Search Results (543)

Timely detection and monitoring of diseases in sweet potato crops are important for hunger alleviation and food security. This study aimed to evaluate the efficacy of the optimized field spectrometric reflectance thresholds in spatially partitioning sweet potato crops on the unmanned aerial vehicle (UAV) multispectral imagery based on infection types. A field survey was carried out to sample deformed leaves for laboratory diagnosis of possible identification of sweet potato leaf infection types. Laboratory analysis results revealed nutrient deficiency, SPVC-positive, fungi isolates (i.e., alternaria, bipolaris, fusarium, phoma), and mechanical damage as the causes of leaf deformation. Overlap analysis results revealed reflectance overlaps across all leaf deformation types, making it difficult to spatially partition sweet potato crops based on deformation types. Instead, sweet potato crops were spatially partitioned by considering the minimum and maximum thresholds acquired from the whole dataset. Area covered by deformed sweet potato leaves in blue, green, red, red edge and NIR were found to be 11.91%, 28.71%, 43.66%, 46.41% and 30.6% respectively. Coefficient of determination results revealed poor classification results, with R² value of 0.23, 0.19, 0.28, 0.17 and 0.63 for blue, green, red, red edge and NIR respectively. However, the NIR spectral band yielded R² value closer to the acceptable value of 0.7. Full article

Accurate and robust detection of leaf diseases is a key enabler for precision agriculture and large-scale crop health monitoring. Despite the strong generalization of modern one-stage detectors (e.g., YOLOv8), two domain-specific challenges remain: (i) weak or blurry lesion boundaries hinder precise localization, and (ii) low color contrast between diseased and healthy tissues forces models to rely on subtle texture patterns rather than salient shapes. To tackle these challenges, we reframe the core agricultural disease detection task as the identification of “asymmetric morphological anomalies” and propose a domain-tailored enhancement framework. First, we introduce an Edge Enhancement Module (EEM) that explicitly strengthens boundary-aware representations. Inspired by the natural symmetry of healthy leaves, our EEM is specifically designed to capture symmetry-breaking boundary discontinuities and localized asymmetric edges caused by disease lesions. Our method enhances edge and texture cues that are indicative of disease lesions, which often exhibit local asymmetries and boundary discontinuities. The EEM includes a Differential Normalized Pooling Block (DNPB) that highlights edge responses through discrepancies between max pooling and average pooling, which also models cross-group edge correlations. Second, the Lightweight Texture-Sensitive Feature Enhancement (LTSFE) mechanism amplifies texture-discriminative channels under low-contrast conditions by leveraging complementary global statistics and efficient channel mixing, all with negligible computational overhead. We evaluated our method on a self-constructed dataset of 106,434 images with 225,640 annotations covering diverse crops. Experiments show that the proposed method achieves state-of-the-art accuracy (81.54% mAP@0.5:0.95) while maintaining real-time inference (142 FPS), consistently outperforming strong baselines. Ablations confirm the effectiveness and complementarity of EEM and LTSFE, demonstrating that domain-specific architectural design, inspired by biological symmetry, can substantially improve agricultural vision systems. Full article

The floodplains of the Paraná and Paraguay rivers form the Chaco wetland, one of the most species-rich plant ecosystems in Argentina. Because wild grasses can serve as reservoirs of fungal species that cause disease and mycotoxin contamination of cereal crops, we examined asymptomatic, wild grasses from the Chaco wetlands for the presence of the genus Fusarium, which includes multiple species that cause agriculturally important diseases and/or mycotoxin contamination of crops. We focused our efforts on the identification and characterization of the multispecies lineage known as the Fusarium fujikuroi species complex (FFSC). Using morphological traits and partial DNA sequences of the TEF1 gene, we determined that 58 isolates recovered from the grasses were members of FFSC. Fifty of the isolates were identified as one of six FFSC species, including the economically important plant pathogenic species F. proliferatum, F. subglutinans, and F. verticillioides. To our knowledge, two of the species, F. anthophilum and F. pseudocircinatum, have not been reported previously in Argentina. Our analyses also indicated that eight of the FFSC isolates were a novel species, herein described as Fusarium varsavskyanum. A polymerase chain reaction (PCR) assay and genome sequence data indicate that each isolate of F. varsavskyanum isolate had only one mating type idiomorph (MAT1-1 or MAT1-2), which suggests that the fungus is heterothallic. Genome sequence analysis indicated that F. varsavskyanum has the genetic potential to produce, (i) the emerging mycotoxins fusaric acid and beauvericin (or enniatins); (ii) the pigments bikaverin, carotenoids, and fusarubin; and (iii) the plant hormones auxins, cytokinins, and gibberellins. Thus, asymptomatic grasses from the Chaco wetland can harbor Fusarium species that in some agroecosystems can cause economically important diseases and/or mycotoxin contamination of crops. It remains to be determined whether the genotypes of Fusarium species that occur on the wetland grasses, including F. varsavskyanum genotypes, can negatively impact agriculture. Full article

Potato (Solanum tuberosum L.) is the world’s fourth-largest staple crop. Alkaline salt stress is a major abiotic stress factor that severely limits the growth, yield, and quality of potatoes; however, little is known about the molecular basis of potatoes’ response to alkaline salt stress or the stress-alleviation mechanism mediated by 24-epibrassinoside. In this study, we conducted a genome-wide identification of the potato miR482 family and analyzed its response patterns under alkaline salt stress and 24-epibrassinoside-mediated stress relief. We identified a total of 9 mature stu-miR482 sequences and 5 precursor sequences; all precursors form typical stable hairpin structures and exhibit high evolutionary conservation among Solanaceae plants. Promoter analysis revealed multiple cis-acting elements in the promoter region associated with light signaling, plant hormones, and stress signaling. A total of 64 potential target genes were predicted, encompassing transcription factors, disease resistance, and signal transduction-related genes, forming a complex regulatory network. Phenotypic analysis confirmed that EBR significantly alleviates the growth inhibition in potatoes induced by alkaline salt stress. qRT-PCR analysis indicated that stu-miR482a-5p is the primary stress-responsive member in leaves; stu-miR482d-3p/5p exhibited the strongest regulatory response to EBR in roots; in potato stolons, all members of the miR482 family were significantly upregulated under alkaline salt stress, with stu-miR482d-5p showing extremely significant upregulation across all treatment groups. In summary, this study represents the first systematic characterization of the potato miR482 family, revealing its tissue differential functions in alkaline salt stress and EBR-mediated stress relief. Full article

INDETERMINATE DOMAIN (IDD) transcription factors are plant-specific regulators essential for plant development and stress adaptation. As a globally important staple crop, common wheat (Triticum aestivum L.) is frequently threatened by fungal diseases such as powdery mildew and stripe rust. To date, however, the IDD gene family in wheat has not been systematically characterized, and its roles in biotic stress responses remain unclear. In this study, we performed genome-wide identification and a comprehensive analysis of the TaIDD gene family. A total of 41 TaIDD genes were identified, which were unevenly distributed across 15 chromosomes and divided into four phylogenetic groups. Synteny and selective pressure analyses demonstrated that segmental duplication was the main driver of family expansion and that TaIDD genes underwent strong purifying selection during evolution. Cis-acting element analysis revealed abundant hormone- and stress-related elements in their promoter regions. Transcriptome and RT-qPCR analyses indicated that TaIDD genes exhibited distinct expression patterns under abiotic and biotic stress. Notably, TaIDD13, TaIDD19, TaIDD27, TaIDD37, TaIDD39, and TaIDD41 were significantly induced by multiple fungal pathogens, suggesting their potential involvement in stress-responsive pathways that may be related to disease resistance. Subcellular localization analysis further confirmed that TaIDD39 was exclusively localized in the nucleus, consistent with its function as a transcriptional regulator. Our findings provide insights into the evolutionary characteristics and stress-response mechanisms of TaIDD genes and highlight TaIDD39 and other potential candidates that may serve as valuable resources for wheat molecular breeding to enhance broad-spectrum disease resistance and stress tolerance. Full article

The detection technology of crop diseases and pests is transitioning from single sensor monitoring to intelligent perception and multimodal fusion. This paper follows the PRISMA 2020 standard and systematically reviews the relevant core literature. This paper systematically summarizes the development history of spectral sensing technology and analyzes the physical mechanisms of hyperspectral and multispectral imaging in early identification of crop diseases. The focus is on the architectural evolution of deep learning models, including lightweight convolutional neural networks (CNNs), vision transformers (ViTs) with long-range dependency modeling capabilities, and the efficient computing state space model Mamba. In addition, the research progress of spatial spectral joint learning, heterogeneous data fusion, and vision-language models (VLMs) in improving system robustness and interpretability are introduced. By synthesizing the integrated applications of UAV remote sensing, Internet of Things (IoT) edge computing and intelligent robots in staple and cash crops, this paper summarizes the implementation of the integrated system of perception, decision-making and execution. To address the issues of insufficient cross-domain generalization ability and uneven allocation of computing resources in existing models, this paper provides perspectives on the future development of agricultural artificial intelligence (AI) towards foundation model-driven, edge-intelligent collaboration, and green sustainable direction, which can provide theoretical reference for engineering applications in the field of intelligent plant protection. Full article

Sugarcane is a globally important crop, widely cultivated for sugar production and bioenergy. However, leaf spot disease leads to a reduction in its quality and yield. In this study, pathogen identification, biological characteristic analysis, and screening of antagonistic bacteria against the causal pathogens were done as a basis for epidemic prediction and green control of sugarcane leaf spot disease. The causal pathogens of sugarcane leaf spot disease were identified as Epicoccum latusicollum El532 and Fusarium sacchari Fs64, respectively, based on morphological characteristics, multi-gene phylogenetic analysis (ITS, TUB2, and RPB2 for El532; ITS, TEF1α, and RPB2 for Fs64), and pathogenicity tests. Biological characterization revealed that both pathogens exhibited optimal mycelial growth at 25 °C and under continuous darkness. However, light-dark cycles inhibited their growth. The optimal pH ranges for both isolates were 6–9 and 5–10, respectively. Maltose was the optimal carbon source for El532, whereas maltose, lactose, and starch were optimal for Fs64. Yeast extract served as the optimal nitrogen source for both. Isolation and screening of bacterial strains from healthy sugarcane roots, leaves, and rhizosphere soil yielded 13 antagonistic bacterial strains. Among them, six strains exhibited inhibition rates exceeding 57% against both pathogens. Bacillus subtilis A5 exhibited the highest antagonistic activity (68.85% against El532, 71.69% against Fs64), underscoring its potential as a promising biocontrol candidate. These findings provide a scientific basis for the diagnosis and management of sugarcane leaf spot disease. Full article

Accurate and actionable crop disease diagnosis requires not only visual recognition of disease symptoms but also the ability to generate grounded reports that integrate symptom interpretation with agronomic knowledge. Existing image-based plant disease diagnosis methods mainly focus on disease classification and often lack fine-grained symptom description, evidence retrieval, and decision-oriented report generation. To address these limitations, we propose CornCare, a multimodal framework for corn disease diagnosis and diagnostic report generation that combines visual recognition, phenotype captioning, document retrieval, and knowledge-graph-based recommendation support. Given a field corn image, CornCare first localizes disease-relevant leaf regions to reduce background interference. The localized leaf image is then used for disease classification and phenotype caption generation, producing both a disease category and a fine-grained symptom description. These outputs jointly support hierarchical knowledge retrieval, where the disease category narrows the search to relevant expert documents and the phenotype caption retrieves symptom-consistent evidence. The retrieved evidence is further combined with a structured agricultural knowledge graph to generate diagnostic reports with symptom interpretation, likely causes, and management suggestions. Experiments show that CornCare achieves competitive performance in disease identification and phenotype description generation while improving the groundedness, completeness, and practical usefulness of generated diagnostic reports. These results suggest that combining multimodal perception with symptom-grounded knowledge retrieval provides a promising path toward more practical and explainable crop disease diagnosis. Full article

Brown spot on the leaf sheath is an emerging disease of sweet corn (Zea mays L.) in Sinaloa, Mexico, with an unknown etiology. This study aimed to identify the causal agent of the disease and assess its pathogenicity on commercial sweet corn hybrids. Bacterial strains were isolated from symptomatic leaf sheaths collected from commercial fields. Identification was performed through biochemical profiling (API 50CHB/E), pathogenicity tests on alternative hosts (potato, onion, celery), and molecular analysis (16S rRNA and recA genes sequencing and phylogenetic reconstruction). Pathogenicity and virulence were confirmed by inoculating four sweet corn hybrids in a greenhouse. The strains were Gram-negative rods, identified as Burkholderia gladioli based on biochemical profiles and molecular data (99% 16S rRNA+ recA similarity; phylogenetic clustering within the B. gladioli clade). In greenhouse trials, the strains induced brown spot lesions on the leaf sheaths of all tested hybrids, replicating field symptoms fulfilling Koch’s postulates. This is the first report of B. gladioli as the causal agent of brown spot on the leaf sheath of sweet corn in Mexico. The pathogen’s broad host range highlights its potential as an emerging threat to horticultural crops in the region. Full article

The accurate and timely detection of leaf diseases is essential in helping farmers take necessary corrective actions to prevent disease spread that can lead to significant crop losses, reduced yield, and economic losses. A real-time Raspberry Pi 5-based prototype classification of tobacco leaf diseases using You Only Look Once Version 8 (YOLOv8n) and a Deep Convolutional Neural Network (DCNN) was developed to assist farmers with their crop disease identification. The calibration was performed by adjusting the camera mounting height and the lux level to achieve the system’s optimal performance. It was evaluated using 24 fresh tobacco leaves upon identifying the system’s optimal setting. Under optimal settings, the prototype achieved an overall accuracy of 93%, with per-class accuracies of 100% for frogeye classification, 100% for TMV classification, 94% for wildfire classification, and 78% for healthy leaves. Full article

The date palm (Phoenix dactylifera L.) is a significant perennial crop in arid and semi-arid regions. Understanding the evolution of research on this crop is vital for identifying major research trends, current challenges, and emerging areas for future agricultural innovation and sustainable crop management strategies. This study conducts a comprehensive scientometric analysis of 9062 scientific publications indexed in the Scopus database between 1837 and 2025, spanning nearly two centuries of research on date palm. Using bibliometric tools such as Bibliometrix and ScientoPy, the study examines patterns of scientific production, collaboration networks, institutional participation, thematic evolution, and emerging research trends. The results indicate a marked increase in scientific publications, especially after 2007, with Saudi Arabia, Egypt, and Iran among the most productive countries. The thematic structure of the literature shows a shift from early studies on diseases and oasis cultivation to recent research focusing on biomass valorization, activated carbon production, antioxidant properties, pest management with special emphasis on the red palm weevil (Rhynchophorus ferrugineus), mechanical properties of date palm fibers, and plant biotechnology on methods like micropropagation and somatic embryogenesis. Geographically, research activity is concentrated in the Middle East and North Africa, the primary palm-producing region, with Saudi Arabia leading in institutions, researchers, funding, and international collaborations in date palm research. Emerging trends indicate a rising interest in digital tools, particularly artificial intelligence and advanced analytical tools, which are increasingly being explored to improve crop management. Overall, these findings provide a structured overview of the historical development of date palm research and contribute to a deeper understanding of the evolution and organization of scientific knowledge in this field. Additionally, the identification of key research pathways and emerging trends offers valuable insights for guiding future agronomic innovation, supporting evidence-based crop management strategies, and promoting the sustainable development of date palm production systems. Full article

Pruning is a critical horticultural practice that requires continuous interpretation of plant structure to maintain crop health and prevent disease. Manual identification of pruning-relevant regions is labor-intensive and limits scalability in precision agriculture. This study presents a cognitive vision-based pruning region identification system using a You Only Look Once version 9 model to detect lateral branches, lower leaves, and diseased leaves in Solanum lycopersicum. A custom dataset of 4905 augmented images was used for training and evaluation. The model achieved 82.86% precision, 77.24% recall, 79.96% F1-score, and 83.21% mAP. Deployment on Raspberry Pi 5 demonstrated real-time, cloud-independent edge inference, indicating the feasibility of low-cost cognitive vision systems for smart agriculture. Full article

In the context of the rapid development of smart horticulture, a deep remote sensing-based dual detection method for horticultural crop growth anomalies and safety risks was proposed to address the limitations of existing remote sensing monitoring approaches. These conventional methods, which predominantly focused on growth vigor assessment or single-task anomaly detection, had difficulty distinguishing anomalies from actual production risks and exhibited insufficient sensitivity to weak anomalies and complex temporal disturbances. Within a unified framework, a growth state modeling branch and an anomaly perception branch were constructed, enabling the joint modeling of normal growth trajectories and anomalous deviation features. By further introducing a risk joint discrimination mechanism, an integrated analysis pipeline from anomaly identification to risk assessment was achieved. Multi-temporal remote sensing features were used as inputs, through which normal crop growth patterns were characterized via trend perception, texture modeling, and temporal aggregation, while sensitivity to local disturbances and weak anomaly signals was enhanced by anomaly embeddings and energy representations. Systematic experiments conducted on multi-regional and multi-crop horticultural remote sensing datasets demonstrated that the proposed method significantly outperformed comparative approaches, including traditional threshold-based methods, support vector machines, random forests, autoencoders, ConvLSTM, and temporal transformer models. In the dual task of horticultural crop growth anomaly detection and safety risk identification, an accuracy of approximately 0.91 and an F1 score of 0.88 were achieved, indicating higher anomaly recognition accuracy and more stable risk discrimination capability. Further anomaly-type awareness experiments showed that consistent performance was maintained across diverse real-world production scenarios, including climate stress, disease-induced anomalies, and management errors. Full article

Robust plant disease detection in real-world agricultural environments remains challenging due to dynamic environmental conditions. Accurate and reliable disease identification is essential for precision agriculture and effective crop management. Although computer vision and Artificial Intelligence (AI) have shown promising results in controlled settings, their performance often drops under lesion scale variability, inter- and intra-class similarity among diseases, class imbalance, and illumination fluctuations. To overcome these challenges, we propose a Heterogeneous Feature Aggregation Network (HFA-Net) that brings together architectural improvements, illumination-aware preprocessing, and training-level enhancements into a single cohesive framework. To extract richer and more discriminative features from the early layers of the network, HFA-Net introduces a multi-scale, multi-level feature aggregation stem. The Reduction-Expansion (RE) mechanism helps preserve important lesion details while adapting to variations in scale. Considering real agricultural environments, an Illumination-Adaptive Contrast Enhancement (IACE) preprocessing pipeline is designed to address illumination variability in real agricultural environments. Experimental results show that HFA-Net achieves 96.03% accuracy under normal conditions and maintains strong performance under challenging lighting scenarios, achieving 92.95% and 93.07% accuracy in extremely dark and bright environments, respectively. Furthermore, quantitative explainability analysis using perturbation-based metrics demonstrates that the model’s predictions are not only accurate but also faithful to disease-relevant regions. Finally, Grad-CAM-based visual explanations confirm that the model’s predictions are driven by disease-specific regions, enhancing interpretability and practical reliability. Full article

Passion fruit (Passiflora edulis Sims) is an important economic fruit crop in Rwanda grown for both domestic consumption and export markets. However, viral diseases pose a significant threat to passion fruit production. Among these, passion fruit woodiness disease (PWD) is the most destructive, causing yield losses of up to 100%. A survey was carried out to assess the distribution of Ugandan passiflora virus (UPV; Potyvirus passiflorafricanse) in major passion fruit growing areas. UPV is one of the major viruses known to cause PWD. The incidence of viral symptoms observed in the field did not differ significantly among districts, ranging from 81% in Rusizi to 100% in Rwamagana. However, mean symptom severity scores varied significantly between districts, with the highest severity recorded in Kayonza (3.1) and the lowest in Rulindo (1.9). Serological analysis detected potyviruses in 44% of the total samples (n = 216), including 43% of symptomatic (n = 144) and 47% of asymptomatic (n = 72) leaf samples collected from passion fruit fields. Further analysis using Reverse-Transcription Polymerase Chain Reaction (RT-PCR) detected UPV in 56% of symptomatic (n = 126) and 53% of asymptomatic (n = 60) samples, corresponding to 55% of the total samples tested (n = 186). The virus was present in all surveyed districts, with UPV infection prevalence of 89% in Rusizi, 75% in Rwamagana, 74% in Karongi, 59% in Nyamagabe, 44% in Nyaruguru, 38% in Kayonza, and 30% in both Gakenke and Rulindo. Fifteen partial coat-protein gene sequences for the Rwandan isolates were obtained. The newly described Rwandan isolates shared 97–99% nucleotide (nt) identity with one another, 89–94% with previously reported Rwandan isolates, 81–97% with Ugandan isolates, and 80–82% with Kenyan UPV isolates, suggesting that the Rwandan virus population is relatively homogenous. Genetic distances among the 15 new UPV isolates and previously reported Rwandan, Ugandan, and Kenyan isolates were very short (0.01–0.03), indicating high sequence similarity. All Rwandan isolates clustered into a single major clade, together with some Ugandan and Kenyan isolates. This close genetic relationship suggests a common ancestry and the regional spread of a single dominant UPV lineage. These findings highlight the need to reinforce seed and planting-material certification systems, as well as the need to enhance farmer capacity through targeted training on viral disease identification and management practices. This is vital to limiting the spread of viral diseases that threaten income security among smallholder passion fruit farmers. Full article