suggest that F. oxysporum strain JZ-5 warrants further investigation as a potential bioherbicide for controlling three problematic weed species—Chenopodium album L. (common lambsquarters), Elsholtzia densa Benth. (dense-flowered elsholtzia), and Lamium amplexicaule L. (henbit deadnettle)—in cultivated fields of hulless barley (Hordeum vulgare var. coeleste L.), wheat (Triticum aestivum L.), and potato (Solanum tuberosum L.). This discovery provides valuable fungal resources for ecologically sustainable weed management strategies, contributing significantly to the advancement of sustainable agricultural practices. Full article

Agricultural water resource management is increasingly challenged by climate variability, land degradation, and socio-economic pressures, particularly in the Mediterranean region. This study, conducted in 2023–2024 within the REACT4MED project (PRIMA initiative), addresses sustainable water use through a comparative analysis of organic and conventional farms in the Stornara and Tara area (Puglia, Italy). The research aimed to identify critical indicators for sustainable water management and develop ecosystem restoration strategies that can be replicated across similar Mediterranean agro-ecosystems. An interdisciplinary, participatory approach was adopted, combining technical analyses and stakeholder engagement through three workshops involving 30 participants from diverse sectors. Fieldwork and laboratory assessments included soil sampling and analysis of parameters such as pH, electrical conductivity, soil organic carbon, nutrients, and salinity. Cartographic studies of vegetation, land use, and pedological characterization supplemented the dataset. The key challenges identified were water loss in distribution systems, seawater intrusion, water pumping from unauthorized wells, and inadequate public policies. Soil quality was significantly influenced by salt stress, hence affecting crop productivity, while socio-economic factors affected farm income. Restoration strategies emphasized the need for water-efficient irrigation, less water-intensive crops, and green vegetation in infrastructure channels while incorporating also the native flora. Enhancing plant biodiversity through weed management in drainage channels proved beneficial for pathogen control. Proposed socio-economic measures include increased inclusion of women and youth in agricultural management activities. Integrated technical and participatory approaches are essential for effective water resource governance in Mediterranean agriculture. This study offers scalable, context-specific indicators and solutions for sustainable land and water management in the face of ongoing desertification and climate stress. Full article

Soil management significantly influences the structure and diversity of soil bacterial communities, affecting biodiversity and ecosystem functions. In semi-arid regions, water efficiency strategies like anti-weed netting are implemented, but their impact on soil microbial communities remains underexplored. This study evaluates the temporal evolution of soil bacterial communities in orange tree (Citrus sinensis (L.) Osbeck) plantations under two conditions: with and without anti-weed netting. Soil samples were collected at three time points over a period of 18 months since the establishment of the crop and analyzed using high-throughput 16S rRNA sequencing, assessing alpha and beta diversity, taxonomic composition, and functional pathways via KEGG analysis. The results indicate that weed control netting contributes to stabilizing bacterial diversity over time and increases the relative abundance of dominant phyla such as Planctomycetota, Proteobacteria, Bacteroidota, and Acidobacteriota. Functional predictions revealed significant differences in metabolic pathways, including those associated with nitrogen fixation and organic matter degradation. These findings suggest that anti-weed netting not only influences the taxonomic composition of soil bacterial communities but also modulates their functional potential, with implications for sustainable agriculture in semi-arid environments. This study provides new insights into the interaction between soil management and soil bacterial communities, offering valuable information for optimizing agricultural practices and soil conservation strategies. Full article