Search Results (107)

Ensuring global food security requires accurate and robust solutions for crop health monitoring, weed detection, and large-scale land-cover classification. To this end, we propose AgroVisionNet, a hybrid deep learning framework that integrates Convolutional Neural Networks (CNNs) for local feature extraction, Vision Transformers (ViTs) for capturing long-range global dependencies, and Graph Neural Networks (GNNs) for modeling spatial relationships between image regions. The framework was evaluated on five diverse benchmark datasets—PlantVillage (leaf-level disease detection), Agriculture-Vision (field-scale anomaly segmentation), BigEarthNet (satellite-based land-cover classification), UAV Crop and Weed (weed segmentation), and EuroSAT (multi-class land-cover recognition). Across these datasets, AgroVisionNet consistently outperformed strong baselines including ResNet-50, EfficientNet-B0, ViT, and Mask R-CNN. For example, it achieved 97.8% accuracy and 95.6% IoU on PlantVillage, 94.5% accuracy on Agriculture-Vision, 92.3% accuracy on BigEarthNet, 91.5% accuracy on UAV Crop and Weed, and 96.4% accuracy on EuroSAT. These results demonstrate the framework’s robustness across tasks ranging from fine-grained disease detection to large-scale anomaly mapping. The proposed hybrid approach addresses persistent challenges in agricultural imaging, including class imbalance, image quality variability, and the need for multi-scale feature integration. By combining complementary architectural strengths, AgroVisionNet establishes a new benchmark for deep learning applications in precision agriculture. Full article

Weedy rice (Oryza spp.) has become one of the most harmful weeds in rice fields worldwide. It is a conspecific plant of cultivated rice (Oryza sativa L.) belonging to the genus Oryza, widely occurring in global rice production systems with a cosmopolitan distribution across major rice-growing regions. Due to its unique biological characteristics, such as strong environmental adaptability, stress resistance, seed shattering propensity, seed dormancy, and competitive dominance, weedy rice can rapidly proliferate and persist in fields, posing a severe threat to rice production systems. This review summarizes the current research progress on the biological characteristics of weedy rice and introduces the significant differences in biological characteristics between weedy and cultivated rice, such as phenotypic diversity, seed shattering, dormancy, strong competitiveness, stress resistance, and early maturity. These distinct biological traits, which significantly differ from cultivated rice, serve as essential mechanisms in the survival strategy of weedy rice. Our review will provide a theoretical reference for a deeper understanding of weedy rice and its integrated management. Full article

Vineyard cover crops deliver well-documented ecosystem services, yet consistent establishment, especially of perennial grasses and legumes, remains a primary barrier to adoption. This review reframes “companion (nurse) cropping” not as a new crop class but as a facilitative establishment strategy within the broader cover-/service-crop literature. We (i) position our contribution relative to recent syntheses, (ii) synthesize evidence on companion crops practices that reduce cover cropping early failure risk, and (iii) propose a testable research agenda. A focused scoping review of peer-reviewed and extension literature indexed in Web of Science and Google Scholar was conducted using search terms encompassing cover/service crops and nurse/companion/facilitation in viticulture systems. Across climates, fast-establishing cereals (Avena sativa, Hordeum vulgare, Secale cereale, × Triticosecale Wittmack) and short-cycle legumes (Vicia sativa, Pisum sativum, Trifolium incarnatum) can reliably “nurse” slower perennials and legumes by providing early groundcover, weeds control, and microclimate buffering when sown at reduced rates (≈25–50% of monoculture) and terminated on time to limit vine competition. Evidence gaps persist for in-row applications, water-use penalties under drought, and long-term effects on yield and grape composition. Companion cropping is argued to be a design principle in vineyard cover-crop programs rather than a separate category. A decision framework and research agenda are presented to quantify establishment reliability, resource trade-offs, and wine-relevant outcomes, and it is recommended that future decision tools make the companion-phase logic explicit to de-risk adoption and align with regional guidelines. Full article

Essential oils are increasingly recognized as promising agents for sustainable weed control due to their selectivity and complex modes of action. This study evaluated the effects of Acorus calamus essential oil (SEO) on mitosis in two Fabaceae species (Vicia faba, Lupinus luteus) and two Brassicaceae species (Brassica napus, Arabidopsis thaliana) treated with species-specific IC₅₀ concentrations (0.03%, 0.025%, 0.01%, and 0.005%, respectively). Previous research showed that SEO induces oxidative stress and S-phase delay via genome instability. Here, SEO consistently disrupted mitosis across all species, reducing mitotic index by 50–60%, decreasing Cdc2 (CDKA homolog) levels, and causing chromosomal aberrations, including uneven chromatin condensation, sticky chromosomes, bridges, and micronuclei. Cells accumulated in metaphase and exhibited abnormal karyokinetic and cytokinetic spindles. Immunolabeling revealed thick, tightly packed microtubules and actin filaments, indicating excessive stabilization and impaired reorganization. Epigenetic regulation was also affected: H3T3 phosphorylation was abnormally strong, widely distributed, and persistent into anaphase/telophase, while H3S10Ph intensity was weakened. These results suggest that SEO targets multiple components of mitotic machinery and epigenetic control, regardless of species. The observed selectivity depends on dosage, not mechanism. This multi-targeted action may limit the development of plant resistance, supporting the potential of SEO as a bioherbicide in sustainable agriculture. Full article

Organic annual vegetable farming systems often rely on intensive tillage for weed management due to the prohibition of synthetic herbicides. Regenerative organic agriculture aims to improve soil health and reduce the frequency and intensity of soil tillage by using cover crops as high-residue mulches to suppress weeds. In southern coastal California, the moderate climate supports year-round vegetable production, discouraging many growers from integrating cover crops into their operation and leaving sustainability-minded growers with few strategies to produce organic vegetables outside of reliance on tillage. This study evaluates standard organic tillage practices versus high-residue cover-crop mulch system on squash, peppers, and eggplant over two seasons. We assessed treatment effects on soil health indicators, weed pressure, and crop production. Soil under the cover-crop system improved soil organic matter, organic carbon and nitrogen, microbially active carbon, and water infiltration compared to bare soil. Weed biomass was substantially lower under the high-residue mulch due to persistent surface cover. Crop yield was 82%, 169%, and 189% higher in the cover-crop plots for squash, pepper, and eggplant, respectively. These findings demonstrate that high-residue cover-crop systems can enhance soil health, reduce weed pressure, and substantially increase yields, providing evidence-based strategies for implementing regenerative organic practices in vegetable systems. Full article

The practice in agriculture of spreading polyethylene (PE) film over the soil surface as mulch is a common, global practice that aids in conserving water, increasing crop yields, suppressing weed growth, and decreasing growing time. However, these films are typically only used for a single growing season, and thus, their use and non-biodegradability come with some serious environmental consequences due to their persistence in the soil and potential for microplastic pollution, particularly when retrieval and disposal options are poor. On the microscale, particles < 5 mm from degraded films have been observed to disrupt soil structure, impede water and nutrient cycling, and affect soil organisms and plant health. On the macroscale, there are obvious and serious environmental consequences associated with the burning of plastic film and its leakage from poorly managed landfills. To maintain the crop productivity afforded by mulching with PE film while avoiding the environmental downsides, the development and use of biodegradable polymer technologies is being explored. Here, the efficacy of a newly developed, water-dispersible, sprayable, and biodegradable polyester–urethane–urea (PEUU)-based polymer was compared with two commercial PE mulches, non-degradable polyethylene (NPE) and OPE (ox-degradable polyethylene), in a greenhouse tomato growth trial. Water savings and the effects on plant growth and soil characteristics were studied. It was found that PEUU provided similar water savings to the commercial PE-based mulches, up to 30–35%, while showing no deleterious effects on plant growth. The results should be taken as preliminary indications that the sprayable, biodegradable PEUU shows promise as a replacement for PE mulch, with further studies under outside field conditions warranted to assess its cost effectiveness in improving crop yields and, importantly, its longer-term impacts on soil and terrestrial fauna. Full article

Some herbicides, such as saflufenacil, can persist as residues in sprayer tanks even after cleaning, causing phytotoxicity in sensitive crops. This study aimed to simulate potential injury caused by saflufenacil residues, applied alone or combined with glyphosate, on soybean. The field experiment was conducted using a randomized complete block design with four replicates. The treatments included glyphosate (1440 g ha⁻¹), eight saflufenacil doses ranging from 1.09 to 70.00 g ha⁻¹, each tested alone or combined with glyphosate, and a weed-free control, totaling 18 treatments. Phytotoxicity was assessed at 7, 14, 21, 28, and 35 days after treatment (DAT). Physiological variables were measured at 21 DAT, and grain yield components were evaluated at harvest. Saflufenacil caused increasing phytotoxicity at doses exceeding 4.38 g ha⁻¹ when applied alone and above 2.17 g ha⁻¹ when combined with glyphosate. The highest doses negatively affected soybean physiology and grain yield components. Soybean tolerated up to 2.17 g ha⁻¹ saflufenacil alone and up to 1.09 g ha⁻¹ combined with glyphosate without significant yield loss. These results highlight the importance of thorough and correct cleaning of the sprayer tank and suggest limit residue levels that avoid crop damage, helping to prevent unexpected damage to soybean in crop rotations. Full article

Pyrrolizidine alkaloids are plant-derived toxins with environmental persistence and the potential to contaminate soil, water, and adjacent crops. This study investigated the leaching behavior and environmental fate of PAs from two PA-producing weeds—Myosotis arvensis L. (Boraginaceae) and Senecio vulgaris L. (Asteraceae)—in two Latvian agricultural soils: sandy loam and loam. Hot- and cold-water plant extracts were applied to soil columns (10 cm and 20 cm), and leachates were analyzed over a 14-day period using QuEChERS purification and LC-HRMS detection. Leaching varied by plant species, extract type, and soil. M. arvensis showed significantly higher cumulative leaching (77–84% for cold, 65–71% for hot extracts), attributed to the higher solubility of N-oxides. In contrast, S. vulgaris extracts leached minimally (<0.84% from sandy loam) and were undetectable in loam. The presence of cyclic diester PAs in S. vulgaris and the higher cation exchange capacity of loam favored retention or degradation. PANO-to-PA conversion occurred in both soils, indicating redox activity. The fate of PAs was influenced by structural type (diesters showing higher persistence), extraction method (hot extraction releasing more pyrrolizidine alkaloids), and soil properties such as pH, organic matter, and cation exchange capacity, which affected sorption and mobility. These findings underscore the significance of soil composition in controlling PA mobility and associated environmental risks. Future research should focus on long-term PA persistence across diverse soil types and investigate crop uptake potential and microbial degradation pathways under field conditions. Full article

This study investigated the production, purification, and evaluation of a microbial metabolite with herbicidal activity produced by Fusarium fujikuroi via submerged fermentation. The purified compound (PC) was obtained through organic solvent extraction and chromatographic purification, and assessed in bioassays using Raphanus sativus and Triticum aestivum as bioindicator plants. A concentration of 23 mg mL⁻¹ completely inhibited seed germination in 96-well plate assays, while the crude extract (EXT) and cell-free broth (CFB) allowed radicle protrusion but resulted in abnormal seedlings with chlorosis and reduced growth. Mathematical models estimated that concentrations of 16.0 mg mL⁻¹ for radish and 0.9 mg mL⁻¹ for wheat were sufficient to suppress germination with the PC. In substrate experiments, the PC at 6.4 and 64.0 mg mL⁻¹ did not inhibit germination but caused anomalies in radish and significantly reduced wheat seedling growth. In naturally infested soil, the PC maintained phytotoxicity symptoms for 21 days, and after 28 days, a concentration of 64.0 mg mL⁻¹ significantly reduced radish seedling growth. The results highlight the potential of the compound as a bioherbicide. Full article

Object detection is revolutionizing precision agriculture by enabling advanced crop monitoring, weed management, pest detection, and autonomous field operations. This comprehensive review synthesizes object detection methodologies, tracing their evolution from traditional feature-based approaches to cutting-edge deep learning architectures. We analyze key agricultural applications, leveraging datasets like PlantVillage, DeepWeeds, and AgriNet, and introduce a novel framework for evaluating algorithm performance based on mean Average Precision (mAP), inference speed, and computational efficiency. Through a comparative analysis of leading algorithms, including Faster R-CNN, YOLO, and SSD, we identify critical trade-offs and highlight advancements in real-time detection for resource-constrained environments. Persistent challenges, such as environmental variability, limited labeled data, and model generalization, are critically examined, with proposed solutions including multi-modal data fusion and lightweight models for edge deployment. By integrating technical evaluations, meaningful insights, and actionable recommendations, this work bridges technical innovation with practical deployment, paving the way for sustainable, resilient, and productive agricultural systems. Full article

The wooly cupgrass (Eriochloa villosa) is an invasive weed species originating from East Asia that rapidly expanded into agricultural and disturbed land. Its tolerance to herbicides and ecological adaptations enable it to become persistent and difficult to remove with limited control methods. This review synthesizes existing research on its distribution, biology, biochemistry, ecology, management and agricultural impact. Lipid synthesis inhibitor herbicides are reported to provide good results when applied early. Others such as Nicosulfuron and Foramsulfuron, although still effective in many populations, have been linked to emerging resistance in others. Chemical control is still widely used and developing resistance is an increasing concern, so various other control methods are also discussed and encouraged. Row crops such as corn (Zea mays) and soybeans (Glycine max) are particularly vulnerable. Despite being problematic, this species presents potential as a medicinal plant as well as in phytoremediation. Regardless, numerous research gaps remain, particularly in chemical control, its economic impact, biochemical properties, community dynamics and distribution. We aim to provide a comprehensive basis for future research with a focus on interdisciplinary approaches in order to contain its spread as much as possible, as well as explore the benefits it may provide. Full article

Weed management is a persistent challenge in Southeast Asian rice production, particularly in direct-seeded rice (DSR), due to the diversity of weed species and variable field and environmental conditions that can compromise weed control, necessitating innovative solutions. An integrated weed seed impact mill (iWSIM) reduces weed seed banks by destroying weed seeds during the harvest process. This mixed study is the first to fully explore the applicability of iWSIM technology in Southeast Asian rice systems, focusing on both combine harvester and iWSIM specifications and operation, determinants of efficacy, and field and harvest conditions. Weed seed bank reduction with an iWSIM depends on several factors, including weed seed retention and subsequent capture by the combine at harvest, weed seed separation into the chaff fraction, and the iWSIM’s efficacy against weed seeds captured in the chaff fraction. Observations from Southeast Asia indicate variable seed retention among key weed species, presenting challenges for harvesting strategies and iWSIM effectiveness. To optimize the iWSIM efficacy, recommendations include larger fields to reduce the weed seed produced on bunds, achieving complete early-season weed control, lowering the harvest header height to about 15 cm to capture more weed seeds, cleaning mechanism adjustments to ensure weed seeds are retained in the chaff fraction, and greater combine harvester engine power to allow a lower header height and power the iWSIM. The estimated weed control benefits of the iWSIM should also be weighed against additional equipment operating costs. iWSIM technology holds promise as part of a sustainable solution for weed control in Southeast Asian rice, contingent upon further region-specific research and adaptation. Full article

The continued emergence of weedy rice (Oryza sativa L.) in Taiwan poses serious challenges to seed purity and commercial rice cultivation, particularly under transplanting systems. These off-type individuals, often marked by a red pericarp, reduce varietal integrity and complicate seed propagation. This study evaluated the morphological variation among 117 Taiwan weedy rice (TWR) accessions and 55 control cultivars, which include 24 temperate japonica cultivars (TEJ), 24 indica cultivars, and seven U.S. weedy rice (UWR) types. Principal component analysis (PCA) showed that TWR shares vegetative traits with modern cultivars but exhibits grain morphology resembling indica landraces—indicating weak artificial selection pressure on grain traits during nursery propagation. TWR was also found to possess a suite of adaptive weedy traits, including semi-dwarfism, delayed heading, high shattering, and superior seed storability, facilitating its persistence in field conditions. These findings provide critical insights for integrated weed management and cultivar purity strategies, emphasizing the importance of certified seed use, stringent field hygiene, and disruption of weedy rice reproductive cycles. Full article

Lettuce, a vital economic crop, benefits significantly from intelligent advancements in its production, which are crucial for sustainable agriculture. Deep learning, a core technology in smart agriculture, has revolutionized the lettuce industry through powerful computer vision techniques like convolutional neural networks (CNNs) and YOLO-based models. This review systematically examines deep learning applications in lettuce production, including pest and disease diagnosis, precision spraying, pesticide residue detection, crop condition monitoring, growth stage classification, yield prediction, weed management, and irrigation and fertilization management. Notwithstanding its significant contributions, several critical challenges persist, including constrained model generalizability in dynamic settings, exorbitant computational requirements, and the paucity of meticulously annotated datasets. Addressing these challenges is essential for improving the efficiency, adaptability, and sustainability of deep learning-driven solutions in lettuce production. By enhancing resource efficiency, reducing chemical inputs, and optimizing cultivation practices, deep learning contributes to the broader goal of sustainable agriculture. This review explores research progress, optimization strategies, and future directions to strengthen deep learning’s role in fostering intelligent and sustainable lettuce farming. Full article

The genus Rhynchosia includes more than 550 species, some exhibiting invasive behavior. Rynchosia senna var. senna (RS) is a challenging weed to control in its native range; however, its invasive potential remains unknown. The aim of this study was to evaluate RS demographic parameters to determine its invasive potential, including (i) plant fecundity during the first year of young adult and in adult plants, (ii) seed dispersal, (iii) pre- and post-dispersal predation, (iv) soil seedbank persistence, and (v) field emergence patterns. RS fecundity declined in autumn and mainly in early established cohorts. Fecundity was influenced by pre-dispersal predation (Bruchus spp. 12 ± 2%), and post-dispersal removal by birds (66 ± 4%) and arthropods (37 ± 5%). Seed dispersal decreased with distance. Seedling emergence occurred mainly during early summer (75%), and to a lesser extent during late summer (20%) and autumn (5%). Seed physical dormancy loss (~80% in the first year) defines a short persistent seedbank. Under the evaluated conditions (native environment), RS shows a limited invasive potential. However, in non-native environments, in the absence of natural predators, its prolific fecundity and the occurrence of staggered emergence patterns could easily enhance invasiveness, enabling rapid colonization, as observed in Medicago polymorpha L. Full article