Search Results (268)

Rice lodging severely affects crop growth, yield, and mechanized harvesting efficiency. The accurate detection and quantification of lodging areas are crucial for precision agriculture and timely field management. However, Unmanned Aerial Vehicle (UAV)-based lodging detection faces challenges such as complex backgrounds, variable lighting, and irregular lodging patterns. To address these issues, this study proposes SWRD–YOLO, a lightweight instance segmentation model that enhances feature extraction and fusion using advanced convolution and attention mechanisms. The model employs an optimized loss function to improve localization accuracy, achieving precise lodging area segmentation. Additionally, a grid-based lodging ratio estimation method is introduced, dividing images into fixed-size grids to calculate local lodging proportions and aggregate them for robust overall severity assessment. Evaluated on a self-built rice lodging dataset, the model achieves 94.8% precision, 88.2% recall, 93.3% mAP@0.5, and 91.4% F1 score, with real-time inference at 16.15 FPS on an embedded NVIDIA Jetson Orin NX device. Compared to the baseline YOLOv8n-seg, precision, recall, mAP@0.5, and F1 score improved by 8.2%, 16.5%, 12.8%, and 12.8%, respectively. These results confirm the model’s effectiveness and potential for deployment in intelligent crop monitoring and sustainable agriculture. Full article

In a greenhouse environment, the application of artificial intelligence technology for selective tomato harvesting still faces numerous challenges, including varying lighting, background interference, and indistinct fruit surface features. This study proposes an improved instance segmentation model called FGS-YOLOv8s-seg, which achieves accurate detection and maturity grading of tomatoes in greenhouse environments. The model incorporates a novel SegNext_Attention mechanism at the end of the backbone, while simultaneously replacing Bottleneck structures in the neck layer with FasterNet blocks and integrating Gaussian Context Transformer modules to form a lightweight C2f_FasterNet_GCT structure. Experiments show that this model performs significantly better than mainstream segmentation models in core indicators such as precision (86.9%), recall (76.3%), average precision (mAP_@0.5 84.8%), F1-score (81.3%), and GFLOPs (35.6 M). Compared with the YOLOv8s-seg baseline model, these metrics show improvements of 2.6%, 3.8%, 5.1%, 3.3%, and 6.8 M, respectively. Ablation experiments demonstrate that the improved architecture contributes significantly to performance gains, with combined improvements yielding optimal results. The analysis of detection performance videos under different cultivation patterns demonstrates the generalizability of the improved model in complex environments, achieving an optimal balance between detection accuracy (86.9%) and inference speed (53.2 fps). This study provides a reliable technical solution for the selective harvesting of greenhouse tomatoes. Full article

Topping is an essential step in cotton cultivation in Xinjiang, China, which can effectively increase the number of bolls per plant and optimize the yield and quality. Paclobutrazol, as a common chemical topping agent for cotton, faces challenges such as unstable topping effect and limited leaf surface absorption during application. In this study, paclobutrazol was used as the ligand and a zinc complex was synthesized by the thermosolvent method to replace paclobutrazol and improve the topping effect on cotton. The structure of the complex was characterized using FTIR, UV-vis, TG, and XRD analyses. The results confirmed that each zinc ion coordinated with four nitrogen atoms from the triazole rings of paclobutrazol and two oxygen atoms from nitrate ions, forming an octahedral geometry. Surface tension measurement and analysis revealed that the complex had a surface tension reduction of 12.75 mN/m compared to paclobutrazol, thereby enhancing the surface activity of the complex in water systems and improving its absorption efficiency on plant leaves. Two-year field trials indicated that the foliar application of the complex at a dosage of 120 g·hm⁻² in inhibiting cotton plant height was more stable to that of paclobutrazol or mepiquat chloride. It also shortened the length of fruiting branches, making the shape of cotton plants compact, thereby indirectly improving the ventilation and light penetration of the cotton field and the convenience of mechanical harvesting. Yield data showed that, compared with artificial topping, the complex at a dosage of 120 g·hm⁻² treatment increased cotton yield by approximately 4.6%. Therefore, the paclobutrazol–zinc complex is a promising alternative to manual topping and have great application potential in future mechanized cotton production. Full article

Color, aroma, and overall sensory quality in red wines are largely influenced by oxygen availability during fermentation. This study evaluated the effects of micro-oxygenation under hyperbaric conditions on the physicochemical, chromatic, volatile, and sensory properties of Vitis vinifera L. cv. Monastrell grape must. Grape clusters were manually harvested and fermented under controlled conditions, applying micro-oxygenation treatments at two fermentation stages (day 3 and day 13) within a hyperbaric chamber. Physicochemical analyses, CIELab color measurements, visible reflectance spectra, GC-FID volatile profiling, and descriptive sensory analysis were performed. Micro-oxygenated samples (M1_MOX and M2_MOX) showed significant increases in lightness (L*), redness (a*), chroma (C*), and reflectance in the 520–620 nm range, indicating enhanced extraction and stabilization of phenolic pigments. Volatile analysis revealed that these samples also contained higher concentrations of key esters and terpenes associated with fruity and floral notes. Sensory evaluation confirmed these findings, with MOX-treated wines displaying greater aromatic intensity, flavor persistence, and varietal character. Control samples (M1_CON and M2_CON) exhibited lower color saturation and volatile compound content, along with diminished sensory quality. These results suggest that hyperbaric micro-oxygenation is an effective strategy for improving color intensity and aromatic complexity during red wine fermentation under controlled, non-thermal conditions. Full article

Tomato ripeness detection in open-field environments is challenged by dense planting, heavy occlusion, and complex lighting conditions. Existing methods mainly rely on color and texture cues, limiting boundary perception and causing redundant predictions in crowded scenes. To address these issues, we propose an improved detection framework called Edge-Guided DETR (EG-DETR), based on the DEtection TRansformer (DETR). EG-DETR introduces edge prior information by extracting multi-scale edge features through an edge backbone network. These features are fused in the transformer decoder to guide queries toward foreground regions, which improves detection under occlusion. We further design a redundant box suppression strategy to reduce duplicate predictions caused by clustered fruits. We evaluated our method on a multimodal tomato dataset that included varied lighting conditions such as natural light, artificial light, low light, and sodium yellow light. Our experimental results show that EG-DETR achieves an $AP$ of 83.7% under challenging lighting and occlusion, outperforming existing models. This work provides a reliable intelligent sensing solution for automated harvesting in smart agriculture. Full article

The transition toward sustainable and decentralized energy solutions necessitates the development of innovative bioelectronic systems capable of harvesting and converting renewable energy. Here, we present a novel photo-bioelectrochemical fuel cell architecture based on a biohybrid anode integrating laser-induced graphene (LIG), poly(3,4-ethylenedioxythiophene) (PEDOT), and isolated thylakoid membranes. LIG provided a porous, conductive scaffold, while PEDOT enhanced electrode compatibility, electrical conductivity, and operational stability. Compared to MXene-based systems that involve complex, multi-step synthesis, PEDOT offers a cost-effective and scalable alternative for bioelectrode fabrication. Thylakoid membranes were immobilized onto the PEDOT-modified LIG surface to enable light-driven electron generation. Electrochemical characterization revealed enhanced redox activity following PEDOT modification and stable photocurrent generation under light illumination, achieving a photocurrent density of approximately 18 µA cm⁻². The assembled photo-bioelectrochemical fuel cell employing a gas diffusion platinum cathode demonstrated an open-circuit voltage of 0.57 V and a peak power density of 36 µW cm⁻² in 0.1 M citrate buffer (pH 5.5) under light conditions. Furthermore, the integration of a charge pump circuit successfully boosted the harvested voltage to drive a low-power light-emitting diode, showcasing the practical viability of the system. This work highlights the potential of combining biological photosystems with conductive nanomaterials for the development of self-powered, light-driven bioelectronic devices. Full article

In this study, the functions of the photosynthetic machinery were evaluated using chlorophyll a fluorescence technique (PAM and JIP test) in pea plants (Pisum sativum L. cv Borec) and its LHC II oligomerization variants (mutants Costata 2/133 and Coeruleovireus 2/16). The oligomeric forms of LHCII increased in the following order: Costata 2/133 < Borec wt < Coeruleovireus 2/16. Data revealed that the mutant with higher LHCII oligomerization (Coeruleovireus 2/16) at low light intensity (LL, 150 µmol photons/m²·s) exhibited the following: (i) decreased energy dissipation and increased electron transport efficiency; (ii) higher reaction center density; (iii) increased amounts of the open reaction centers (qp) and their excitation efficiency (Φexc); and (iv) influenced the reoxidation of Q_A⁻, alleviating its interaction with plastoquinone. These effects enhanced photosynthetic performance related to PSII photochemistry (PI_ABS) and overall photosynthetic efficiency (PItotal). High light intensity (HL, 500 µmol photons/m²·s) caused a reduction in open reaction centers (qp), excitation efficiency (Φexc), photochemical energy conversion of PSII (Φ_PSII), maximum efficiency of PSII photochemistry in light (Fv′/Fm′), and linear electron transport via PSII, with more pronounced effects observed in membranes with a lower degree of LHCII oligomerization (Costata 2/133). This study provides novel experimental evidence for the pivotal role of the LHCII structural organization in determining the efficiency of light-dependent reactions of photosynthesis. Full article

Accurate fruit target identification is crucial for autonomous harvesting robots in complex orchards, where image segmentation using deep learning networks plays a key role. To address the trade-off between segmentation accuracy and inference efficiency, this study proposes LGVM-YOLOv8n, a lightweight instance segmentation model based on YOLOv8n-seg. LGVM is an acronym for lightweight, GSConv, VoVGSCSP, and $MPDIoU$, highlighting the key improvements incorporated into the model. The proposed model integrates three key improvements: (1) the GSConv module, which enhances feature interaction and reduces computational cost; (2) the VoVGSCSP module, which optimizes multi-scale feature representation for small objects; and (3) the $MPDIoU$ loss function, which improves target localization accuracy, particularly for occluded fruits. Experimental results show that LGVM-YOLOv8n reduces computational cost by 9.17%, decreases model weight by 7.89%, and improves inference speed by 16.9% compared to the original YOLOv8n-seg. Additionally, segmentation accuracy under challenging conditions (front-light, back-light, and occlusion) improves by 3.28% to 4.31%. Deployment tests on an edge computing platform demonstrate real-time performance, with inference speed accelerated to 0.084 s per image and frame rate increased to 28.73 FPS. These results validated the model’s robustness and adaptability, providing a practical solution for apple-picking robots in complex orchard environments. Full article

The chloroplast signal recognition particle (cpSRP) components cpSRP43 and cpSRP54 not only form a complex with light-harvesting chlorophyll (Chl)-binding proteins to direct them to the thylakoid membrane, but also serve other functions. cpSRP43 independently acts as a chaperone for some tetrapyrrole biosynthesis (TBS) enzymes, while cpSRP54 participates in the co-translational targeting of plastid-encoded proteins. However, it remains unclear to what extent the two cpSRP components are coregulated—despite their distinct functions—and whether both participate in genomes-uncoupled (GUN)-mediated retrograde signaling. Here, we demonstrate that cpSRP43 and cpSRP54 accumulation is strongly interdependently controlled: overexpression of one protein increases the level of the other, while a deficiency in one of the two proteins leads to a simultaneous decrease in the other component. Disruption of this balance, e.g., by combining the overexpression of one component with a knockout of the other, results in severe chlorosis, stunted growth, and reduced levels of Chl and tetrapyrrole intermediates. Moreover, cpSRP43 deficiency exacerbates the pale-green phenotype of gun4 and gun5 mutants, highlighting a synergistic impact on TBS; however, cpSRP43 overexpression fails to rescue these defects. Remarkably, loss of cpSRP43 does not affect the expression of nuclear-encoded photosynthetic genes under intrinsic plastid stress, clearly demonstrating that cpSRP43 is not involved in plastid-to-nucleus retrograde signaling. Overall, our findings underscore that the fine-tuned expression of cpSRP43 and cpSRP54 is crucial for proper chloroplast function and pigment biosynthesis, while cpSRP43 alone does not participate in the retrograde signaling pathway. Full article

To improve the object recognition and localization capabilities of wolfberry harvesting robots, this study introduces an object feature-based image segmentation algorithm designed for the segmentation and localization of wolfberry fruits and branches in unstructured lighting environments. Firstly, based on the a-channel of the Lab color space and the I-channel of the YIQ color space, a feature fusion algorithm combined with wavelet transformation is proposed to achieve pixel-level fusion of the two feature images, significantly enhancing the image segmentation effect. Experimental results show that this method achieved a 78% segmentation accuracy for wolfberry fruits in 500 test image samples under complex lighting and occlusion conditions, demonstrating good robustness. Secondly, addressing the issue of branch colors being similar to the background, a K-means clustering segmentation algorithm based on the Lab color space is proposed, combined with morphological processing and length filtering strategies, effectively achieving precise segmentation of branches and localization of gripping point coordinates. Experiments validated the high accuracy of the improved algorithm in branch localization. The results indicate that the algorithm proposed in this paper can effectively address illumination changes and occlusion issues in complex harvesting environments. Compared with traditional segmentation methods, it significantly improves the segmentation accuracy of wolfberry fruits and the localization accuracy of branches, providing technical support for the vision system of field-based wolfberry harvesting robots and offering theoretical basis and a practical reference for research on agricultural automated harvesting operations. Full article

Dragon fruit detection in natural environments remains challenged by limited accuracy and deployment difficulties, primarily due to variable lighting and occlusions from branches. To enhance detection accuracy and satisfy the deployment constraints of edge devices, we propose YOLOv10n-CGD, a lightweight and efficient dragon fruit detection method designed for robotic harvesting applications. The method builds upon YOLOv10 and integrates Gated Convolution (gConv) into the C2f module, forming a novel C2f-gConv structure that effectively reduces model parameters and computational complexity. In addition, a Global Attention Mechanism (GAM) is inserted between the backbone and the feature fusion layers to enrich semantic representations and improve the detection of occluded fruits. Furthermore, the neck network integrates a Dynamic Sample (DySample) operator to enhance the spatial restoration of high-level semantic features. The experimental results demonstrate that YOLOv10n-CGD significantly improves performance while reducing model size from 5.8 MB to 4.5 MB—a 22.4% decrease. The mAP improves from 95.1% to 98.1%, with precision and recall reaching 97.1% and 95.7%, respectively. The observed improvements are statistically significant (p < 0.05). Moreover, detection speeds of 44.9 FPS and 17.2 FPS are achieved on Jetson AGX Orin and Jetson Nano, respectively, demonstrating strong real-time capabilities and suitability for deployment. In summary, YOLOv10n-CGD enables high-precision, real-time dragon fruit detection while preserving model compactness, offering robust technical support for future robotic harvesting systems and smart agricultural terminals. Full article

The absence of α-carbonic anhydrase 2 (α-CA2) in Arabidopsis thaliana leads to higher contents of chlorophylls a and b, and to a reduced chlorophyll a/b ratio, suggesting an increased PSII antenna compared to the wild type (WT). The evaluation of the OJIP kinetics of chlorophyll fluorescence in leaves of WT and α-carbonic anhydrase 2 knockout (α-CA2-KO) plants revealed higher apparent photosystem II (PSII) light-harvesting antenna size in the mutants. The higher levels of both Lhcb1 and Lhcb2 proteins in α-CA2-KO plants compared to WT plants were demonstrated using immunoblotting. Gene expression analysis showed increased lhcb1 expression levels in mutants, whereas the lhcb2 and lhcb3 genes were downregulated. The content of hydrogen peroxide (H₂O₂) in leaves, as well as the production of H₂O₂ within the thylakoid membranes (“membrane” H₂O₂) was lower in α-CA2-KO plants as compared with WT plants. The expression levels of the genes encoding regulating proteins, which are involved in retrograde chloroplast–nucleus signaling, were lower in the α-CA2-KO than in the WT. The changes in the PSII light-harvesting complex size in the absence of α-CA2 correlates with the decreased accumulation of H₂O₂ in the leaves of mutants. It is suggested that this led to lower expression levels of the genes related to retrograde signal transduction from the chloroplast to the nucleus. The results of this study support previous conclusions regarding the involvement of α-CA2 in photosynthetic processes and its location within the chloroplasts of Arabidopsis. Full article

As one of the world’s economically valuable fruit crops, citrus has its quality and productivity closely tied to the degree of fruit ripeness. However, accurately and efficiently detecting citrus ripeness in complex orchard environments for selective robotic harvesting remains a challenge. To address this, we constructed a citrus ripeness detection dataset under complex orchard conditions, proposed a lightweight algorithm based on visual saliency priors and the RT-DETR model, and named it LightSal-RTDETR. To reduce computational overhead, we designed the E-CSPPC module, which efficiently combines cross-stage partial networks with gated and partial convolutions, combined with cascaded group attention (CGA) and inverted residual mobile block (iRMB), which minimizes model complexity and computational demand and simultaneously strengthens the model’s capacity for feature representation. Additionally, the Inner-SIoU loss function was employed for bounding box regression, while a weight initialization method based on visual saliency maps was proposed. Experiments on our dataset show that LightSal-RTDETR achieves a mAP@50 of 81%, improving by 1.9% over the original model while reducing parameters by 28.1% and computational cost by 26.5%. Therefore, LightSal-RTDETR effectively solves the citrus ripeness detection problem in orchard scenes with high complexity, offering an efficient solution for smart agriculture applications. Full article

Our multi-omics investigation of pepper fruit coloration dynamics demonstrates that the coordinated regulation of flavonoid accumulation and chlorophyll retention underpins the distinct pigmentation patterns between dark green (XHB) and light green (QL2017) cultivars. Through the integrated analysis of three developmental stages (10–30 DPA), we identified 989 differentially accumulated metabolites (DAMs) and 810 differentially expressed genes (DEGs), with flavonoid biosynthesis, phenylpropanoid metabolism, and chlorophyll turnover pathways pinpointed as central regulatory hubs. Notably, key metabolites such as quercitrin, kaempferol-3-O-rhamnoside, and cinnamic acid were significantly enriched in dark green fruits (XHB), coinciding with enhanced antioxidant activity and delayed chlorophyll degradation. Transcriptomic data revealed the coordinated upregulation of chlorophyll biosynthesis genes (COX15, POR) and light-harvesting complex components (Lhcb1, Lhcb2), while PAO—a pivotal chlorophyll catabolism gene—also exhibited elevated expression. Co-expression network analysis highlighted scopoletin GTase, F5H, CCR, and CAD as hub genes regulating flavonoid biosynthesis. qRT-PCR validation confirmed high consistency with transcriptomic trends (r > 0.85, p < 0.01). Our findings propose a synergistic model wherein flavonoid accumulation and chlorophyll metabolic dynamics jointly orchestrate green fruit pigmentation, offering novel insights and molecular targets for the precision breeding of pepper fruit coloration. Full article

Temperature changes strongly affect apple development and quality. In this study, we analyze the relationships between the main factors modulating both of the aforementioned processes in the fruits of four apple cultivars. We assessed three-dimensional data concerning the expression profile (fold change) of eight genes related to fruit ripeness regulation (involved in the cell respiration process and sorbitol metabolism as well as encoding cell kinase receptors) and fruit parameters such as fruit weight, ethylene concentration, concentration of soluble solids and acidity, which are affected by seasonal temperature variations (2018–2020). We observed that low temperatures (before the apple ripening phase) promoted an increase in gene activity and improved the fruit quality of the following cultivars: early-flowering/mid-ripening ‘Pink Braeburn’ and ‘Pinokio’, early-flowering/late-ripening ‘Ligol’ and late-flowering/late-ripening ‘Ligolina’. We confirmed the positive effect of low temperatures on the activity of the AAAA1, AALA1, StG and AAXA genes and on the evaluated fruit quality parameters, and we confirmed their dependence on the genotype of the studied cultivars. The obtained results shed light on the complexity of the variability mechanism in fruit features and fruit harvest dates. This knowledge may improve breeding programs for the production of better-quality apples. Full article