Search Results (177)

Frequent corn leaf diseases and pests pose serious threats to agricultural production. Traditional manual detection methods suffer from significant limitations in both performance and efficiency. To address this, the present paper proposes a novel biotic condition screening (BCS) model for the detection of corn leaf diseases and pests, called BCS_YOLO, based on the You Only Look Once version 11n (YOLOv11n). The proposed model enables accurate detection and classification of various corn leaf pathologies and pest infestations under challenging agricultural field conditions. It achieves this thanks to three key newly designed modules—a Self-Perception Coordinated Global Attention (SPCGA) module, a High/Low-Frequency Feature Enhancement (HLFFE) module, and a Local Attention Enhancement (LAE) module. The SPCGA module improves the model’s ability to perceive fine-grained targets by fusing multiple attention mechanisms. The HLFFE module adopts a frequency domain separation strategy to strengthen edge delineation and structural detail representation in affected areas. The LAE module effectively improves the model’s discrimination ability between targets and backgrounds through local importance calculation and intensity adjustment mechanisms. Conducted experiments show that BCS_YOLO achieves 78.4%, 73.7%, 76.0%, and 82.0% in $precision$, recall, $F1score$, and $mAP@50$, respectively, representing corresponding improvements of 3.0%, 3.3%, 3.2%, and 4.6% compared to the baseline model (YOLOv11n), while also outperforming the mainstream object detection models. In summary, the proposed BCS_YOLO model provides a practical and scalable solution for efficient detection of corn leaf diseases and pests in complex smart-agriculture scenarios, demonstrating significant theoretical and application value. Full article

The integration of computer vision (CV) and generative artificial intelligence (GenAI) into smart agriculture has revolutionised traditional farming practices by enabling real-time monitoring, automation, and data-driven decision-making. This review systematically examines the applications of CV in key agricultural domains, such as crop health monitoring, precision farming, harvesting automation, and livestock management, while highlighting the transformative role of GenAI in addressing data scarcity and enhancing model robustness. Advanced techniques, including convolutional neural networks (CNNs), YOLO variants, and transformer-based architectures, are analysed for their effectiveness in tasks like pest detection, fruit maturity classification, and field management. The survey reveals that generative models, such as generative adversarial networks (GANs) and diffusion models, significantly improve dataset diversity and model generalisation, particularly in low-resource scenarios. However, challenges persist, including environmental variability, edge deployment limitations, and the need for interpretable systems. Emerging trends, such as vision–language models and federated learning, offer promising avenues for future research. The study concludes that the synergy of CV and GenAI holds immense potential for advancing smart agriculture, though scalable, adaptive, and trustworthy solutions remain critical for widespread adoption. This comprehensive analysis provides valuable insights for researchers and practitioners aiming to harness AI-driven innovations in agricultural ecosystems. Full article

The Colorado potato beetle (Leptinotarsa decemlineata, CPB) is a major pest in potato crops, notorious for its rapid dispersal and insecticide resistance, which are enabled by its robust elytra and flight-capable hindwings. The Miniature (Mi) gene, encoding a protein with a zona pellucida (ZP) domain, is involved in wing development and cuticle integrity, yet its functional role in beetles remains underexplored. In this study, we cloned and characterized the LdMi gene in the CPB and investigated its function using RNA interference (RNAi), morphological analyses, and spectroscopy. LdMi encodes a 146.35 kDa transmembrane protein with a conserved ZP domain, clusters with coleopteran homologs, and exhibits relative conservation across insect species. Expression profiling showed high LdMi transcript levels in the hindwings, the elytra, and the pupal stages. RNAi knockdown in fourth-instar larvae resulted in severe eclosion defects, including malformed wings and reduced adult weight. Scanning electron microscopy (SEM) revealed disrupted elytral patterns and deformed hindwing veins in knockdown individuals. Spectroscopic analyses using Fourier-transform infrared (FTIR) and Raman spectroscopy indicated a reduction in protein–chitin crosslinking and diminished hydrogen bonding, suggesting compromised cuticular integrity. These results highlight the essential role of LdMi in cuticle formation and the surface morphology of the elytra and hindwings, offering new insights into ZP domain proteins in insects. Full article

Cytoplasmic polyadenylation element-binding proteins (CPEBs) are critical regulators of maternal mRNA translation during oogenesis, yet their roles in insect reproduction remain underexplored. Here, we characterized CmCPEB2, a CPEB homolog in the rice leaf roller Cnaphalocrocis medinalis, a destructive lepidopteran pest insect, and elucidated its role in mating-induced oviposition. The CmCPEB2 protein harbored conserved RNA recognition motifs and a ZZ-type zinc finger domain and was phylogenetically clustered with lepidopteran orthologs. Spatiotemporal expression profiling revealed CmCPEB2 was predominantly expressed in ovaries post-mating, peaking at 12 h with a 6.75-fold increase in transcript levels. Liposome-mediated RNA interference targeting CmCPEB2 resulted in a 52% reduction in transcript abundance, leading to significant defects in ovarian maturation, diminished vitellogenin deposition, and a 36.7% decline in fecundity. The transcriptomic analysis of RNAi-treated ovaries identified 512 differentially expressed genes, with downregulated genes enriched in chorion formation and epithelial cell development. Tissue culture-based hormonal assays demonstrated the juvenile hormone-dependent regulation of CmCPEB2, as JH treatment induced its transcription, while knockdown of the JH-responsive transcription factor CmKr-h1 in the moths suppressed CmCPEB2 expression post-mating. These findings established CmCPEB2 as a juvenile hormone-dependent regulator of mating-induced oviposition that orchestrates vitellogenesis through yolk protein synthesis and ovarian deposition and choriogenesis via transcriptional control of chorion-related genes. This study provides novel evidence of CPEB2-mediated reproductive regulation in Lepidoptera, highlighting its dual role in nutrient allocation and structural eggshell formation during insect oogenesis and oviposition. Full article

Small heat shock proteins (sHsps) play crucial roles in organismal adaptation to stress tolerance. Sitodiplosis mosellana, a devastating insect wheat pest, undergoes long obligatory larval diapause to survive temperature extremes during summer and winter. To elucidate the function of sHsps in this process, two sHsp-encoding genes (SmHsp22.2 and SmHsp26.7) were characterized from S. mosellana, and their responsiveness to diapause and thermal stress, as well as their roles in cold stress, was analyzed. Both SmHsp22.2 and SmHsp26.7 possessed the canonical α-crystallin domain and lacked introns. Quantitative PCR indicated significant upregulation of SmHsp22.2 and SmHsp26.7 during diapause, especially in summer and winter. Notably, SmHsp22.2 exhibited higher expression in summer relative to winter, whereas SmHsp26.7 showed the opposite profile. Moreover, short-term heat shock (≥35 °C) in over-summering larvae or cold shock (≤−10 °C) in over-wintering larvae was found to trigger transcriptional upregulation of both genes, while prolonged temperature extremes (i.e., 45–50 °C or −15 °C) did not elicit a comparable response. RNA interference-mediated knockdown of both genes significantly increased the mortality of S. mosellana larvae under cold stress. These findings indicate the importance of both SmHsps in diapause and environmental adaptation in S. mosellana. Full article

This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test (${\chi }^2$ = 12.00, p = 0.02) and Nemenyi post hoc comparisons (p < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability. Full article

Sweet corn (Zea mays L. saccharata) has emerged as a valuable crop not only for its economic potential but also for its role in sustainable food systems due to its high consumer demand and adaptability. As global agricultural systems face increasing pressure from climate change, resource scarcity, and nutritional challenges, a strategic synthesis of research is essential to guide future innovation. This review aims to critically assess and synthesize major advancements in sweet corn (Zea mays L. saccharata) research from 2010 to 2025, with the objectives of identifying key genetic improvements, evaluating agronomic innovations, and examining sustainable production strategies that collectively enhance crop performance and resilience. The analysis is structured around three core pillars: genetic improvement, agronomic optimization, and sustainable agriculture, each contributing uniquely to the enhancement of sweet corn productivity and environmental adaptability. In the genetics domain, recent breakthroughs such as CRISPR-Cas9 genome editing and marker-assisted selection have accelerated the development of climate-resilient hybrids with enhanced sweetness, pest resistance, and nutrient content. The growing emphasis on biofortification aims to improve the nutritional quality of sweet corn, aligning with global food security goals. Additionally, studies on genotype–environment interaction have provided deeper insights into varietal adaptability under varying climatic and soil conditions, guiding breeders toward more location-specific hybrid development. From an agronomic perspective, innovations in precision irrigation and refined planting configurations have significantly enhanced water use efficiency, especially in arid and semi-arid regions. Research on plant density, nutrient management, and crop rotation has further contributed to yield stability and system resilience. These agronomic practices, when tailored to specific genotypes and environments, ensure sustainable intensification without compromising resource conservation. On the sustainability front, strategies such as reduced-input systems, organic nutrient integration, and climate-resilient hybrids have gained momentum. The adoption of integrated pest management and conservation tillage further promotes sustainable cultivation, reducing the environmental footprint of sweet corn production. By integrating insights from these three dimensions, this review provides a comprehensive roadmap for the future of sweet corn research, merging genetic innovation, agronomic efficiency, and ecological responsibility to achieve resilient and sustainable production systems. Full article

20-hydroxyecdysone (20E) is essential for insect development and diapause. Ecdysone receptor (EcR) and ultraspiracle (USP) proteins are crucial regulators of 20E signaling. To explore their potential roles in the development of Sitodiplosis mosellana, a major wheat pest that undergoes obligatory diapause as a larva, one SmEcR and two SmUSPs (SmUSP-A and SmUSP-B) from this species were isolated and characterized. The deduced SmEcR and SmUSP-A/B proteins contained a conserved DNA-binding domain with two zinc finger motifs that bind to specific DNA sequences. Expression of SmEcR and the SmUSPs was developmentally controlled, as was 20E induction. Their transcription levels increased as the larvae entered pre-diapause, followed by downregulation during diapause and upregulation during the shift to post-diapause quiescence, which is highly consistent with ecdysteroid titers in this species. Topical application of 20E to diapausing larvae also elicited a dose-dependent expression of the three genes. Expression of SmEcR and SmUSPs decreased markedly during the pre-pupal stage and was higher in adult females compared to males. These findings suggested that 20E-induced expression of SmEcR and SmUSPs has key roles in diapause initiation and maintenance, post-diapause quiescence, and adult reproduction, while the larval–pupal transformation may be associated with a decrease in their expression levels. Full article

Timely detection and treatment of moisture anomalous regions in grain storage facilities is crucial for preventing mold growth, germination, and pest infestation. To locate these regions, this paper presents a novel anomalous moisture region localization algorithm based on the delay-multiply-and-sum (DMAS) beamforming techniques, including the design of an effective spatial arrangement of electromagnetic wave transmitters and receivers, along with comprehensive testing of detectable regions and experimental validation of anomaly localization across varying moisture levels and positions within grain piles. Following initial localization using the proposed algorithm, the study introduces a reliability assessment method for unknown samples based on the signal-to-mean ratio (SMR) value and compares the region of maximum response intensity with that of maximum connected domain volume. The system demonstrated successful localization of a 7 cm × 7 cm × 7 cm region with 15.4% moisture content within a cubic experimental bin containing 10.5% moisture content long-grained rice, achieving an average recall accuracy exceeding 50%. The proposed method presents rapid detection capabilities and precise localization, showing potential for moisture content evaluation of anomalous regions and practical applications in grain storage monitoring systems. Full article

Monolepta hieroglyphica Motschulsky, a major agricultural pest in China, causes considerable economic damage to crops, such as maize. In this study, a Bacillus thuringiensis (Bt) strain was discovered to exhibit insecticidal activity against M. hieroglyphica. A novel Bt gene, vpb4Fa1, with toxicity against both adults and larvae of M. hieroglyphica was cloned. The Vpb4Fa1 protein causes damage to the midgut of adult M. hieroglyphica, disrupting their normal growth and development and ultimately leading to death. To further enhance the insecticidal activity of the vpb4Fa1 gene, a random mutation library was established. A total of 75 mutants with amino acid mutations were generated, among which 7 mutants demonstrated significantly enhanced activity relative to the wild-type gene. Notably, three mutants, C9, 6C2, and 6A7, exhibited the highest activity, with LC₅₀ values for adult M. hieroglyphica of 10.21, 9.45, and 9.83 µg/g, respectively. The mutants C9, 6C2, and 6A7 each harbored nine, three, and six amino acid mutations, respectively, mainly located in Domains I, II, and III. The novel insecticidal gene vpb4Fa1 and its mutants offer valuable genetic resources for the biological control of M. hieroglyphica and the development of Bt transgenic maize. Full article

The accurate detection of citrus surface defects is essential for automated citrus sorting to enhance the commercialization of the citrus industry. However, previous studies have only focused on single-modal defect detection using visible light images (RGB) or near-infrared light images (NIR), without considering the feature fusion between these two modalities. This study proposed an RGB-NIR multimodal fusion method to extract and integrate key features from both modalities to enhance defect detection performance. First, an RGB-NIR multimodal dataset containing four types of citrus surface defects (cankers, pests, melanoses, and cracks) was constructed. Second, a Multimodal Compound Domain Attention Fusion (MCDAF) module was developed for multimodal channel fusion. Finally, MCDAF was integrated into the feature extraction network of Real-Time DEtection TRansformer (RT-DETR). The experimental results demonstrated that RT-DETR-MCDAF achieved Precision, Recall, mAP@0.5, and mAP@0.5:0.95 values of 0.914, 0.919, 0.90, and 0.937, respectively, with an average detection performance of 0.598. Compared with the model RT-DETR-RGB&NIR, which used simple channel concatenation fusion, RT-DETR-MCDAF improved the performance by 1.3%, 1.7%, 1%, 1.5%, and 1.7%, respectively. Overall, the proposed model outperformed traditional channel fusion methods and state-of-the-art single-modal models, providing innovative insights for commercial citrus sorting. Full article

Pest infestations have always been a major factor affecting tea production. Real-time detection of tea pests using machine vision is a mainstream method in modern agricultural pest control. Currently, there is a notable absence of machine vision devices capable of real-time monitoring for small-sized tea pests in the market, and the scarcity of open-source datasets available for tea pest detection remains a critical limitation. This manuscript proposes a YOLOv8-FasterTea pest detection algorithm based on cross-domain transfer learning, which was successfully deployed in a novel tea pest monitoring device. The proposed method leverages transfer learning from the natural language character domain to the tea pest detection domain, termed cross-domain transfer learning, which is based on the complex and small characteristics shared by natural language characters and tea pests. With sufficient samples in the language character domain, transfer learning can effectively enhance the tiny and complex feature extraction capabilities of deep networks in the pest domain and mitigate the few-shot learning problem in tea pest detection. The information and texture features of small tea pests are more likely to be lost with the layers of a neural network becoming deep. Therefore, the proposed method, YOLOv8-FasterTea, removes the P5 layer and adds a P2 small target detection layer based on the YOLOv8 model. Additionally, the original C2f module is replaced with lighter convolutional modules to reduce the loss of information about small target pests. Finally, this manuscript successfully applies the algorithm to outdoor pest monitoring equipment. Experimental results demonstrate that, on a small sample yellow board pest dataset, the mAP@.5 value of the model increased by approximately 6%, on average, after transfer learning. The YOLOv8-FasterTea model improved the mAP@.5 value by 3.7%, while the model size was reduced by 46.6%. Full article

Mushrooms are a valuable source of bioactive compounds to develop efficient, secure medicines and environmentally friendly agrochemicals. Cylindracin is a small cysteine-rich protein that is specifically expressed in the immature fruiting body of the edible mushroom Cyclocybe cylindracea. Recombinant protein (rCYL), comprising the C-terminal cysteine-rich domain of cylindracin, inhibits the hyphal growth and conidiogenesis of filamentous fungi. Here, we show that rCYL represses the egg-laying and development of Caenorhabditis elegans and Drosophila melanogaster. The feeding of rCYL at 16 µM reduced the body volume of C. elegans larvae to approximately 60% when compared to the control. At the same concentration, rCYL repressed the frequencies of pupation and emergence of D. melanogaster to 74% and 40%, respectively, when compared to the control. In virgin adult flies, feeding of rCYL at 47 µM substantially repressed the frequency of egg-laying, and the pupation and emergence of the next generation, especially for females. These inhibitory effects of rCYL gradually disappeared after ceasing the ingestion of rCYL. The use of fluorescence-labeled rCYL revealed that the protein accumulates specifically at the pharynx cuticles of C. elegans. In D. melanogaster, fluorescence-labeled rCYL was detected primarily in the midguts and to a lesser degree in the hindguts, ovaries, testes, and malpighian tubules. rCYL was stable against trypsin, chymotrypsin, and pepsin, whereas it did not inhibit proteolytic and glycolytic enzymes in vitro. rCYL oligomerized and formed amyloid-like aggregates through the binding to heparin and heparan sulfate in vitro. These results suggest that rCYL has potential as a new biocontrol agent against pests. Full article

Currently, there is no publicly available dataset for the classification of potato pest and disease-related queries. Moreover, traditional query classification models generally adopt a single maximum-pooling strategy when performing down-sampling operations. This mechanism only extracts the extreme value responses within the local receptive field, which leads to the degradation of fine-grained feature representation and significantly amplifies text noise. To address these issues, a dataset construction method based on prompt engineering is proposed, along with a question classification method utilizing a gated fusion–convolutional neural network (GF-CNN). By interacting with large language models, prompt words are used to generate potato disease and pest question templates and efficiently construct the Potato Pest and Disease Question Classification Dataset (PDPQCD) by batch importing named entities. The GF-CNN combines outputs from convolutional kernels of varying sizes, and after processing with max-pooling and average-pooling, a gating mechanism is employed to regulate the flow of information, thereby optimizing the text feature extraction process. Experiments using GF-CNN on the PDPQCD, Subj, and THUCNews datasets show F1 scores of 100.00%, 96.70%, and 93.55%, respectively, outperforming other models. The prompt engineering-based method provides a new paradigm for constructing question classification datasets, and the GF-CNN can also be extended for application in other domains. Full article

Traditional methods for detecting plant diseases and pests are time-consuming, labor-intensive, and require specialized skills and resources, making them insufficient to meet the demands of modern agricultural development. To address these challenges, deep learning technologies have emerged as a promising solution for the accurate and timely identification of plant diseases and pests, thereby reducing crop losses and optimizing agricultural resource allocation. By leveraging its advantages in image processing, deep learning technology has significantly enhanced the accuracy of plant disease and pest detection and identification. This review provides a comprehensive overview of recent advancements in applying deep learning algorithms to plant disease and pest detection. It begins by outlining the limitations of traditional methods in this domain, followed by a systematic discussion of the latest developments in applying various deep learning techniques—including image classification, object detection, semantic segmentation, and change detection—to plant disease and pest identification. Additionally, this study highlights the role of large-scale pre-trained models and transfer learning in improving detection accuracy and scalability across diverse crop types and environmental conditions. Key challenges, such as enhancing model generalization, addressing small lesion detection, and ensuring the availability of high-quality, diverse training datasets, are critically examined. Emerging opportunities for optimizing pest and disease monitoring through advanced algorithms are also emphasized. Deep learning technology, with its powerful capabilities in data processing and pattern recognition, has become a pivotal tool for promoting sustainable agricultural practices, enhancing productivity, and advancing precision agriculture. Full article