Recent contributions of molecular population genetic and phylogenetic studies to classic biological control of weeds

Gaskin, John

doi:10.1007/s10526-023-10230-5

Cited by 4 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current main weeding control methods include biological weeding, chemical weeding, traditional mechanical weeding and targeted weeding [1][2][3]. Biological weeding involves introducing foreign organisms to suppress weed growth, but these organisms can threaten local ecosystems [4]; Extensive application of herbicides plays a crucial role in controlling weeds and boosting agricultural efficiency, yet, this extensive application can induce resistance in weeds and significantly affect soil, biota, and human health [5]; Traditional mechanical weeding is effective pre-emergence but post-emergence inaccuracy can irreversibly damage crops; Targeted weeding technology, which focuses on the specific locations of weeds, has gradually become a focal point in the era of precision agriculture and Agriculture 4.0 [6].…”

Section: Introductionmentioning

confidence: 99%

Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Lyu,

Lu,

2024

Preprint

View full text Add to dashboard Cite

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, suitable for complex vegetable field environments and resource-limited laser weeding devices.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Lyu,

Lu,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Current main weeding control methods include biological weeding, chemical weeding, traditional mechanical weeding, and targeted weeding [1][2][3]. Biological weeding involves introducing foreign organisms to suppress weed growth, but these organisms can threaten local ecosystems [4]. Extensive application of herbicides plays a crucial role in controlling weeds and boosting agricultural efficiency, yet, this extensive application can induce resistance in weeds and significantly affect soil, biota, and human health [5].…”

Section: Introductionmentioning

confidence: 99%

Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Lyu,

Lu,

2024

Applied Sciences

View full text Add to dashboard Cite

Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8 MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, and is suitable for complex vegetable field environments and resource-limited laser weeding devices.

show abstract

Traits of insect herbivores and target weeds associated with greater biological weed control establishment and impact

Panta,

Schwarzländer,

Weyl

et al. 2024

BioControl

View full text Add to dashboard Cite

Improving success rates of classical weed biocontrol programs is an ongoing effort that requires a variety of different approaches. Previous assessments indicated biocontrol agent taxonomy and feeding characteristics and weed life history traits are associated with better control outcomes. We examined weed biocontrol releases for correlations between biocontrol agent and target weed traits associated with different levels of reported establishment and control. Data collated in the 5th edition of ‘Biological Control of Weeds: A World Catalogue of Agents and Their Target Weeds’ were used as the basis for this global analysis. Published literature was used to augment the catalog with data for eight biocontrol agent traits and four target weed traits. Biocontrol agent establishment and impact data were analyzed against these traits using generalized linear mixed models and categorical models, respectively. Analyses for biocontrol agent establishment reveal the following agent traits were correlated with a greater probability of establishment: being an internal feeder, feeding on above-ground plant tissues, multivoltine agents and agents that feed during both their adult and immature life stages. Insect taxon did not affect establishment except for the order Lepidoptera, which had the lowest establishment probability. For weed traits, those occurring in aquatic or riparian habitats were associated with a higher probability of biocontrol agent establishment. Regarding agent impact, using the definition categories in the catalog, agents feeding externally and on vegetative plant tissues, multivoltine agents and those with both adult and immature plant-feeding life stages were strongly correlated with greater impact. Perennials, reproducing only vegetatively and invading aquatic or riparian habitats were associated with greater biocontrol impact. Our findings could facilitate both the prioritization of invasive plants targeted for biocontrol and the selection of suitable biocontrol agent candidates, which should further improve biocontrol project outcomes.

show abstract

Recent contributions of molecular population genetic and phylogenetic studies to classic biological control of weeds

Cited by 4 publications

References 51 publications

Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Improved YOLOv8-seg Based on Multi-scale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation

Traits of insect herbivores and target weeds associated with greater biological weed control establishment and impact

Contact Info

Product

Resources

About