Search Results (434)

This study evaluated the effects of tillage and sowing systems on faba bean productivity and subsequent wheat yield under variable weather conditions in western Poland. A field experiment conducted in 2017–2019 compared four systems: conventional tillage with row sowing (CRS), conventional tillage with strip-drill sowing (SD-C), reduced tillage with strip-drill sowing (SD-R), and zero tillage with strip-drill sowing (SD-Z). Weather conditions varied markedly between years and were the main factor influencing yield formation. Faba bean seed yield declined from 6.3 t ha⁻¹ in 2017 to 1.0 t ha⁻¹ in 2019 due to reduced pod and seed numbers. Yield was strongly correlated with seeds per plant (r = 0.95), pods per plant (r = 0.86), and rainfall (r = 0.91). Strip-drill systems generally produced higher seed and protein yields than CRS, particularly under favorable moisture conditions, while protein content remained relatively stable. The establishment system of the preceding faba bean crop also affected subsequent wheat yield, with higher yields observed after strip-drill systems. Overall, weather conditions, especially water availability, were the primary drivers of productivity, whereas strip-drill systems improved crop performance and rotational benefits under variable climatic conditions. Full article

Interest in light detection and ranging (LiDAR) for the precise monitoring of vegetative growth of grain crops has increased. The study was conducted to estimate wheat size and plant distance using LiDAR and the convex hull method (CHM) compared to the voxel grid method (VGM). A commercial LiDAR system was used for data collection in the middle and late growth stages using static and dynamic scanning. A small number (ten) of data frames, consisting of a region of interest (ROI) of 1 m × 0.9 m for each frame, were selected as data samples. The data processing workflow consisted of data conversion, targeted data frame selection, visualization, region of interest (ROI) segmentation, outlier and untargeted point removal, downsampling, denoising, voxelization, preparation of the convex hull, and 3D PCD density map. To estimate the plant size and distance of wheat, the results obtained using CHM and VGM were compared with measured data results, and both methods were applied for the middle and late growth stages of wheat. The relative accuracy of LiDAR-estimated plant height, canopy volume, plant spacing, and row distances with respect to the measured results were 94%, 87%, 94%, and 87%, respectively, using CHM, and 76%, 72%, 62%, and 71% by VGM for static data scanning; for dynamic scanning, the estimated relative accuracy percentages were 87%, 91%, 94%, and 93%, respectively, using CHM, and 77%, 74%, 75%, and 74%, respectively, using VGM. The same methods were applied to the late growth stage data sets. Between the two methods, CHM provided higher accuracy for static and dynamic data-scanning approaches in the middle and late growth stages because the complex geometry of plants, thin and sparse leaf area, and structure complicated voxelization. Despite several challenges in PCD collection and processing, this study supports size and distance estimation for wheat and similar grains as non-destructive methods. Full article

Ball vegetables (such as cabbage, Chinese cabbage, broccoli, etc.) hold an important position in the vegetable industry due to their unique morphology and diverse applications and are widely favored by both consumers and the market. However, the harvesting of Ball vegetables poses significant challenges to agricultural production and market supply. Traditional manual harvesting struggles to meet the rapid demands of large-scale cultivation, primarily due to its high labor intensity and time-consuming nature, compounded by the increasingly prominent issues of aging and shortage of agricultural labor in recent years. As an alternative, intelligent harvesting robot technology, through integration with optimized cropping practices, innovations in preservation techniques, and improvements in processing workflows, offers an effective solution for expanding market planting areas and enhancing production efficiency. However, such harvesting robots still require further optimization and improvement in terms of adaptability, operational efficiency, and damage control. To systematically review the research progress and current status of this field, this study employs a bibliometric analysis approach to evaluate the current performance characteristics of various types of heading vegetable harvesting robots, aiming to provide a reference for future technological developments. This review analyzes solutions suitable for low-damage, high-quality harvesting of Ball vegetables in modern agriculture from five dimensions: identification and localization, row-following mechanisms, cutting mechanisms, pulling and conveying mechanisms, and leaf-removal mechanisms. It also summarizes the main challenges currently facing harvesting equipment, including the complexity of harvest targets, diversification of crop varieties and cultivation patterns, and harvest-induced damage to Ball vegetables. Finally, this review provides a future outlook on heading vegetable harvesting from four perspectives: research on the characteristics of Ball vegetables, investigation into harvest-induced damage mechanisms, improvement in machinery adaptability, and enhancement in equipment versatility and intelligence. Full article

The increasing demand for resilient and multifunctional crops in the Mediterranean region has renewed interest in Urtica dioica L. as a potential alternative crop. This study evaluated the combined effects of fertilization and row spacing on the growth, yield, and nitrogen use efficiency of nettle in Athens, Greece. A split-plot experimental design was employed in a three-year experiment, with three fertilization treatments (C = control, U = urea, and I = urea with urease inhibitor) and two different row spacings (D1 = 30 cm × 20 cm, and D2 = 50 cm × 20 cm). Agronomic traits, seed yield, nitrogen content, vegetation indices (NDVI), chlorophyll content (SPAD), and nitrogen efficiency indices were assessed. Fertilization significantly enhanced plant performance, with the application of I consistently producing the highest values for plant height (increased by 10–30%), biomass (increased by 10–20%), and seed yield (increased up to 30%) compared to C. Row spacing influenced crop performance, with D2 favoring plant height (up to 9% compared to D1), while D1 generally increased biomass production per unit area (up to 20% compared to D2). Nitrogen-related indices (NUE, NAE, and NUtE) were markedly improved under fertilized treatments, particularly when I was applied (up to 20%, 100%, and 19% compared to U). NDVI and SPAD values were also influenced by fertilization and row spacing at early growth stages. The findings demonstrate that both factors play critical roles in optimizing nettle cultivation under Mediterranean conditions, highlighting the importance of integrated agronomic management practices. Full article

The diagnosis of missing seedlings in high-density drill-seeded crops is often hindered by the strong coupling between visual perception and diagnostic rules, which leads to an irreversible cascade amplification of underlying missed detection errors. To address this dilemma, this paper proposes a “Perception–Topology” collaborative decoupling framework oriented toward row structure perception. In the perception phase, a row-structure-enhanced detection model (RS-YOLO) is constructed. It integrates Space-to-Depth (SPD) conversion, a Selective Frequency-domain Aggregation Module (SFAM), and a Row-Structure Attention Mechanism (RSM) to effectively suppress tire rut interference and explicitly reinforce the spatial topological priors of crops. In the diagnostic phase, an Adaptive Intra-row Gap Analysis (AIGA) algorithm is proposed. By utilizing a dynamic median intra-plant spacing scale and core canopy geometric pruning, this algorithm fundamentally reformulates missing seedling diagnosis into a physical interruption metric of one-dimensional graph connectivity. Evaluated on a finely reconstructed UAV-based sorghum imagery dataset, RS-YOLO achieved a significant improvement of 2.7% in precision and 3.2% in recall over the baseline model, providing a structure-aligned, high-confidence input for the diagnostic process. Based on this perceptual foundation, the AIGA algorithm ultimately achieved a diagnostic precision of 96.11% and a recall of 91.48% without the need for negative sample annotations. This framework effectively severs the propagation chain of perceptual errors, providing a noise-robust and highly physically interpretable new paradigm for the automated inspection of field population structures. Full article

The field inspection and ripeness detection of tomatoes in China remain heavily dependent on manual labor, while existing robotic solutions often exhibit limited functionality, poor environmental adaptability, prohibitive hardware costs, and unstable positioning accuracy. To address these limitations, this study proposes an intelligent tomato inspection robot that seamlessly integrates real-time ripeness recognition with precise spatial localization. Built upon a Raspberry Pi 5 core controller, the robot employs a lightweight, layered modular architecture designed to flexibly navigate complex agricultural environments. A comprehensive, multi-dimensional image dataset of tomato ripeness was constructed to train a three-category detection model based on the YOLOv8n architecture. Following 413 training epochs, the model demonstrated exceptional performance, achieving an overall mAP@0.5 of 87.8% and an mAP@0.5:0.95 of 72.7% on the held-out test dataset. In field inspections, the system achieved detection precisions of 82.22% for immature tomatoes, 92.66% for half-ripened tomatoes, and 100% for fully ripe tomatoes, successfully identifying all ripe tomatoes and satisfying the practical demands of field inspection. Furthermore, the integration of an Ultra-Wideband positioning system yielded an overall Root Mean Square Error of 0.231 m, successfully confining positioning errors to within 0.24 m to fully satisfy the stringent localization demands of crop-level inspection. Field evaluations confirmed that under optimal configurations, the robot can efficiently inspect a 50-m planting row in 10 min (±1 min) and maintains a continuous operational battery life of 2 h (±10 min). The core contribution of this work is the system-level integration and optimization of technologies for greenhouse agriculture. This integrated design achieves low hardware cost and high deployment flexibility, addressing longstanding challenges of labor-intensive inspection and delayed harvesting, and delivering a practical solution for intelligent tomato plantation management. Full article

Real-time and accurate crop row extraction is a fundamental requirement for vision-based perception in autonomous agricultural machinery. In maize fields, however, row detection is easily affected by variable illumination, leaf occlusion, weed interference, and uneven soil backgrounds, which can reduce the reliability of both GNSS- and image-based navigation methods. To address these challenges, this study proposes a plant-oriented crop row perception framework that reconstructs row structures from individual maize plant detections. A lightweight detection model, named Maize–YOLO, was developed based on YOLOv11n for maize seedling detection. Three key improvements were introduced to enhance the balance between accuracy and efficiency. First, the C3k2_Faster_CGLU module replaces the original C3k2 block to reduce redundant convolutional computation while improving selective feature representation through convolutional gated linear units, thereby enhancing robustness under complex field backgrounds. Second, a lightweight shared detection head, Detect_LSH, was designed to share convolutional parameters across multi-scale feature maps and adaptively adjust feature amplitudes, reducing detection-head redundancy while maintaining multi-scale prediction capability. Third, a Layer-Adaptive Magnitude-Based Pruning strategy was applied to remove low-contribution channels and further improve computational efficiency for CPU-based deployment. Experimental results on field-collected maize seedling images showed that Maize–YOLO achieved an mAP@0.5 of 97.6%, reduced GFLOPs by 61.9%, and maintained a CPU inference speed of 84.4 FPS. After plant detection, row centerlines were estimated using an IPM–DBSCAN–LSM pipeline, which transformed detected plant centers into a quasi-top-view space, clustered them into crop rows, and fitted continuous centerlines. The extracted crop rows reached a positional accuracy of 98.6%, with a mean angular deviation of 0.44°. These results demonstrate that the proposed method can provide accurate, lightweight, and real-time crop row perception for autonomous agricultural navigation and precision field operations. Full article

To solve the problems of low seeding precision and the poor operational adaptability of traditional no-till seeders under dense planting mode, and meet the agronomic requirements for high maize yield, this study carried out optimization and experimental research on the no-till precision fertilizer-seed co-sowing system for maize with wide-narrow row dense planting, relying on the experimental base of the Science and Technology Courtyard for Super High-Yield Cropping Systems in Qihe, China Agricultural University. Through modular integration and the optimization of key components, precise row spacing adjustment and improved sowing depth consistency in complex plots were achieved. A tractor-implement integrated a kinematic model and a dynamic model of the seed metering tube, which were constructed to quantify the correlation between operational parameters and motion states, providing theoretical support for structural parameter optimization. Field tests showed that all operational quality indicators of the system met the local high-yield requirements for no-till dense planting; the comprehensive performance was optimal at a density of 75,000 plants·ha⁻¹, with the best seeding uniformity (coefficient of variation: 5.65%), seedling emergence and seedling uniformity, which is well adapted to the agronomic characteristics of the wheat–maize rotation areas in the Huang-Huai-Hai Plain. Subsequent optimization by reducing the operating speed and increasing the spring stiffness can further improve the operational quality, realize the deep integration of agronomy and agricultural machinery, provide agricultural machinery support for high-yield and high-quality maize cultivation, and is of great significance for improving agricultural production efficiency and resource utilization. Full article

Quinoa is a highly nutritious Andean crop with considerable yield potential that remains underexploited in southern Ecuador. This study evaluated the effects of planting method (row seeding, hill seeding, and transplanting) and plant density (8–20 plants m⁻²) on quinoa growth and yield under Andean highland conditions. A factorial field experiment was conducted using a randomized complete block design with three replicates. Plant density significantly affected grain yield, increasing from 4.4 to 4.8 t ha⁻¹ at 8 plants m⁻² to a maximum of 6.97 t ha⁻¹ at 20 plants m⁻². This increase was mainly driven by a higher grain number per unit area, while thousand-grain weight remained stable across treatments. In contrast, the planting method and its interaction with plant density had no significant effect on yield or yield components. Grain yield showed a strong positive relationship with above-ground biomass, indicating that biomass accumulation was the main driver of yield variation. These results demonstrate that plant density is the primary agronomic factor controlling quinoa productivity under Andean conditions. Optimizing plant density to 15–20 plants m⁻² is recommended as a simple and cost-effective management strategy to maximize grain yield, regardless of planting method. Full article

Peanut planting presents unique challenges due to the large, fragile, and irregular seed and the sensitivity of seed metering systems to operating conditions. Field experiments were conducted between 2022 and 2025 in Georgia to evaluate how planting speed, row-unit downforce, vacuum setting, and planter platform influence peanut stand establishment, final within-row plant distribution, and yield in single-row planting systems. Trials included speed × downforce evaluations using an electric seed meter and planter-platform × speed × planter-specific vacuum comparisons involving ground-driven, hydraulic-driven, and electric-driven seed meters. Achieved population was determined from post-emergence stand counts, plant distribution was evaluated using emerged-plant position classification relative to theoretical plant spacing, and yield was measured at harvest. Across site years, achieved population patterns were consistently associated with planting speed and vacuum setting, whereas downforce effects were minor and inconsistent within site years. Higher achieved populations were generally obtained at 5 km h⁻¹ and at higher planter-specific vacuum settings, especially for the ground-driven planter. Hydraulic- and electric-driven planter platforms were less sensitive to changes in speed and vacuum and more often maintained acceptable stands at 8 km h⁻¹. Despite large differences in achieved population and plant distribution, peanut yield was often not significantly reduced until stand loss became severe, indicating substantial yield compensation. Spacing uniformity remained poor across all treatments, with skips and long skips common regardless of planter platform. These results indicate that peanut planting performance in current single-row systems is constrained primarily by seed singulation rather than downforce, and that hydraulic- and electric-driven planter platforms improve operational flexibility more consistently than yield. Full article

Cotton planting efficiency is increasingly constrained by narrow planting windows, motivating interest in higher operating speeds if stand establishment and seed placement accuracy can be maintained. Field experiments were conducted in Georgia between 2020 and 2025 to quantify the effects of planter operating parameters and system configurations on cotton planter performance. Trials evaluated combinations of planting speed, row-unit downforce, seed plate type (singulated vs. hill-drop), and seed delivery system using conventional gravity-tube planters and two high-speed planter systems equipped with advanced delivery systems. The achieved population was determined from stand counts, planting quality was assessed using plant position classification relative to theoretical plant spacing, and lint yield was measured at harvest. Across site-years, the achieved population was generally not affected by planting speed or downforce within the tested ranges. With conventional gravity-tube delivery systems, the proportion of perfectly spaced plants declined from 44.0% to 22.1% in 2020 and from 52.8% to 28.4% in 2021 as planting speed increased from 5 to 11 km ${\mathrm{h}}^{-1}$. In contrast, across the advanced planter systems evaluated in 2025, mean perfect spacing remained within a narrow range of 45.8% to 49.5% across 8 to 14 km ${\mathrm{h}}^{-1}$. Hill-drop seed plates increased the achieved population relative to singulated plates in the seed plate × downforce trials, increasing mean achieved population from 79.6 to 87.8 thousand plants h${\mathrm{a}}^{-1}$ at Midville and from 62.2 to 73.1 thousand plants h${\mathrm{a}}^{-1}$ at Plains in 2022, and from 45.4 to 58.1 thousand plants h${\mathrm{a}}^{-1}$ at Midville in 2024, but these increases did not result in consistent lint yield differences. The high-speed hill-drop configuration evaluated in 2025 did not consistently produce plant pairs meeting the hill-drop spacing criterion. These results indicate that current high-speed planter systems can be used for singulated cotton to increase planting productivity while maintaining placement accuracy, although additional research is needed to determine the environmental and management conditions under which spacing improvements translate into yield benefits. Full article

This study investigated how fertilization regimes and ridge furrow planting patterns influence the soil nutrient conditions and microbial taxonomic composition and function in the rhizosphere of spring maize in Northeast China. Three treatments were compared: CK (compound fertilizer, small ridge), KF (formula fertilization, small ridge), and BMP (formula fertilization, large double-row ridge). High-throughput sequencing was used to characterize the soil bacterial and fungal community composition and diversity. The results showed that the combination of formula fertilizer and wide-ridge cultivation synergistically improved soil physicochemical properties and significantly increased maize yield (p < 0.05). Compared with CK, both BMP and KF significantly improved the composition and diversity of microbial communities. Notably, the BMP treatment increased the relative abundances of Ascomycota and Basidiomycota—key decomposers of soil organic matter, lignin, and cellulose—which suggested enhanced nutrient cycling potential under this integrated management practice. Among the three treatments, BMP (N:P₂O₅:K₂O = 1:2:1, 130 cm wide-ridge double-row planting) achieved the highest maize yield (859 ± 14 kg ha⁻¹), representing an 11.0% increase over conventional practices (CK, 774 ± 13 kg ha⁻¹). We propose that integrating optimized fertilization with ridge configuration is an effective strategy for improving soil quality, microbial functionality, and crop productivity in Northeast China’s black soil region. Full article

Soil compaction and reduced infiltration capacity are critical constraints limiting soil physical quality and hydraulic functioning in semi-arid vineyard systems subjected to repeated machinery traffic. This study aimed to develop and evaluate a geometry-optimized strip tillage tool designed to improve structural functionality within the compacted root zone while minimizing inter-row disturbance. A U-shaped working body configuration, consisting of two oppositely inclined shanks and a central chisel, was theoretically substantiated and optimized using multifactor analysis. Field experiments were conducted to assess changes in penetration resistance, bulk density, and infiltration rate within the 20–40 cm soil layer under semi-arid conditions. The optimized geometry significantly reduced penetration resistance and bulk density in the trafficked strip, indicating alleviation of mechanical impedance and improved root-relevant physical conditions. Infiltration capacity increased after treatment, indicating enhanced hydraulic continuity within the root zone. Unlike full-width subsoiling, the localized strip intervention preserved inter-row soil stability and limited unnecessary disturbance, which is consistent with conservation-oriented soil management. The results indicate that geometry-optimized strip tillage is associated with improved soil physical quality and hydraulic function within compacted vineyard strips. The operational applicability of the developed implement may also depend on vineyard layout and terrain conditions. The prototype tool was tested under conditions representative of vineyards with standard row spacing and relatively moderate slopes typical for the experimental site. In vineyards with very narrow row spacing, steep slopes, or highly heterogeneous soil conditions, adjustments in working width, shank spacing, or tractor–implement configuration may be required. Future studies should therefore investigate the performance of the optimized geometry under contrasting vineyard configurations, including steep hillside vineyards and high-density planting systems. By linking implement design to quantitative soil structural and hydraulic indicators, this study contributes to the development of vineyard soil management practices for semi-arid perennial cropping systems. Full article

Barley remains the fourth most cultivated cereal crop worldwide and is valued for its versatility in malting and brewing, animal feed, human nutrition, and dietary supplements. The identification of genotypes suitable for breeding or specific end-use applications requires multi-environment testing to evaluate agronomic performance, grain quality, and trait stability. In this study, a panel of 50 winter barley genotypes (two-row and six-row) originating from diverse genetic backgrounds was evaluated over three growing seasons (2021–2023) under the environmental conditions of southeastern Romania. Seven traits were analyzed, including three phenological traits (heading time, flowering time and plant height), grain yield, and three quality parameters (thousand-grain weight, protein content, and starch content). Environmental conditions had a strong influence on phenological development and grain yield, whereas grain quality traits showed relatively greater stability, indicating a stronger genetic control. Multivariate analyses (Principal Component Analysis (PCA) and Genotype plus Genotype-by-Environment interaction biplot (GGE biplots)) revealed clear relationships among traits and highlighted contrasting adaptive strategies between the two barley types. In two-row barley, genotypes such as Idra and Sandra combined favorable yield performance with stable grain quality traits and therefore represent promising candidates for breeding programs and large-scale cultivation. In six-row barley, SU-Ellen and LG Zebra showed high productivity and strong starch accumulation, making them valuable genetic resources for yield-oriented breeding, although further improvement in nitrogen use efficiency may be beneficial. The 2022–2023 growing season represented the most restrictive environment, emphasizing the importance of stability under stress conditions. Genotypes located close to the Average Environment Coordination axis (AEC axis) during that season, such as Ametist (six-row) and Lardeya (two-row), may represent promising material for breeding programs targeting drought resilience. Overall, the results expand the phenotypic characterization of winter barley germplasm and identify valuable genetic resources that can support pre-breeding efforts and the development of climate-resilient barley cultivars. Full article

Unmanned aerial systems (UASs) and artificial intelligence (AI) allow for the effective monitoring of the plants, but it is difficult to determine the stages of cotton development in the process of irrigation gradients. In this paper, UAS images were combined with deep learning to conduct field-scale cotton phenology classification in graded drought situations. SegNet, U-Net, and DeepLabv3+ were trained on various sample sizes and tested on global accuracy (GA), mean intersection-over-union (mIoU), and mean boundary F-score (mBF). It was found that DeepLabv3+ outperformed all other methods and yielded the most uniform delineation of crop row spacing, canopy edges, and boll opening boundaries throughout the entire growing season. Under single-stage training, performance became stable at training sample sizes ≥ 960 for the seedling and squaring stages, whereas the boll and boll-opening stages required ≥ 1280; for full-season training, performance became stable when the sample size reached 4480 (GA = 0.98, mIoU = 0.95, mBF = 0.81). Cross-treatment evaluation indicated that errors were mainly concentrated between adjacent stages, with higher confusion under the 0% irrigation treatment and more stable identification results under the 90% irrigation treatment. A DAP 138 field survey (36 points) confirmed an irrigation-gradient phenological shift from boll-opening dominance at 0% irrigation to universal boll at 90% irrigation, consistent with spatial phenology maps. Overall, the proposed framework provides a cost-effective, field-scale solution to support precision irrigation management in arid cotton-growing regions. Full article