Search Results (48)

In recent years, significant advancements in artificial intelligence, particularly in the field of deep learning, have increasingly been integrated into agricultural applications, including critical processes such as disease detection. Tomato, being one of the most widely consumed agricultural products globally and highly susceptible to a variety of fungal, bacterial, and viral pathogens, remains a prominent focus in disease detection research. In this study, we propose a deep learning-based approach for the detection of tomato diseases, a critical challenge in agriculture due to the crop’s vulnerability to fungal, bacterial, and viral pathogens. We constructed an original dataset comprising 6414 images captured under real production conditions, categorized into three image types: leaves, green tomatoes, and red tomatoes. The dataset includes five classes: healthy samples, late blight, early blight, gray mold, and bacterial cancer. Twenty-one deep learning models were evaluated, and the top five performers (EfficientNet-b0, NasNet-Large, ResNet-50, DenseNet-201, and Places365-GoogLeNet) were selected for feature extraction. From each model, 1000 deep features were extracted, and feature selection was conducted using MRMR, Chi-Square (Chi²), and ReliefF methods. The top 100 features from each selection technique were then used for reclassification with traditional machine learning classifiers under five-fold cross-validation. The highest test accuracy of 92.0% was achieved with EfficientNet-b0 features, Chi² selection, and the Fine KNN classifier. EfficientNet-b0 consistently outperformed other models, while the combination of NasNet-Large and Wide Neural Network yielded the lowest performance. These results demonstrate the effectiveness of combining deep learning-based feature extraction with traditional classifiers and feature selection techniques for robust detection of tomato diseases in real-world agricultural environments. Full article

Real-time detection of tomato pests and diseases is essential for precision agriculture, as it requires high accuracy, speed, and energy efficiency of edge-computing agricultural robots. This study proposes AgriLiteNet (Lightweight Networks for Agriculture), a lightweight neural network integrating MobileNetV3 for local feature extraction and a streamlined Swin Transformer for global modeling. AgriLiteNet is further enhanced by a lightweight channel–spatial mixed attention module and a feature pyramid network, enabling the detection of nine tomato pests and diseases, including small targets like spider mites, dense targets like bacterial spot, and large targets like late blight. It achieves a mean average precision at an intersection-over-union threshold of 0.5 of 0.98735, which is comparable to Suppression Mask R-CNN (0.98955) and Cas-VSwin Transformer (0.98874), and exceeds the performance of YOLOv5n (0.98249) and GMC-MobileV3 (0.98143). With 2.0 million parameters and 0.608 GFLOPs, AgriLiteNet delivers an inference speed of 35 frames per second and power consumption of 15 watts on NVIDIA Jetson Orin NX, surpassing Suppression Mask R-CNN (8 FPS, 22 W) and Cas-VSwin Transformer (12 FPS, 20 W). The model’s efficiency and compact design make it highly suitable for deployment in agricultural robots, supporting sustainable farming through precise pest and disease management. Full article

As an important economic crop, tomato is highly susceptible to diseases that, if not promptly managed, can severely impact yield and quality, leading to significant economic losses. Traditional diagnostic methods rely on expert visual inspection, which is not only laborious but also prone to subjective bias. In recent years, object detection algorithms have gained widespread application in tomato disease detection due to their efficiency and accuracy, providing reliable technical support for crop disease identification. In this paper, we propose an improved tomato leaf disease detection method based on the YOLOv10n algorithm, named BED-YOLO. We constructed an image dataset containing four common tomato diseases (early blight, late blight, leaf mold, and septoria leaf spot), with 65% of the images sourced from field collections in natural environments, and the remainder obtained from the publicly available PlantVillage dataset. All images were annotated with bounding boxes, and the class distribution was relatively balanced to ensure the stability of training and the fairness of evaluation. First, we introduced a Deformable Convolutional Network (DCN) to replace the conventional convolution in the YOLOv10n backbone network, enhancing the model’s adaptability to overlapping leaves, occlusions, and blurred lesion edges. Second, we incorporated a Bidirectional Feature Pyramid Network (BiFPN) on top of the FPN + PAN structure to optimize feature fusion and improve the extraction of small disease regions, thereby enhancing the detection accuracy for small lesion targets. Lastly, the Efficient Multi-Scale Attention (EMA) mechanism was integrated into the C2f module to enhance feature fusion, effectively focusing on disease regions while reducing background noise and ensuring the integrity of disease features in multi-scale fusion. The experimental results demonstrated that the improved BED-YOLO model achieved significant performance improvements compared to the original model. Precision increased from 85.1% to 87.2%, recall from 86.3% to 89.1%, and mean average precision (mAP) from 87.4% to 91.3%. Therefore, the improved BED-YOLO model demonstrated significant enhancements in detection accuracy, recall ability, and overall robustness. Notably, it exhibited stronger practical applicability, particularly in image testing under natural field conditions, making it highly suitable for intelligent disease monitoring tasks in large-scale agricultural scenarios. Full article

This study aimed to investigate the biocontrol activity of rhizosphere isolates against late blight disease of tomatoes caused by the fungus Phytophthora infestans. A total of 30 rhizospheric bacterial isolates were evaluated for their antagonistic activity against P. infestans in vitro and in vivo. The results demonstrated that among the 30 isolates tested, six (RS65, RP6, RS47, RS46, RP2, and RS61) exhibited a highly significant inhibitory effect (p < 0.001) on the mycelial growth of P. infestans in vitro, with the inhibition rate exceeding 67%. Among the isolates, RS65 exhibited the highest inhibition rate at 78.48%. For antagonistic mechanisms, the results demonstrated that the six isolates exhibited significant enzymatic activity, including proteolytic, lipolytic, and chitinolytic activity, as well as the production of HCN, cellulase, and pectinase. Isolate RS65, which showed the highest inhibition rate, was further evaluated under greenhouse conditions. This investigation revealed significant differences in the severity of late blight between the control and the RS65 treatment. The control showed a severity level of 31.26%, whereas the RS65 treatment achieved the lowest severity of 16.54%. Molecular identification results indicated that the RS65 isolate (accession numbers PV208381) is a Bacillus genus with 99% proximity to Bacillus velezensis. This finding suggests that the Bacillus RS65 treatment could provide effective protection against P. infestans infection in tomato plants. These findings highlight the potential of Bacillus RS65 as a biocontrol agent in integrated disease management for tomato late blight. Full article

Plant diseases pose significant economic challenges and may lead to ecological consequences. Although plant pathologists have a significant ability to diagnose plant diseases, rapid, accurate, and early diagnosis of plant diseases by intelligent systems could improve disease control and management. This study evaluates six efficient classification models (classifiers) based on deep learning to detect common tomato diseases by analyzing symptomatic patterns on leaves. Additionally, group learning techniques, including simple and weighted majority voting methods, were employed to enhance classification performance further. Six tomato leaf diseases, including Pseudomonas syringae pv. syringae bacterial spot, Phytophthora infestance late blight, Cladosporium fulvum leaf mold, Septoria lycopersici Septoria leaf spot, Corynespora cassiicola target spot, and Alternaria solani early blight, as well as healthy leaves, resulting in a total of seven classes, were utilized for the classification. Deep learning models, such as convolutional neural networks (CNNs), GoogleNet, ResNet-50, AlexNet, Inception v3, and MobileNet, were utilized, achieving classification accuracies of 65.8%, 84.9%, 93.4%, 89.4%, 93.4%, and 96%, respectively. Furthermore, applying the group learning approaches significantly improved the results, with simple majority voting achieving a classification accuracy of 99.5% and weighted majority voting achieving 100%. These findings highlight the effectiveness of the proposed deep ensemble learning models in accurately identifying and classifying tomato diseases, featuring their potential for practical applications in tomato disease diagnosis and management. Full article

Late blight is a destructive disease affecting tomato production. The identification and characterization of resistance (R) genes are critical for the breeding of late blight-resistant cultivars. The incompletely dominant gene Ph-2 confers resistance against the race T₁ of Phytophthora infestans in tomatoes. Herein, we identified Solyc10g085460 (RGA1) as a candidate gene for Ph-2 through the analysis of sequences and post-inoculation expression levels of genes located within the fine mapping interval. The RGA1 was subsequently validated to be a Ph-2 gene through targeted knockout and complementation analyses. It encodes a CC-NBS-LRR disease resistance protein, and transient expression assays conducted in the leaves of Nicotiana benthamiana indicate that Ph-2 is predominantly localized within the nucleus. In comparison to its susceptible allele (ph-2), the transient expression of Ph-2 can elicit hypersensitive responses (HR) in N. benthamiana, and subsequent investigations indicate that the structural integrity of the Ph-2 protein is likely a requirement for inducing HR in this species. Furthermore, ethylene and salicylic acid hormonal signaling pathways may mediate the transmission of the Ph-2 resistance signal, with PR1- and HR-related genes potentially involved in the Ph-2-mediated resistance. Our results could provide a theoretical foundation for the molecular breeding of tomato varieties resistant to late blight and offer valuable insights into elucidating the interaction mechanism between tomatoes and P. infestans. Full article

To increase biodiversity in tomato cultivation, two herbal aromatic plants, thyme (Thymus vulgaris) and basil (Ocimum basilicum L.), were introduced as companion plants. Their role was to improve crop plant growth and stress resistance. Moreover, the effect of the soil application of Trichoderma microbial preparations on tomato growth parameters and yield, in combination with companion plants, was studied. Ligno-cellulose multi-layer microcapsules with Trichoderma atroviride TRS14 spores (MIC14) and the commercial preparation Trianum G (TG) were used as microbial preparations. This experiment was carried out in a certified organic field. Tomato plants were intercropped with thyme or basil in the arrangement of two tomato rows alternating with one herbal row. In all intercropping arrangements and in the control (tomato plants grown without herbs), subplots were sectioned. The soil in the subplots was amended with the MIC14 and TG preparations used at a concentration of 10⁴ spores g⁻¹ of the soil and planted with tomato transplants. No control measures were applied during tomato growing, and the plants were naturally infected with late blight. Tomato plant growth parameters and yield were assessed, and late blight severity was monitored. The degree of soil colonization by Trichoderma fungi and the effect of these applications on soil microbial activity and biodiversity (dehydrogenases activity, EcoPlates AWCD, and Shannon index) were evaluated. The results clearly showed a significant influence of thyme and basil on tomato growth and yield in organic production. The cultivation of thyme adjacent to tomatoes had a beneficial effect on the development of the root system and the number of flowers and fruits on the crop plants. Basil, on the other hand, clearly decreased tomato yield and adversely affected the effect of Trichoderma applications by reducing root system development. Moreover, basil as a companion plant increased late blight symptoms. Both Trichoderma strains colonized soil, but they had no significant effect on the microbial activity or metabolic potential measured on the EcoPlates with the use of the BIOLOG system. However, a decrease in dehydrogenases activity was noted. In organic cultivation, the Trichoderma preparations used had no significant effect on tomato yield, opposite to its increase in integrated tomato production. Full article

Some strains of Bacillus vallismortis have been reported to be efficient biocontrol agents against tomato pathogens. The aim of our study was to assess the biocontrol ability of the endophytic strain BL01 Bacillus vallismortis through in vitro and field trials, as well as to verify its plant colonization ability and analyze the bacterial genome in order to find genes responsible for the biocontrol activity. We demonstrated in a gnotobiotic system and by confocal laser microscopy that the endophytic strain BL01 was able to colonize the endosphere and rhizosphere of tomato, winter wheat and oilseed rape. In vitro experiments demonstrated the inhibition activity of BL01 against a wide range of phytopathogenic fungi and bacteria. BL01 showed biological efficacy in two-year field experiments with tomato plants against black bacterial spotting by 40–70.8% and against late blight by 47.1% and increased tomato harvest by 24.9% or 10.9 tons per hectare compared to the control. Genome analysis revealed the presence of genes that are responsible for the synthesis of biologically active secondary metabolites, which could be responsible for the biocontrol action. Strain BL01 B. vallismortis can be considered an effective biocontrol agent to control both fungal and bacterial diseases in tomato plants. Full article

Plant pathologies significantly jeopardise global food security, necessitating the development of prompt and precise diagnostic methods. This study employs advanced deep learning techniques to evaluate the performance of nine convolutional neural networks (CNNs) in identifying a spectrum of phytosanitary issues affecting the foliage of Solanum lycopersicum (tomato). Ten thousand RGB images of leaf tissue were subsampled in training (64%), validation (16%), and test (20%) sets to rank the most suitable CNNs in expediting the diagnosis of plant disease. The study assessed the performance of eight well-known networks under identical hyperparameter conditions. Additionally, it introduced the GamaNNet architecture, a custom-designed model optimised for superior performance on this specific type of dataset. The investigational results were most promising for the innovative GamaNNet and ResNet-152, which both exhibited a 91% accuracy rate, as evidenced by their confusion matrices, ROC curves, and AUC metrics. In comparison, LeNet-5 and ResNet-50 demonstrated lower assertiveness, attaining accuracies of 74% and 69%, respectively. GoogLeNet and Inception-v3 emerged as the frontrunners, displaying diagnostic preeminence, achieving an average F1-score of 97%. Identifying such pathologies as Early Blight, Late Blight, Corynespora Leaf Spot, and Septoria Leaf Spot posed the most significant challenge for this class of problem. Full article

Accurate identification of plant diseases is a critical task in agricultural production. The existing deep learning crop disease recognition methods require a large number of labeled images for training, limiting the implementation of large-scale detection. To overcome this limitation, this study explores the application of self-supervised learning (SSL) in plant disease recognition. We propose a new model that combines a masked autoencoder (MAE) and a convolutional block attention module (CBAM) to alleviate the harsh requirements of large amounts of labeled data. The performance of the model was validated on the CCMT dataset and our collected dataset. The results show that the improved model achieves an accuracy of 95.35% and 99.61%, recall of 96.2% and 98.51%, and F1 values of 95.52% and 98.62% on the CCMT dataset and our collected dataset, respectively. Compared with ResNet50, ViT, and MAE, the accuracies on the CCMT dataset improved by 1.2%, 0.7%, and 0.8%, respectively, and the accuracy of our collected dataset improved by 1.3%, 1.6%, and 0.6%, respectively. Through experiments on 21 leaf diseases (early blight, late blight, leaf blight, leaf spot, etc.) of five crops, namely, potato, maize, tomato, cashew, and cassava, our model achieved accurate and rapid detection of plant disease categories. This study provides a reference for research work and engineering applications in crop disease detection. Full article

Foliar diseases are the significant production constraints in tomatoes. Among them, foliar fungal diseases in tomatoes, such as early blight (Alternaria linaria), Septoria leaf spot (Septoria lycopersici), and late blight (Phytophthora infestans), which is oomycetes, have higher economic significance. This paper will discuss the etiology, host range, distribution, symptoms, and disease cycle to help us understand the biology, followed by management approaches emphasizing the resistance breeding approach for these diseases. We provide an analytical review of crop improvement efforts, including conventional and molecular methods for improving these diseases’ resistance. We discuss the importance of modern breeding tools, including genomics, genetic transformation, and genome editing, to improve the resistance to these diseases in the future. Full article

Late blight is a destructive disease of solanaceous crops such as tomato (Solanum lycopersicum L.), caused by the Oomycete Phytophthora infestans (Mont.) de Bary. Late blight is generally controlled by fungicide applications, which quickly become ineffective due to the appearance of new P. infestans genotypes that can overcome the resistance of improved tomato cultivars and cause total production losses. The aim of this study is to assess the resistance level of tomato cultivars under controlled conditions and inoculations were carried out on detached leaflets (cvs. Trakia, Saint Pierre and Marmande) using inoculums of the major P. infestans clonal lineages found in Algeria such as EU_13_A2 (n = 1), EU_23_A1 (n = 2) and EU_2_A1 (n = 1) (three replicates of each isolate). This investigation showed that the choice of resistant cultivars can help control late blight and provide economic and environmental advantages by reducing the use of inputs. Full article

Late blight, caused by the oomycete Phytophthora infestans, is one of the most important diseases affecting tomato and potato production worldwide. In Thailand, the disease is widespread in the north and northeast, especially in the Chiang-Mai and Tak provinces. The mating type, metalaxyl sensitivity, mitochondrial DNA (mtDNA) haplotype, RG57 fingerprinting, and microsatellite were used to characterize the P. infestans populations. The study revealed that the P. infestans of tomato isolates in Thailand are of the same lineage as those from 1994 until 2002. The clonal lineages that were found in the potato populations have changed since 1994. The changes in P. infestans isolates in the potato populations have likely been the result of the import of seed potatoes to Thailand. Furthermore, the P. infestans populations in potatoes show resistance to metalaxyl, whereas those from tomato isolates show sensitivity to fungicides. The reasons for the different responses can be attributed to (i) the use of metalaxyl, (ii) the host preferences of P. infestans, and (iii) the migration of new genotypes from infected potato seeds. Full article

Mancozeb (MZ) is a broadly used fungicide for the control of plant diseases, including late blight in potatoes caused by the oomycete Phytophthora infestans (Mont.) De Bary. MZ has been banned for agricultural use by the European Union as of January 2022 due to its hazards to humans and the environment. In a search for replacement fungicides, twenty-seven registered anti-oomycete fungicidal preparations were evaluated for their ability to mitigate the threat of this disease. Fourteen fungicides provided good control (≥75%) of late blight in potted potato and tomato plants in growth chambers. However, in Tunnel Experiment 1, only three fungicides provided effective control of P. infestans in potatoes: Cyazofamid (Ranman, a QiI inhibitor), Mandipropamid (Revus, a CAA inhibitor), and Oxathiapiprolin + Benthiavalicarb (Zorvek Endavia, an OSBP inhibitor + CAA inhibitor). In Tunnel Experiment 2, these three fungicides were applied at the recommended doses at 7-, 9-, and 21-day intervals, respectively, totaling 6, 4, and 2 sprays during the season. At 39 days post-inoculation (dpi), control efficacy increased in the following order: Zorvec Endavia > Ranman > Revus > Mancozeb. Two sprays of Zorvec Endavia were significantly more effective in controlling the blight than six sprays of Ranman or four sprays of Revus. We, therefore, recommend using these three fungicides as replacements for mancozeb for the control of late blight in potatoes. A spray program that alternates between these three fungicides may be effective in controlling the disease and also in avoiding the build-up of resistance in P. infestans to mandipropamid and oxathiapiprolin. Full article

New solutions to reduce the use of chemical pesticides to combat plant diseases and to meet societal and political demands are needed to achieve sustainable agriculture. Tomato production, both in greenhouses and in open fields, is affected by numerous pathogens. The aim of this study is to assess the possibility of controlling both late blight and powdery mildew in tomatoes with a single biocontrol product currently under registration. The biocontrol product AXP12, based on the lysate of Willaertia magna C2c Maky, has already proved its efficacy against downy mildew of grapevine and potato late blight. Its ability to elicit tomato defenses and its efficacy in the greenhouse and in the field were tested. This study establishes that AXP12 stimulates the tomato genes involved in plant defense pathways and has the capacity to combat in greenhouse and field both late blight (Phytophtora infestans) and powdery mildew (Oidium neolycopersici and Leveillula taurica) of tomato. Full article