Search Results (308)

Accurate detection of plant leaf diseases is essential for enhancing crop productivity and supporting global food security. In addition to disease classification, understanding how environmental and soil conditions affect model performance is important for developing robust real-world agricultural monitoring systems. Although deep learning (DL) models achieve high accuracy on benchmark datasets, their performance in real-world settings is often limited by variations in illumination, background complexity, and environmental conditions. This study proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants. The framework combines U²-Net-based leaf segmentation with a Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN–Bi-GRU) architecture. MobileNetV2 is employed as the feature extraction backbone to capture spatial characteristics, while Bi-GRU layers model sequential feature dependencies, forming a spatio-temporal network whose architectural design prioritizes parameter efficiency through depthwise separable convolutions and reduced gating complexity. The model was trained and validated using the PlantVillage benchmark dataset and achieved a classification accuracy of 99.8% with a macro-averaged F1-score of 94%, outperforming several state-of-the-art architectures. To assess robustness under real-world conditions, the trained model was further tested on leaf images collected from open-field environments near Eluru, South India. The field evaluation revealed a reduction in classification accuracy to 61.97%, indicating the impact of domain shift and environmental variability. To investigate potential contributing factors, soil parameters, including pH, temperature, moisture, and NPK levels, were monitored using an IoT-based Arduino sensing system over ten consecutive days. Rather than serving as direct inputs to the disease classification model, these environmental measurements were analyzed to assess their potential influence on disease symptom expression and the observed reduction in model performance under field conditions. The results suggest that environmental conditions may influence disease symptom expression and model transferability. This study highlights the importance of integrating DL-based disease recognition with environmental monitoring for reliable field-level agricultural applications. Nevertheless, computational complexity metrics, including inference latency and memory footprint, were not evaluated in the present work and are identified as a priority for future edge deployment studies. Full article

Tomato, as a globally vital economic crop, relies heavily on accurate disease recognition to safeguard food security. However, tomato leaf disease identification constitutes a classic fine-grained visual classification task characterized by minimal inter-class variance, spatially sparse lesion features, and complex background interference. These challenges hinder conventional deep learning models from precisely localizing critical discriminative regions. In response to the aforementioned challenges, we introduce EA-HFA, an innovative framework based on deep neural networks that synergistically integrates an Entropy Attention mechanism alongside a Hierarchical Feature Alignment component. Specifically, the Entropy Attention module leverages information-theoretic entropy to quantify pixel-wise predictive uncertainty, adaptively selecting high-confidence pixels to automatically focus the network on sparse yet highly discriminative lesion features. Concurrently, the Hierarchical Feature Alignment module imposes KL-divergence constraints on the temperature-scaled probability distributions across adjacent network layers, enforcing cross-scale consistency in the localization of discriminative regions. Evaluations conducted on the PlantVillage and AI Challenger 2018 benchmarks reveal that EA-HFA achieves Top-1 accuracies of 99.29% and 97.82%, respectively, yielding performance comparable to established deep learning architectures while maintaining a reasonable computational footprint. Furthermore, qualitative analyses indicate that the model tends to attend to minute lesion-relevant areas, providing a certain level of interpretability for its decision-making process. Thus, EA-HFA holds practical potential as an alternative solution for automated plant disease monitoring in precision farming. Full article

Crop leaf diseases cause 10–40% annual yield losses, yet timely field diagnosis remains difficult. Vision-language models (VLMs) lift recognition accuracy with rich textual descriptions, but multimodal pipelines are too slow for real-time field use because they require text processing at inference. We present MTL-AWL, a framework built on a training–inference asymmetry: VLM text serves as privileged training-time supervision, and two coupled mechanisms—one retaining VLM semantics in the image encoder and one exploiting them—enable image-only deployment at multimodal accuracy. A modal-dropout strategy ($p=0.6$) intermittently masks the VLM text sequence during training, forcing the image encoder to retain cross-modal representations independently. An adaptive multi-task loss jointly optimizes InfoNCE contrastive alignment, attention diversity, and modality consistency under learnable softmax weights, consistently converging to a dominant contrastive weight (55% on soybean, 68% on PlantDoc)—identifying cross-modal alignment as the primary mechanism of VLM knowledge transfer. At inference, the model reaches 818 FPS (3.7× faster than multimodal methods) at only 0.41% accuracy cost, attaining 99.30%/98.89% (multimodal/image-only) on soybean and 72.65%/68.80% on PlantDoc—compact enough for real-time, offline field screening. Full article

Melon (Cucumis melo L.) is a globally significant horticultural crop, characterized by high nutritional value and substantial commercial status. However, frequent outbreaks of powdery mildew severely threaten its yield and fruit quality. Current early detection methods primarily focus on detached leaf assays, which often lack sufficient model generalization. This study proposes a temporal 3D multispectral point cloud reconstruction method for melon plants by integrating multispectral imaging with 3D reconstruction technology. An Artificial Neural Network (ANN) model for 3D spatial light field distribution was developed based on a hemispherical white reference to achieve precise reflectance calibration of the multispectral point clouds. Post-calibration, the coefficient of variation (CV) for the spectral reflectance of the hemispherical reference in 3D space was reduced to less than 2.4%. On this basis, an early classification model for melon powdery mildew was constructed using Partial Least Squares Discriminant Analysis (PLS-DA) based on the mean reflectance spectra of individual plant point clouds. The results demonstrate that the average recognition accuracy reaches 85.94% from 4 days post-inoculation onwards, enabling disease early warning three days in advance. This research provides critical theoretical support and technical reference for the non-destructive early monitoring and precision smart plant protection of crops in facility agriculture. Full article

The emergence of multimodal large language models (MLLMs) is opening a new avenue for explainable and interactive intelligent diagnosis in agriculture. However, generic MLLMs still face two major obstacles in plant disease recognition—insufficient fine-grained visual perception and misalignment between visual and linguistic features—which jointly limit diagnostic accuracy. To address these issues, we propose a Qwen2.5-VL-based full-chain fine-tuning framework termed dual-side synergistic low-rank adaptation. Unlike the mainstream paradigm that freezes the vision encoder, our method injects trainable LoRA adapters into both the vision encoder and the large language model, while establishing end-to-end gradient backpropagation across the entire multimodal pipeline. By using the supervision signal from autoregressive text generation (text-supervised visual learning), the framework directly drives deep optimization of visual representations, thereby enabling coordinated alignment between pixel-level perception and semantic-level understanding. We trained Qwen over CDDM and conducted in-domain (CDDM) and cross-domain (PlantVillage) experiments. The results show that the proposed 7B-parameter model achieves 98.8 and 96.0% diagnostic accuracy under in-domain and cross-domain scenarios, respectively. The recognition accuracy of Qwen in the case of cross-domain only decreases slightly, which demonstrates that the MLLM trained by our method exhibits excellent cross-domain recognition capability. This indicates that our method can significantly improve the robustness and generalization ability of MLLM in complex agricultural scenarios. Full article

Grapevine downy mildew, caused by the oomycete pathogen Plasmopara viticola (P. viticola), is one of the most devastating diseases threatening the global grape industry. The pathogen invades host plants through stomata, triggering a series of highly coordinated physiological disorders and biochemical defense events. This review systematically summarizes the dynamic changes in morphological structures (stomatal characteristics), physiological functions (photosynthesis, membrane system integrity, and carbon metabolism), and multi-level biochemical defense systems (reactive oxygen species (ROS) scavenging enzyme system, phenylpropanoid metabolic pathway, pathogenesis-related proteins, and phenolic compounds) in grapevines following infection. It focuses on analyzing the differences in the timing, intensity, and metabolic reprogramming of defense responses between resistant and susceptible cultivars, pointing out that the essence of disease resistance lies in early pathogen recognition and rapid defense induction. The conflicting conclusions regarding indicators such as soluble sugars, peroxidase (POD), and superoxide dismutase (SOD) are discussed from the perspectives of experimental systems, cultivar genetic backgrounds, and pathogen physiological race differences. Furthermore, the known physiological and biochemical alterations are linked to upstream signaling pathways, including salicylic acid and jasmonic acid (SA/JA), calcium signaling, and mitogen-activated protein kinase (MAPK) cascades. Recent advances in revealing resistance mechanisms in the omics era are also introduced. Finally, future research directions are proposed, including constructing multi-indicator dynamic evaluation models, verifying key gene functions using gene editing, exploring the potential of epigenetic regulation, and developing integrated control strategies combined with microbiome research. This review aims to provide theoretical support for grapevine downy mildew resistance breeding and sustainable disease management. Full article

Extracellular vesicles (EVs) are key mediators of intercellular communication across biological kingdoms, with central roles in immune regulation and disease processes. Despite shared structural features, EVs derived from bacteria, plants, and mammalian cells differ substantially in their biogenesis, molecular composition, and immunological functions. EV formation pathways generate vesicles with distinct cargo profiles, including pathogen-associated molecular patterns (PAMPs) in bacterial EVs, regulatory small RNAs in plant-derived vesicles, and cytokines, microRNAs, and antigen-presenting complexes in mammalian EVs. Differences in cargo result in divergent immune outcomes. Bacterial EVs predominantly activate innate immunity via pattern recognition receptors such as Toll-like receptors, whereas plant-derived EVs exhibit low immunogenicity and mediate cross-kingdom RNA interference. In contrast, mammalian EVs primarily regulate immune responses by modulating antigen presentation and cytokine signaling. These findings support a framework in which EV origin determines immunological function and therapeutic applicability. This perspective highlights the importance of selecting appropriate EV sources for vaccine development, regenerative medicine, and targeted delivery strategies, while addressing current challenges related to heterogeneity, standardization, and safety. Full article

Background/Objectives: Mosquitoes, including Culex quinquefasciatus and Aedes aegypti, are important vectors of dengue fever, Zika virus, West Nile virus, Japanese encephalitis virus, Eastern equine encephalitis virus, etc. Biological control has always been urgent in mosquito prevention due to resistance developing to synthetic insecticides and environmental toxicity by insecticides. Methods: The leaf essential oil of Mosla. chinensis was isolated, and major components were identified via GC-MS, followed by olfactory behavior assays to evaluate its repellent activity against C. quinquefasciatus. Additionally, the odorant-binding protein 1 and odorant-binding protein 2 (CquiOBP1-2) genes were prokaryotically expressed, and their fluorescence competitive binding activities with the active components of essential oils were examined. Results: The bioassays indicated this essential oil greatly repels C. quinquefasciatus, which will significantly protect people against vector-borne diseases. In the fluorescence competitive binding experiments, the CquiOBP1-2 proteins exhibit great binding capacities to volatile components, including Citronellal, Citronellol, Geraniol, Limonene and Isopulegol. Furthermore, the behavioral experimental results also indicate that the mixture of these five ligand compounds has an obvious repellent effect on mosquitoes, highlighting that they may be applied as potential mosquito repellent agents. Moreover, molecular docking and site-directed mutation analysis further confirm Phe123 and Gln77 are both key amino acid residues of CquiOBP1-2 proteins involved in the olfactory recognition of repellent ligand compounds from M. chinensis essential oil. Conclusions: The behavioral experimental verification and the exploration of olfactory molecular mechanisms are helpful to promote the biological control of plant essential oils in mosquito pests. Full article

Plant disease recognition models trained under laboratory conditions often degrade markedly after cross-domain transfer because of the pronounced distribution gap between source and target domains and the scarcity of labeled target-domain samples. To address the transfer task from PlantVillage (PV_100) to PlantDoc, this study develops and evaluates a lightweight cross-domain few-shot plant disease recognition method under a strict PlantVillage-to-PlantDoc protocol. The method integrates EfficientNet-B0 feature extraction, cosine-similarity-based prototypical classification, and training-time target-domain BN adaptation (TBA). During training, unlabeled target-domain images are used only for BN statistical calibration, whereas inference is limited to feature extraction and prototype matching, without gradient updates or iterative optimization. Under a unified experimental protocol, the proposed method achieved cross-split mean accuracies of 42.69 ± 0.62% for one-shot and 54.24 ± 0.72% for five-shot, where ± denotes the standard deviation across three strict data splits; it outperformed ProtoNet by 7.44 and 9.43 percentage points, respectively. Ablation results indicate that TBA is the main source of performance improvement, whereas more complex adaptation strategies do not yield stable additional gains. The core encoder can be executed entirely on the NPU, with an estimated single-sample inference latency as low as 0.658 ms, indicating strong potential for encoder-level mobile deployment. Full article

Bacteriophages infecting phytopathogenic bacteria represent promising alternatives for plant disease control; however, some groups, such as filamentous bacteriophages, remain comparatively underexplored. In this study, we present a comprehensive characterization of XaF13, a filamentous bacteriophage that infects Xanthomonas vesicatoria, the causal agent of bacterial spot disease in pepper. Morphological analysis revealed a flexible filamentous virion architecture consistent with members of the family Inoviridae. To refine its genomic features, the XaF13 genome was resequenced through a hybrid approach combining newly generated Oxford Nanopore long reads with previously available Illumina data, resulting in a revised genome of 6965 bp. Comparative genomic analysis and intergenomic similarity assessment revealed low nucleotide identity with related inoviruses, supporting the recognition of XaF13 as a putative novel species based on VIRIDIC species-level thresholds. Phylogenetic reconstruction based on the Zot-like protein placed XaF13 within a broader inovirus lineage and showed that it forms a distinct evolutionary branch. In addition, physicochemical assays revealed that XaF13 remains stable across a broad pH range and tolerates brief exposure to elevated temperatures, whereas chloroform treatment and UV-C radiation reduced viral infectivity over time. Overall, these findings highlight the genomic distinctiveness and in vitro physicochemical stability of XaF13, contribute to a better understanding of filamentous bacteriophage diversity and provide a basis for future studies on its ecological role and possible interactions with phytopathogenic bacteria. Full article

Background: Toddaliae Asiaticae Radix (TA) boasts a long history of medicinal application. However, origin traceability and quality assessment of the widely distributed original plant Toddalia asiatica have not been fully elucidated. Methods: A hybrid framework integrating targeted metabolomics, network pharmacology (NP), and machine learning (ML) was established. By optimizing key parameters, a high-coverage and rapid method for multiple categories compounds was developed using ultra-high performance liquid chromatography-multiple reaction monitoring tandem mass spectrometry (UPLC-MRM MS/MS). Using samples collected across 16 geographical regions, redundancy analysis (RDA) and pattern recognition techniques were applied to explore environment-sensitive metabolites. Taking into account five types of diseases, NP analysis was employed to obtain the bioactive components and their contribution weight in disease treatment. Subsequently, core Quality Markers (Q-Markers) with dual functions of responsive to geographic variations and biologically relevant to therapeutic efficacy were figured out, and were used to establish origin scoring model and discrimination model. Results: The geographical metabolic characteristics of the TA from broad regions in China were thoroughly analyzed, and 60 geographically sensitive compounds were identified. Through NP analysis, 27 core Q-Markers were locked. The bioactivity-weighted scoring model based on Q-Markers revealed the consistency of regional rankings as well as minor fluctuations across five diseases. ML demonstrated that the Q-Markers preserved regional discrimination performance, and the introducing of practical-oriented weights enhanced overall discriminative confidence. Conclusions: This research decodes the Geographical metabolic characteristics of TA, and highlights the necessity of function-oriented prioritization of drug resources. 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

Crop disease diagnosis can be degraded by structured cast shadows, including panel-like strip shadows that motivate applications in agrivoltaic-style farming. This paper presents ShadowFormer-AV, a transformer-based framework that adapts general shadow-robust visual learning to crop disease classification by separating disease evidence from illumination interference. The proposed approach combines a soft shadow-prior extractor, an illumination-decoupled dual-stream token encoder, lesion-preserving adaptive attention, and a cross-view consistency objective between original and shadow-perturbed images. The method uses only standard RGB inputs and does not require shadow-free reference images, multispectral sensing, or pixel-level shadow annotation. We evaluated the framework on publicly available plant disease datasets using calibrated panel-like synthetic shadows and a naturally shadowed PlantDoc subset. Because no on-site agrivoltaic disease dataset was used, the conclusions were limited to shadow robustness under these simulated and naturally shadowed test conditions rather than verified performance under real photovoltaic-panel shadows. Within this validation boundary, ShadowFormer-AV improved accuracy, Macro-F1, and calibration over representative convolutional and transformer baselines, suggesting that illumination-aware token learning is useful for crop disease recognition under structured shadow interference. Full article

In the field of smart plant protection, accurate early monitoring of winged aphids is critical, as it enables the interruption of viral disease transmission and reduces dependence on pesticides. In response to the core challenges of low efficiency in manual counting associated with current sticky trap-based monitoring, as well as the insufficient recognition accuracy and poor robustness of computer vision models in dense small-target scenarios, this study aims to develop a high-precision, highly reliable automated identification method for winged aphids. To achieve this, a specialized detection model named PCSNet is proposed. Based on YOLOv12, this model innovatively incorporates a coordinate attention mechanism to enhance the perception of spatial structures for small targets. Simultaneously, a shallow feature enhancement branch (SFEB) is introduced to enrich detailed information, and the Normalized Wasserstein Distance loss function is integrated to optimize bounding box regression. Comparative experiments conducted on a self-constructed dataset of sticky trap images encompassing complex field backgrounds demonstrate that the PCSNet model achieves optimal detection performance, with a mean average precision (mAP) of 0.791 and a precision of 0.866, significantly outperforming mainstream detection models and various attention mechanism variants. This research provides an effective technical solution for constructing a real-time and automated intelligent pest monitoring system, offering substantial application value for advancing the intelligent transformation of pest and disease monitoring and promoting practices in green prevention and control. Full article

Early and reliable detection of rose diseases is important for automating plant monitoring and timely intervention throughout the crop lifecycle. In this context, leaf-image analysis combined with machine learning offers a practical approach for disease detection in roses. This study tests a binary classification framework that distinguishes diseased leaves using convolutional neural networks (CNNs). Three architectures were evaluated: a lightweight CNN trained from scratch as a baseline model, and two residual network models fine-tuned through transfer learning from weights pretrained on a large-scale visual recognition dataset. To assess robustness, two preprocessing strategies were also compared: a lightweight hue-based leaf isolation method that preserves full color information, and a grayscale conversion approach without masking. Experimental results obtained on a small held-out test set show strong classification performance across all evaluated models. At the same time, the findings indicate that additional validation is needed on more diverse datasets to confirm generalization under varying lighting conditions, background complexity, and plant growth stages. The results support the feasibility of CNN-based disease detection for roses and highlight its potential for integration into automated monitoring workflows. Full article