Mechanical weeding is an important technical means for organic and regenerative agricultural systems. Current weed control equipment has a variety of problems, such as difficulty adapting to ...high-stalk crops and poor operational quality. A high-clearance mid-tillage weeder (HMTW) has been developed to meet the mechanical weed control needs of high-stalk crops. The weeder mainly comprises a suspension device, a frame, parallel four-rod profiling mechanisms, weeding operation components, and depth-limiting soil-cutting devices. Based on the agronomic requirements of dryland flat planting, the overall structure of the HMTW was determined, and the weeding unit and flat shovel hoe were designed. Theoretical analysis was conducted on the depth stability of the HMTW, and an optimization mathematical model of the HMTW was established to further improve its tillage depth stability for agronomic requirements. The optimization objective was to minimize the deflection angle (∆β) of the profiling rod on a vertical plane, and the parameters of the parallel four-rod profiling mechanism were optimized. Based on the optimized structural parameters, a prototype of the HMTW was developed and evaluated. The test results show that the optimized HMTW exhibited a good weeding effect, and the tillage depth stability was within the design operating range. When the driving speed was 1.0 m/s and the tillage depth was 8 cm, the weed removal rate, seedling injury rate, seedling burial rate, and qualified rate of tillage depth were 90.8%, 3.2%, 4.1%, and 94%, respectively. The proposed HMTW successfully meets the weeding agronomic requirements of high-stalk crops for dryland farming, and the performance analysis and optimization models provide technical references for the design and development of such structures.
•Efficient branch-level transfer learning integrates features across dual-branch tasks.•End-to-end plant counting network, integrating a counting head with YOLOv5s backbone, enhances counting ...performance.•Attention mechanism aids not only in feature reduction and extraction, but also in feature redistribution.•TasselNetV2++ leverages dual-branch architecture, enhanced by branch-level transfer learning, YOLOv5s backbone, attention mechanism, and multilayer fusion.•TasselNetV2++ demonstrates robust adaptability to diverse crop scenarios and data collection techniques.
Plant counting plays an important role in evaluating planter effectiveness, assessing seed quality, devising agricultural management plans, and estimating crop yields. Given its significance and the ease of acquiring agricultural images, the development of an end-to-end image-based plant counting model applicable across diverse agricultural settings is crucial. The proposed TasselNetV2++, an improved version of TasselNetV2+ for plant counting, introduces notable enhancements to its encoder and counter while maintaining the existing normalizer. In the encoder, we designed a dual-branch architecture, with one branch being a customized YOLOv5s backbone and the other branch being the original encoder equipped with an attention mechanism. It is precisely the branch-level transfer learning, coupled with multilayer fusion, within the dual-branch architecture that significantly enhances the feature extraction capability of the network across a wide range of scenarios. Moreover, the counter has been enhanced with an attention mechanism that recalibrates its focus on crucial spatial locations and channel-wise features following average pooling. Experimental results demonstrate that TasselNetV2++ outperforms its predecessor across multiple counting tasks. Compared to TasselNetV2+, TasselNetV2++ achieves a substantial reduction in relative root mean squared error (rRMSE). Specifically, it brings a 33.3% relative decrease of rRMSE on the soybean seedlings counting dataset, 8.4% on the wheat ears detection dataset, 28.6% on the maize tassels counting dataset, and 18.0% on the sorghum heads counting dataset. Notably, ablation experiment demonstrates the indispensability of the branch-level transfer learning in achieving precise plant counting. Branch-level transfer learning achieves a notable relative decrease in rRMSE of 31.4% for soybean seedlings, 7.9% for wheat tassels, 36.5% for maize tassels, and 2.0% for sorghum heads. The proposed TasselNetV2++ attains remarkable advancements and introduces a straightforward yet highly effective branch-level transfer learning strategy.
Precision agriculture technology has become a crucial means of improving the quality of crop production. As an emerging technology in farmland management, intelligent weeding robots utilize ...intelligent spraying systems to effectively manage weeds, adjusting the types and dosages of herbicides in a timely manner. The accuracy and real-time performance of weed identification algorithms are the keys to intelligent weeding. This study established a proprietary dataset comprising 6690 images of soybean seedlings and weeds and proposed an improved lightweight algorithm, YOLOv8-ECFS. Based on YOLOv8s, this model introduces the EfficientNet network to improve feature extraction capability and accelerate the inference speed, replacing the CIoU loss with Focal_SIoU to optimize the regression accuracy of the bounding boxes. Furthermore, the coordinate attention module is introduced into the neck to enable the model to precisely capture textural and color differences between various weeds and soybean crops, thereby ensuring precise identification of multiple weed species. The results demonstrate that YOLOv8-ECFS achieves precision, mAP, and F1 values of 92.2%, 95.0%, and 90.9%, representing an increase of 2.5%, 1.3%, and 1.6%, respectively, compared to YOLOv8s. Simultaneously, the model's GFLOPs and model size have been reduced by 11.1G and 9.1 MB, respectively, ensuring both recognition accuracy and lightweight performance. The test set results show that YOLOv8-ECFS accurately identifies densely growing and mutually occluding weeds, reducing cases of false positives and missed detections. Compared to other mainstream YOLO algorithms, YOLOv8-ECFS demonstrates the best overall performance, thus providing support for intelligent weeding robots in farmland management and unmanned farms.
•A complex dataset containing soybeans and weeds was created.•Proposed YOLOv8-ECFS lightweight weed identification model.•Achieved accurate identification and classification of different weeds.
Increasing the maize planting density is considered a potential approach for increasing the grain yield in China, but there is no consensus regarding its yield-increasing effect and the influence of ...specific factors. Thus, we established a database (2721 pairs of data from 187 publications) to quantify the effects of increasing the maize planting density on the phenotypic traits and yield, to determine an appropriate maize planting density for each planting area, and to quantify the effects of environmental factors and agricultural imputs on the outcomes of increasing the planting density. We found that increasing the planting density increased the individual competition among maize plants, with negative effects on their growth, but the grain yield increased by 11.18–13.43 % due to the increased population biomass. Using the database, we found large differences in the optimal density and peak grain yield among maize planting areas, and the factors that caused these differences were analyzed based on subgroup analysis. Field management practices significantly influenced the outcomes of increasing the planting density. In particular, higher agricultural inputs (irrigation amount, and nitrogen and phosphorus application rates) enhanced the positive effect of increasing plant density on the optimal plant density and peak grain yield. In addition, the effects of increasing the planting density were significantly influenced by environmental (climate and soil) factors. When the mean annual temperature was 7–14°C and the mean annual precipitation was 400–800 mm, the yield and maximum peak yield were highest in relatively fertile (high total nitrogen, available nitrogen, and soil organic matter contents) and neutral (pH 6–8) soils. Our results highlight the need to increase the current maize planting density and provide a scientific basis for determining reasonable planting densities for different maize growing areas in China.
Display omitted
•It is necessary to increase the maize planting density (PD) in China.•Increasing planting density significantly increased maize grain yield.•There were differences in the optimal planting density among maize growing-areas.•The effects of increasing the PD were influenced by environmental factors.
Cell death plays an important role in host-pathogen interactions. Crystal proteins (toxins) are essential components of Bacillus thuringiensis (Bt) biological pesticides because of their specific ...toxicity against insects and nematodes. However, the mode of action by which crystal toxins to induce cell death is not completely understood. Here we show that crystal toxin triggers cell death by necrosis signaling pathway using crystal toxin Cry6Aa-Caenorhabditis elegans toxin-host interaction system, which involves an increase in concentrations of cytoplasmic calcium, lysosomal lyses, uptake of propidium iodide, and burst of death fluorescence. We find that a deficiency in the necrosis pathway confers tolerance to Cry6Aa toxin. Intriguingly, the necrosis pathway is specifically triggered by Cry6Aa, not by Cry5Ba, whose amino acid sequence is different from that of Cry6Aa. Furthermore, Cry6Aa-induced necrosis pathway requires aspartic protease (ASP-1). In addition, ASP-1 protects Cry6Aa from over-degradation in C. elegans. This is the first demonstration that deficiency in necrosis pathway confers tolerance to Bt crystal protein, and that Cry6A triggers necrosis represents a newly added necrosis paradigm in the C. elegans. Understanding this model could lead to new strategies for nematode control.
Cell death plays an important role in host-pathogen interactions. Crystal proteins (toxins) are essential components of Bacillus thuringiensis (Bt) biological pesticides because of their specific ...toxicity against insects and nematodes. However, the mode of action by which crystal toxins to induce cell death is not completely understood. Here we show that crystal toxin triggers cell death by necrosis signaling pathway using crystal toxin Cry6Aa-Caenorhabditis elegans toxin-host interaction system, which involves an increase in concentrations of cytoplasmic calcium, lysosomal lyses, uptake of propidium iodide, and burst of death fluorescence. We find that a deficiency in the necrosis pathway confers tolerance to Cry6Aa toxin. Intriguingly, the necrosis pathway is specifically triggered by Cry6Aa, not by Cry5Ba, whose amino acid sequence is different from that of Cry6Aa. Furthermore, Cry6Aa-induced necrosis pathway requires aspartic protease (ASP-1). In addition, ASP-1 protects Cry6Aa from over-degradation in C. elegans. This is the first demonstration that deficiency in necrosis pathway confers tolerance to Bt crystal protein, and that Cry6A triggers necrosis represents a newly added necrosis paradigm in the C. elegans. Understanding this model could lead to new strategies for nematode control.