Search Results (46)

Weeds are an inevitable element in agricultural production, and their significant negative impacts on crop growth make weed detection a crucial task in precision agriculture. The diversity of weed species and the substantial background noise in weed images pose considerable challenges for weed detection. To address these challenges, constructing a high-quality dataset and designing an effective artificial intelligence model are essential solutions. We captured 2002 images containing 10 types of weeds from cotton and corn fields, establishing the CornCottonWeed dataset, which provides rich data support for weed-detection tasks. Based on this dataset, we developed the MKD8 model for weed detection. To enhance the model’s feature extraction capabilities, we designed the CVM and CKN modules, which effectively alleviate the issues of deep-feature information loss and the difficulty in capturing fine-grained features, enabling the model to more accurately distinguish between different weed species. To suppress the interference of background noise, we designed the ASDW module, which combines dynamic convolution and attention mechanisms to further improve the model’s ability to differentiate and detect weeds. Experimental results show that the MKD8 model achieved mAP₅₀ and mAP_[50:95] of 88.6% and 78.4%, respectively, on the CornCottonWeed dataset, representing improvements of 9.9% and 8.5% over the baseline model. On the public weed dataset CottoWeedDet12, the mAP₅₀ and mAP_[50:95] reached 95.3% and 90.5%, respectively, representing improvements of 1.0% and 1.4% over the baseline model. Full article

Weeds are unwanted and invasive plants characterized by their rapid growth and ability to compete with crops for essential resources such as space, water, nutrients, and sunlight. This competition has a negative impact on crop quality and productivity. To reduce the influence of weeds, precision weeding is used, which uses image sensors and computational algorithms to identify plants and classify weeds using digital images. This study used images of maize (Zea mays L.) to detect four types of weeds (Lolium rigidum, Sonchus oleraceus, Solanum nigrum, and Poa annua). For this purpose, YOLO (You Only Look Once) architectures, YOLOv8s, YOLOv9s, YOLOv10s, and YOLOv11s versions, were trained and compared, along with an architecture based on RT-DETR (Real-Time Detection Transformer), version RT-DETR-1. The YOLO architectures are noted for their real-time detection efficiency, and RT-DETR-l allows evaluation of the impact of an architecture that dispenses with Non-Maximum Suppression (NMS). The YOLOv9s model had the best overall performance, achieving a mAP@0.5 of 0.834 in 60 epochs and an F1-score of 0.78, which demonstrates a optimal balance between accuracy and recall, although with less confidence in its predictions. On the other hand, the RT-DETR-l model stood out for its efficiency in convergence, reaching a competitive performance in only 58 epochs with a mAP@0.5 of 0.828 and an F1-score of 0.80. Full article

In agricultural planting, early plant classification is an indicator of crop health and growth. In order to accurately classify early plants, this paper proposes a classification method combining a dual attention mechanism and multi-scale module. Firstly, the ECA module (Efficient channel attention) is added to enhance the attention of the network to plants and suppress irrelevant background noise; secondly, the MSFN (Multi-scale Feedforward Network) module is embedded to improve the ability to capture complex data features. Finally, CA (Channel attention) is added to further emphasize the extracted features, thus enhancing the discrimination ability and improving the accuracy of the model. The experimental results show an accuracy of 93.20%, precision of 94.53%, recall of 93.27%, and an F1 score of 93.39%. This study can realize the classification of early plants, and effectively distinguish crops from weeds, which is helpful to identify and realize accurate weeding, thus promoting the intelligent and modern process of agricultural production. Full article

To thrive as a successful weed in natural pastures, a plant must have not only highly competitive ability, but also the resilience to endure environmental stress and rapidly reclaim space once those stressors diminish and the other non-stress-tolerant plants die. Acanthostyles buniifolius [(Hook. ex Hook. & Arn.) R.M.King & H.Rob.], known as chirca, is a widely spread weed in South American natural pastures. It is known for its remarkable ability to withstand environmental stress and flourish in environments with prevalent stressors. The study evaluated the memory effect of water stress (drought) in chirca plants. The experiment was conducted in a greenhouse in a randomized block design with three replications. Treatments included Control = control plants without water deficit kept at 100% of the soil water-holding capacity (WHC); Primed plants = plants that were primed with water stress at 141 days after emergence (DAE) and received recurrent stress at 164 DAE; Naïve plants: plants that only experienced water stress at 164 DAE. To reach water stress, plants were not watered until the soil reached 15% of the soil’s WHC, which occurred ten days after water suppression in the priming stress and nine days after water suppression in the second stress. During periods without restriction, the pots were watered daily at 100% of the WHC. Primed plants exposed to water deficit better-maintained water status compared to the naïve plants; glycine betaine is an important defense mechanism against water deficit in chirca; naïve plants have a higher concentration of proline than plants under recurrent stress, demonstrating the greater need for protection against oxidative damage and needs greater osmotic regulation. Recurrent water deficits can prepare chirca plants for future drought events. These results show that chirca is a very adaptative weed and may become a greater threat to pastures in South America due to climate change, especially if drought becomes more frequent and severe. Full article

Wheat (Triticum aestivum) is grown on more arable acreage than any other food crop and has been well documented to produce allelochemicals. Wheat allelochemicals include numerous benzoxazinoids and their microbially transformed metabolites that actively suppress growth of weed seedlings. Production and subsequent release of these metabolites by commercial wheat cultivars, however, has not yet been targeted by focussed breeding programmes seeking to develop more competitive crops. Recently, the Commonwealth Scientific and Industrial Organisation (CSIRO), through an extensive recurrent selection programme investment, released numerous early-vigour wheat genotypes for commercial use, but the physiological basis for their improved vigour is under investigation. In the current study, we evaluated several early-vigour genotypes alongside common commercial and heritage wheat cultivars to assess the impact of improved early vigour on the production and release of targeted benzoxazinoids by field-grown wheat roots over a two-year period. Using UPLC coupled with triple quadrupole mass spectrometry (LC-MS QQQ), we quantified common wheat benzoxazinoids and their microbially produced metabolites (aminophenoxazinones) in soil collected from the rhizosphere and rhizoplane of wheat plants over two growing seasons in the Riverina region of New South Wales, Australia. The benzoxazolinone MBOA and several aminophenoxazinones were readily detected in soil samples, but actual soil concentrations differed greatly between years and among genotypes. In contrast to 2019, the concentration of aminophenoxazinones in wheat rhizosphere soil was significantly elevated in 2020, a year receiving adequate rainfall for optimal wheat growth. Aminophenoxazinones were detected in the rhizosphere of early-vigour genotypes and also parental lines exhibiting weed suppression, suggesting that improved early vigour and subsequent weed competitiveness may be related to increased root exudation and production of microbial metabolites in addition to changes in canopy architecture or other root-related early-vigour traits. As previously reported, MBOA was detected frequently in both the rhizoplane and rhizosphere of wheat. Depending on the year and genotype, we also observed enhanced biotransformation of these metabolites to several microbially transformed aminophenoxazinones in the rhizosphere of many of the evaluated genotypes. We are now investigating the role of early-vigour traits, including early canopy closure and biomass accumulation upon improved competitive ability of wheat, which will eventually result in more cost-effective weed management. Full article

Canola (Brassica napus L.) is an important oilseed crop that provides essential vegetable oil but faces significant competition from weeds that are influenced by various agronomic practices and environmental conditions. This study examines the complex interactions between canola stand density and weed intensity over three growing seasons, identifying a total of 27 weed species. It is important to establish a connection between the density of winter canola stands, the intensity of weeding and the response of individual weed species in real conditions. The case study was executed on plots located in the Přerov district (Olomouc region, Czech Republic). The assessment was carried out during two periods—autumn in October and spring in April. Canola plants (plant density) were counted in each evaluated area, weed species were identified, and the number of plants for each weed species was determined. Half of the plots were covered with foil before herbicide application to prevent these areas from being treated with herbicides. We used redundancy analysis (RDA) to evaluate the relationships between canola density and weed dynamics, both with and without herbicide treatment. The results show the ability of canola to compete with weeds; however, that is factored by the density of the canola stand. In dense stands (over 60 plants/m²), canola is able to suppress Galium aparine L., Geranium pusillum L., Lamium purpureum L., Papaver rhoeas L. and Chamomilla suaveolens (Pursh) Rydb. Nevertheless, there are weed species that grow well even in dense canola stands (Echinochloa crus-galli (L.) P. Beauv., Phragmites australis (Cav.) Steud., Tripleurospermum inodorum (L.) Sch. Bip. and Triticum aestivum L.). These findings highlight the potential for using canola stand density as a strategic component of integrated weed management to reduce herbicide reliance and address the growing challenge of herbicide-resistant weed populations. This research contributes significantly to our understanding of the dynamics of weed competition in canola systems and informs sustainable agricultural practices for improved crop yield and environmental stewardship. Full article

Canola (Brassica napus L.) is a profitable grain crop for Australian growers. However, weeds remain a major constraint for its production. Chemical herbicides are used for weed control, but this tactic also leads to the evolution of herbicide resistance in different weed species. The suppression of weeds by crop interference (competition and allelopathic) mechanisms has been receiving significant attention. Here, the weed suppressive ability and associated functional traits and stability of four selected canola genotypes (PAK85388-502, AV-OPAL, AV-GARNET, and BAROSSA) were examined at different locations in NSW, Australia. The results showed that there were significant effects of canola genotypes and of genotypes by crop density interaction on weed growth. Among the tested genotypes, PAK85388-502 and AV-OPAL were the most weed suppressive and, at a plant density of 10 plants/m², they reduced the weed biomass of wild radish, shepherd’s purse, and annual ryegrass by more than 80%. No significant differences were found in the primary root lengths among canola varieties; however, plants of the most weed-suppressive genotype PAK8538-502 exhibited a 35% increase in lateral root number relative to plants of the less weed-suppressive genotype BAROSSA. The analysis of variance revealed a significant influence of genotypes with PAK85388-502 and AV-OPAL performing the best across all the research sites. Results showed that canola genotypes PAK85388-502 and AV-OPAL were more weed suppressive than AV-GARNET and BAROSSA and may release specific bioactive compounds in their surroundings to suppress neighboring weeds. This study provides valuable information that could be utilised in breeding programs to select weed-suppressive varieties of canola in Australia. Thus, lateral root number could be a potential target trait for weed-suppressive varieties. Additionally, other root architecture traits may contribute to the underground allelopathic interaction to provide a competitive advantage to the crop. Full article

Due to the existence of cotton weeds in a complex cotton field environment with many different species, dense distribution, partial occlusion, and small target phenomena, the use of the YOLO algorithm is prone to problems such as low detection accuracy, serious misdetection, etc. In this study, we propose a YOLOv8-DMAS model for the detection of cotton weeds in complex environments based on the YOLOv8 detection algorithm. To enhance the ability of the model to capture multi-scale features of different weeds, all the BottleNeck are replaced by the Dilation-wise Residual Module (DWR) in the C2f network, and the Multi-Scale module (MSBlock) is added in the last layer of the backbone. Additionally, a small-target detection layer is added to the head structure to avoid the omission of small-target weed detection, and the Adaptively Spatial Feature Fusion mechanism (ASFF) is used to improve the detection head to solve the spatial inconsistency problem of feature fusion. Finally, the original Non-maximum suppression (NMS) method is replaced with SoftNMS to improve the accuracy under dense weed detection. In comparison to YOLO v8s, the experimental results show that the improved YOLOv8-DMAS improves accuracy, recall, mAP0.5, and mAP0.5:0.95 by 1.7%, 3.8%, 2.1%, and 3.7%, respectively. Furthermore, compared to the mature target detection algorithms YOLOv5s, YOLOv7, and SSD, it improves 4.8%, 4.5%, and 5.9% on mAP0.5:0.95, respectively. The results show that the improved model could accurately detect cotton weeds in complex field environments in real time and provide technical support for intelligent weeding research. Full article

Recently, there has been growing interest in the use of summer cover crops that can be grown during summer fallow periods of crop rotation. This study evaluates the potential of sunn hemp (Crotalaria juncea L.), velvetbean [Mucuna pruriens (L.) DC.] and cowpea [Vigna unguiculata (L.) Walp.]. as three annual legumes summer cover crops. The main objective of this review was to conduct global research comparing these summer cover crops to investigate the benefits, challenges, and trade-offs among ecosystems services when implementing these summer cover crops. In European agriculture, there are three main windows in crop rotation when these summer legumes can be grown: Around mid-spring after winter fallow, early summer after harvest of a winter crop, and mid- to late summer after harvest of an early-season crop. All three legumes can suppress weeds while they are actively growing. After termination, their mulch can create unfavorable conditions for weed emergence. Sunn hemp and velvetbean cover crops can cause a reduction in weed biomass of more than 50%. In addition to their ability to suppress weeds, sunn hemp, velvetbean, and cowpea provide a variety of ecosystem services, such as improving soil health, quality, and fertility, controlling pests, and sequestering carbon. The review highlights their promising role in weed suppression and their contribution to sustainable agricultural practices. However, further research is needed to evaluate their performance in weed management and their environmental impact in field trials under different soil-climatic conditions, as cover cropping is an effective practice but highly context-specific. Full article

Navua sedge (Cyperus aromaticus), a perennial plant native to Africa, poses a significant weed concern due to its capacity for seed and rhizome fragment dissemination. Infestations can diminish pasture carrying capacity, displacing desirable species. Despite the burgeoning interest in integrated weed management strategies, information regarding the efficacy of competitive interactions with other pasture species for Navua sedge management remains limited. A pot trial investigated the competitive abilities of 14 diverse broadleaf and grass pasture species. The results indicated a range of the reduction in Navua sedge dry biomass from 6% to 98% across these species. Subsequently, three broadleaf species—burgundy bean (Macroptilium bracteatum), cowpea (Vigna unguiculata), and lablab (Lablab purpureus), and three grass species—Gatton panic (Megathyrsus maximus), Rhodes grass (Chloris gayana), and signal grass (Urochloa decumbens) were chosen for a follow-up pot trial based on their superior dry biomass performance. These six species were planted at three varying densities (44, 88, and 176 plants/m²) surrounding a Navua sedge plant. Among the grass pasture species, Gatton panic and Rhodes grass exhibited high competitiveness, resulting in a minimum decrease of 86% and 99%, respectively, in Navua sedge dry biomass. Regarding the broadleaf species, lablab displayed the highest competitiveness, causing a minimum decrease of 99% in Navua sedge dry biomass. This study highlights the increasing efficacy of crop competition in suppressing weed growth and seed production, with the most significant suppression observed at a density of 176 plants/m². Full article

This study focuses on real-time detection of maize crop rows using deep learning technology to meet the needs of autonomous navigation for weed removal during the maize seedling stage. Crop row recognition is affected by natural factors such as soil exposure, soil straw residue, mutual shading of plant leaves, and light conditions. To address this issue, the YOLOv5s network model is improved by replacing the backbone network with the improved MobileNetv3, establishing a combination network model YOLOv5-M3 and using the convolutional block attention module (CBAM) to enhance detection accuracy. Distance-IoU Non-Maximum Suppression (DIoU-NMS) is used to improve the identification degree of the occluded targets, and knowledge distillation is used to increase the recall rate and accuracy of the model. The improved YOLOv5s target detection model is applied to the recognition and positioning of maize seedlings, and the optimal target position for weeding is obtained by max-min optimization. Experimental results show that the YOLOv5-M3 network model achieves 92.2% mean average precision (mAP) for crop targets and the recognition speed is 39 frames per second (FPS). This method has the advantages of high detection accuracy, fast speed, and is light weight and has strong adaptability and anti-interference ability. It determines the relative position of maize seedlings and the weeding machine in real time, avoiding squeezing or damaging the seedlings. Full article

The performance and degradation of nonwoven mulches made from viscose, jute, hemp fibers, and their blends with PLA fibers, subjected to field conditions, are investigated. This research explores the possible substitution of traditional agricultural polyethylene mulching agro foil with environmentally friendly biodegradable nonwoven mulches produced from blends of jute, hemp, and viscose fibers along with PLA fibers. The nonwoven mulches underwent a ten-month exposure to field conditions, showing varied degradation. The jute and hemp nonwoven mulches degraded completely within the test period, whereas their blends with PLA fibers exhibited slowed degradation. This study indicated that PLA fibers in blends with jute, hemp, and viscose mulches slowed degradation, impacting their structural integrity and tensile properties. The tensile properties of nonwoven mulches blended with 20% of PLA fibers increased the breaking forces after field exposure. Observations on structural changes through microscopy highlighted the structure maintenance in jute and hemp blends due to the non-degraded PLA fibers, contrasting the complete degradation of 100% jute and hemp mulches. A microscopic analysis revealed alterations in the fiber structure and density changes, particularly in viscose mulches and their blends with PLA fibers. Soil temperature variations were observed under different mulches; e.g., agro foil consistently exhibited higher temperatures compared to nonwoven mulches. Notably, the hemp and jute/PLA blend mulches showed slightly elevated temperatures, while the viscose-based mulches consistently revealed the lowest temperatures. Regarding soil moisture, the nonwoven mulches generally maintained higher moisture levels compared to the control field and agro foil from June to October. These findings suggest that nonwoven mulches effectively preserved soil moisture during critical growth periods, potentially positively impacting plant growth. The weed suppression capabilities varied among mulches, with hemp mulch initially displaying the lowest suppression ability in the first six months. The addition of 20% of PLA fibers in mulch blends with viscose, jute, and hemp notably improved the weed control capabilities. Understanding the impacts of field conditions on newly produced nonwoven mulches is crucial for optimizing mulch selection in agricultural practices to enhance soil conditions and weed management. Full article

The ability of plants to release chemicals that affect the growth of other plants offers potential benefits for weed management and sustainable agriculture. This review explores the use of Camelina sativa as a promising cover crop with weed control potential. Camelina sativa, known for its high oil content and adaptability to diverse climatic conditions, exhibits allelopathic potential by releasing chemical compounds that inhibit weed growth. The crop’s vigorous growth and canopy architecture contribute to effective weed suppression, reducing the prevalence and spread of associated pathogens. Furthermore, the chemical compounds released by camelina through the solubilization of compounds from leaves by rain, root exudation, or deriving from microbial-mediated decay of camelina’s tissues interfere with the growth of neighbouring plants, indicating allelopathic interactions. The isolation and identification of benzylamine and glucosinolates as allelochemicals in camelina highlight their role in plant–plant interactions. However, the studies carried out on this species are outdated, and it cannot be excluded that other chemicals deriving from the breakdown of the glucosinolates or belonging to other classes of specialized metabolites can be involved in its allelopathic potential. Camelina sativa also demonstrates disease suppression capabilities, with glucosinolates exhibiting fungicidal, nematocidal, and bactericidal activities. Additionally, camelina cover crops have been found to reduce root diseases and enhance growth and yields in corn and soybeans. This review sheds light on the allelopathic and agronomic benefits of Camelina sativa, emphasizing its potential as a sustainable and integrated pest management strategy in agriculture. Full article

Screening suitable allelopathic crops and crop genotypes that are competitive with weeds can be a sustainable weed control strategy to reduce the massive use of herbicides. In this study, three accessions of common buckwheat Fagopyrum esculentum Moench. (Gema, Kora, and Eva) and one of Tartary buckwheat Fagopyrum tataricum Gaertn. (PI481671) were screened against the germination and growth of the herbicide-resistant weeds Lolium rigidum Gaud. and Portulaca oleracea L. The chemical profile of the four buckwheat accessions was characterised in their shoots, roots, and root exudates in order to know more about their ability to sustainably manage weeds and the relation of this ability with the polyphenol accumulation and exudation from buckwheat plants. Our results show that different buckwheat genotypes may have different capacities to produce and exude several types of specialized metabolites, which lead to a wide range of allelopathic and defence functions in the agroecosystem to sustainably manage the growing weeds in their vicinity. The ability of the different buckwheat accessions to suppress weeds was accession-dependent without differences between species, as the common (Eva, Gema, and Kora) and Tartary (PI481671) accessions did not show any species-dependent pattern in their ability to control the germination and growth of the target weeds. Finally, Gema appeared to be the most promising accession to be evaluated in organic farming due to its capacity to sustainably control target weeds while stimulating the root growth of buckwheat plants. Full article

Sustainable landscapes provide environmental, social, and financial benefits, with interest and adoption increasing due to environmental awareness. Ornamental ground-cover systems have garnered interest in the landscape due to the reduced need for water, fertilizers, pesticides, and maintenance compared to typical landscapes; however, limited research on groundcover ability to modulate soil conditions or suppress weeds exists. This study explored how ornamental groundcover systems impact the sustainability of landscapes. The effects of ground-cover growth habit (matting; bunching) and irrigation delivery method (micro spray; overhead) on soil temperature, volumetric water content (VWC), and electric conductivity (EC), along with impacts on weed growth, soil microbial communities, and plant coverage, were measured. Soil temperatures were generally lower under groundcover species with a matting growth habit, and to a lesser extent, bunching growth habits, in comparison to the warmer fallow systems. Groundcovers with a matting form led to lower VWC values compared to taxa with other growth habits, particularly when micro-irrigated. Plant form did not significantly influence EC values; however, micro spray irrigated plots had significantly higher EC values, likely attributed to irrigation spray patterns. Micro spray irrigation in tandem with matting growth habit taxa decreased weed density more effectively than taxa with bunching growth habits or groundcovers maintained under overhead irrigation. Selection of groundcover species with greater foliar coverage along with implementing more efficient irrigation practices can decrease soil temperatures, soil moisture, and weed density. Incorporating groundcovers in the landscape can decrease maintenance requirements and water/chemical use, thus increasing sustainability and decreasing environmental consequences. Full article