Grape Leaves Research Articles

Transcriptomic analysis of the defense response in "Cabernet Sauvignon" grape leaf induced by Apolygus lucorum feeding.

To investigate the molecular mechanism of the defense response of "Cabernet Sauvignon" grapes to feeding by Apolygus lucorum, high-throughput sequencing technology was used to analyze the transcriptome of grape leaves under three different treatments: feeding by A. lucorum, puncture injury, and an untreated control. The research findings indicated that the differentially expressed genes were primarily enriched in three aspects: cellular composition, molecular function, and biological process. These genes were found to be involved in 42 metabolic pathways, particularly in plant hormone signaling metabolism, plant-pathogen interaction, MAPK signaling pathway, and other metabolic pathways associated with plant-induced insect resistance. Feeding by A. lucorum stimulated and upregulated a significant number of genes related to jasmonic acid and calcium ion pathways, suggesting their crucial role in the defense molecular mechanism of "Cabernet Sauvignon" grapes. The consistency between the gene expression and transcriptome sequencing results further supports these findings. This study provides a reference for the further exploration of the defense response in "Cabernet Sauvignon" grapes by elucidating the expression of relevant genes during feeding by A. lucorum.

Grape leaf disease detection using image processing and CNN

Grape leaf disease detection using image processing and CNN

IMAGE CLASSIFICATION OF VINE LEAF DISEASES USING COMPLEX-VALUED NEURAL NETWORK

Leaf diseases are a serious challenge in the agricultural industry affecting crop quality and yield especially in grapevines. Early recognition and classification of grape leaf diseases is crucial to enable farmers to take appropriate preventive measures in maintaining the health of their crops. The research utilized an innovative approach based on Complex-Valued Neural Network (CVNN) to address the problem. Using Complex-Valued Neural Network (CVNN) this research seeks to identify and classify grape leaf diseases through a series of experiments. A total of 100 images divided into 4 classes namely Black Rot, ESCA, Leaf Blight, and Healthy were collected to train the model. The results show that the trained CVNN model successfully achieved a training accuracy of 100% and a testing accuracy of 97%, demonstrating excellent performance in classifying grape leaf diseases. This states that the proposed approach has great potential to be an effective tool in helping growers manage their vineyards more efficiently and effectively. The developed image processing method is expected to be applied in designing a system to perform image classification of diseases on grape leaves.

Fourier Domain Adaptation for the Identification of Grape Leaf Diseases

With the application of computer vision in the field of agricultural disease recognition, the convolutional neural network is widely used in grape leaf disease recognition and has achieved remarkable results. However, most of the grape leaf disease recognition models have the problem of weak generalization ability. In order to overcome this challenge, this paper proposes an image identification method for grape leaf diseases in different domains based on Fourier domain adaptation. Firstly, Fourier domain adaptation is performed on the labeled source domain data and the unlabeled target domain data. To decrease the gap in distribution between the source domain data and the target domain data, the low-frequency spectrum of the source domain data and the target domain data is swapped. Then, three convolutional neural networks (AlexNet, VGG13, and ResNet101) were used to train the images after style changes and the unlabeled target domain images were classified. The highest accuracy of the three networks can reach 94.6%, 96.7%, and 91.8%, respectively, higher than that of the model without Fourier transform image training. In order to reduce the impact of randomness, when selecting the transformed image, we propose using farthest point sampling to select the image with low feature correlation for the Fourier transform. The final identification result is also higher than the accuracy of the network model trained without transformation. Experimental results showed that Fourier domain adaptation can improve the generalization ability of the model and obtain a more accurate grape leaf disease recognition model.

Using wood rings to determine age and climate constraints of grapevine (Vitis vinifera) radial growth

Summary Grapevine (Vitis vinifera) is the most widely cultivated and economically relevant crop in the world, but its productivity is menaced by aridification in some wine-growing regions such as the Mediterranean Basin. The impacts of climate on vines depend on regional conditions, cultivar, and vine age, among other factors. Hence, a better understanding of vine radial-growth responses to climate in different regions is sorely needed. First, we related climate data and drought severity with a long-term series of vine leaf unfolding from NE Spain to test if climate warming is advancing the onset of the growing season. Second, we used growth rings to estimate age and quantify climate-growth relationships of vines using dendrochronology. Three sites from different designations of origin and vine varieties were studied: Logroño in northern Spain (La Rioja, Tempranillo), San Martín del Río in northeast Spain (Calatayud, Garnacha) and Anzi in southern Italy (Aglianico, Aleatico). Vine leaf unfolding occurred earlier as winter-spring conditions were warmer and drier. Vine ages ranged between 16 (Logroño, Anzi) and 56 years (S. Martín del Río), and growth rates declined in the two youngest grapevines. Ring widths varied between 1.19 (S. Martín del Río) and 1.80 mm (Logroño), with Anzi showing intermediate values (1.37 mm). February precipitation enhanced vine growth in San Martín del Río () and Anzi (), whereas the correlation with soil moisture peaked in March in San Martín del Río (). Vine growth rates positively responded to September minimum temperatures in San Martín del Río () and Logroño (). Garnacha cultivar in San Martín del Río showed the highest responsiveness to water availability. Therefore, similar old grapevines from continental, seasonally dry areas could be the most negatively affected by future warmer and drier climate conditions.

Grape Leaf Disease Identification and Classification using Deep Learning

In the Indian agricultural context, where crop quality profoundly influences farmers' profits, safeguarding crops from potential threats is paramount. Our proposed solution employs deep learning, specifically Convolutional Neural Networks (CNNs), to detect and classify grape leaf conditions accurately. By analysing image datasets, our system efficiently predicts grape leaf disorders and provides actionable recommendations. Through training the CNN with publicly available plant disease images and employing various visualization methods, we observed that neural networks can effectively mimic human decision-making processes in diagnosing issues, thus holding promise for enhancing agricultural practices and minimizing crop losses in the future

PLANTS LEAF DISEASES DETECTION USING DEEP LEARNING

Agriculture field has a high impact on our life. Agriculture is the most important sector of our Economy. Proper management leads to a profit in agricultural products. Farmers do not expertise in leaf disease, so they produce less production. Plant leaf diseases detection is the important because profit and loss are depending on production. CNN is the solution for leaf disease detection and classification. Main aim of this research is to detect the apple, grape, corn, potato and tomato plants leaf diseases. Plant leaf diseases are monitoring of large fields of crops disease detection, and thus automatically detected some feature of diseases as per that provide medical treatment. Proposed Deep CNN model has been compared with popular transfer learning approach such as VGG16. Plant leaf disease detection has wide range of applications available in various fields such as Biological Research and in Agriculture Institute. Plant leaf disease detection is the one of the required research topics as it may prove benefits in monitoring large fields of crops, and thus automatically detect the symptoms of diseases as soon as they appear on plant leaves. Key Words: Diseases, CNN, Deep Learning

Multiclass classification of diseased grape leaf identification using deep convolutional neural network(DCNN) classifier

The cultivation of grapes encounters various challenges, such as the presence of pests and diseases, which have the potential to considerably diminish agricultural productivity. Plant diseases pose a significant impediment, resulting in diminished agricultural productivity and economic setbacks, thereby affecting the quality of crop yields. Hence, the precise and timely identification of plant diseases holds significant importance. This study employs a Convolutional neural network (CNN) with and without data augmentation, in addition to a DCNN Classifier model based on VGG16, to classify grape leaf diseases. A publicly available dataset is utilized for the purpose of investigating diseases affecting grape leaves. The DCNN Classifier Model successfully utilizes the strengths of the VGG16 model and modifies it by incorporating supplementary layers to enhance its performance and ability to generalize. Systematic evaluation of metrics, such as accuracy and F1-score, is performed. With training and test accuracy rates of 99.18 and 99.06%, respectively, the DCNN Classifier model does a better job than the CNN models used in this investigation. The findings demonstrate that the DCNN Classifier model, utilizing the VGG16 architecture and incorporating three supplementary CNN layers, exhibits superior performance. Also, the fact that the DCNN Classifier model works well as a decision support system for farmers is shown by the fact that it can quickly and accurately identify grape diseases, making it easier to take steps to stop them. The results of this study provide support for the reliability of the DCNN classifier model and its potential utility in the field of agriculture.

Bioactive extracts from grape (Vitis vinifera L. cv. País) leaves: Characterization and encapsulation in poly-3-hydroxybutyrate-co-3-valerate microparticles

Vitis vinifera var. L. País leaf extract, previously characterized, was microencapsulated by emulsion-solvent evaporation method using two different procedures: the conventional dropwise and micromixer device. The poly-3-hydroxybutyrate-co-3-hydroxyvalerate (PHBV) was used as encapsulating polymer. In addition, the effect of extraction time and ethanol:water ratio on the yield and the content of bioactive compounds of grape leaf extract obtained by Soxhlet method was determined using the face-centered central composite design. The highest bioactive compound were obtained using a 70:30 ethanol:water solvent ratio during 4 cycles. This extract is mainly composed of cinnamic acid, quercetin-3-glucoside and quercetin-3-glucorinide, containing 3.56, 2.08 and 1.19 mg g−1 extract, respectively. The total polyphenol content determined by Folin Ciocalteu method was 164 ± 14 mg GAE g−1 extract. The microparticles (2–3 μm) had spherical shape with rough and porous surface. The encapsulation efficiency was 15.1% and 60.6% for the PHBV microparticles prepared using conventional dropwise and micromixer device, respectively. The antioxidant activity present in the original extract was preserved around 50%–80% and 20%–70% in the loaded microparticles. The best results were achieved when grape leaf extract was encapsulated using micromixer device. The cell viability assay in 3T3-L1 fibroblasts, showed that loaded microparticles are not cytotoxic. In conclusion micromixer device showed to be effective for the microencapsulation of grape leaf extract using PHBV as encapsuling polymer.

Optimization of vortex-assisted magnetic nanofluid based liquid phase microextraction for fast, green and reliable extraction of ibuprofen from real samples: Multivariate approach

In this research, the vortex-assisted magnetic nanofluid based liquid phase microextraction (VA-MNF-LPME) procedure was optimized using Box–Behnken Design (BBD) for the selective and reliable extraction of ibuprofen from aqueous solutions. Three MNFs were prepared and tested for the selective extraction of ibuprofen. Ultraviolet–visible spectrophotometry (UV–Vis) was used to determine the amount of ibuprofen and measurements were made at a wavelength of 238 nm. The effects of pH, MNF volume, vortex time, volume of back extraction solvent were optimized using BBD. Separation of the MNF phase containing the ibuprofen in aqueous solution was achieved using a neodymium magnet without the need for centrifugation step. Using optimized parameters (pH = 3.4, 690 μL of MNF, 100 s vortex and 230 μL of ethanol), the detection limit and working range of the V-MNF-LPME procedure were 0.6 ng mL−1 and 2–180 ng mL−1, respectively. Relative standard deviations and recovery (for 25 ng mL−1 of ibuprofen solution, N = 5) were 2.8% and 94.1%. Key validation parameters of the method were studied in detail and calculated under optimized conditions. The VA-MNF-LPME procedure was successfully applied to some drugs, baby lettuce and grape leaf samples in ten stages with a standard-addition approach, and quantitative recoveries were obtained (91.4–98.7%).

基于改进YOLOv8s的实时葡萄病害检测模型

This research is dedicated to enhancing the accuracy and processing speed of grape disease recognition. As a result, a real-time grape disease detection model named MSCI-YOLOv8s, based on an improved YOLOv8s framework is proposed. The primary innovation of this model lies in replacing the backbone network of the original YOLOv8s with the more efficient MobileNetV3. This alteration not only strengthens the ability of the model to capture features of various disease manifestations in grape leaf images but also improves its generalization capabilities and stability. Additionally, the model incorporates the SPPFCSPC pyramid pooling structure, which maintains the stability of the receptive field while significantly enhancing processing speed. The integration of the CBAM attention mechanism further accentuates the ability of the model to identify key features, substantially increasing the accuracy of disease detection. Moreover, the model employs Inner-SIoU as the loss function, optimizing the precision of bounding box regression and accelerating model convergence, thereby further enhancing detection efficiency. Rigorous testing has shown that the MSCI-YOLOv8s model achieves an impressive average precision (mAP) of 97.7%, with an inference time of just 37.2 milliseconds and a memory footprint of 39.3 MB. These advancements render the MSCI-YOLOv8s not only highly efficient but also extremely practical for real-time grape disease detection, meeting the actual demands of grape orchard disease identification and demonstrating significant potential for application.

Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases

AbstractPlant diseases cause significant agricultural losses, demanding accurate detection methods. Traditional approaches relying on expert knowledge may be biased, but advancements in computing, particularly deep learning, offer non-experts effective tools. This study focuses on fine-tuning cutting-edge pre-trained CNN and vision transformer models to classify grape leaves and diagnose grape leaf diseases through digital images. Our research examined a PlantVillage dataset, which comprises 4062 leaf images distributed across four categories. Additionally, we utilized the Grapevine dataset, consisting of 500 leaf images. This dataset is organized into five distinct groups, with each group containing 100 images corresponding to one of the five grape types. The PlantVillage dataset focuses on four classes related to grape diseases, namely Black Rot, Leaf Blight, Healthy, and Esca leaves. On the other hand, the Grapevine dataset includes five classes for leaf recognition, specifically Ak, Alaidris, Buzgulu, Dimnit, and Nazli. In experiments with 14 CNN and 17 vision transformer models, deep learning demonstrated high accuracy in distinguishing grape diseases and recognizing leaves. Notably, four models achieved 100% accuracy on PlantVillage and Grapevine datasets, with Swinv2-Base standing out. This approach holds promise for enhancing crop productivity through early disease detection and providing insights into grape variety characterization in agriculture.

Grape leaf moisture prediction from UAVs using multimodal data fusion and machine learning

Grape leaf moisture prediction from UAVs using multimodal data fusion and machine learning

Intelligent vineyard blade density measurement method incorporating a lightweight vision transformer

Under the new demand model of Agriculture 4.0, automated spraying is a very complex task in precision agriculture, which needs to be combined with a computerized vision perception system to distinguish the plant leaf density and execute the spraying operation in real-time accordingly. Aiming at the accurate determination of grape leaf density, an image leaf density determination method based on the lightweight Vision Transformer (ViT) architecture is proposed, which designs a fusion data augmentation method containing a dual augmentation spatial extension and weather data augmentation method, where the former adopts the pixel augmentation and spatial augmentation for the original image processing, and the latter realizes the data augmentation from the empirical point of view adapted to the agricultural operation environment, and fuses the two in order to expand the sample capacity of the grape leaf density image, which then enhances the model's generalization ability and robustness. The lightweight ViT model has self-attention that can automatically and efficiently extract high-frequency local feature representations and use the two-branch structure to mix high-frequency and low-frequency information to form grapevine-leaf density features in the region of interest. The semantic analysis of the feature extraction layer is parsed using t-SNE and histogram methods, which improves the transparency of the model from the multidimensional with frequency domain distribution space. The experimental results show that the fusion data augmentation method can effectively improve the model recognition accuracy, and the accuracy of comparing the included data augmentation methods is improved by 0.55 % and 3.46 %, respectively. The accuracy of recognizing all four types of grape leaf densities exceeded 94 %, and the MCC reached 90.39 %. In addition, the proposed lightweight ViT improves the accuracy by at least 0.34 % with FLOPs of only 0.6 G compared to the popular MobileViT. The proposed method of this work has high recognition speed and accuracy, which can provide practical technical support for plant protection spraying robots and improve the profitability of growers based on the reduction of pesticide residues.

UPFormer: U-sharped Perception lightweight Transformer for segmentation of field grape leaf diseases

In the smart agriculture community, segmentation models are de-facto for the timely detection and identification of plant diseases. However, the complex background and the small diseases make it challenging to segment the grape leaf disease. The performance improvement trend of the existing models comes at the cost of model size and computational cost, which hinders deployment on resource-constrained hardware. Towards this end, we propose a tailored lightweight segmentation architecture referred to as the U-sharped Perception Transformer (UPFormer) for field grape leaf diseases, which achieves a better trade-off between performance and efficiency. Concretely, we leverage the U-shaped hierarchy to acquire small tokens with superior cost efficiency. The prototype perception and the pixel-aware broadcast are developed in parallel architectures to learn low-frequency global information and mine high-frequency local information for small diseases in complex environments. Besides, a fast token aggregation recipe is designed to compensate for the sacrificed detail information in an efficient aggregation paradigm without increasing the count of parameters. Extensive experiments have demonstrated that UPFormer remarkably outperforms existing CNNs, ViTs, and CNN-Transformer hybrid architectures on the datasets, including Field-PV, Syn-PV, and Plant Village.

Potential feeding value, feed quality, microbial protein production, and antimethanogenic properties of tree leaves admixed with Italian ryegrass at different ratios using <i>in vitro</i> gas production

The purpose of this study was to use the in vitro gas production (IVGP) method to assess the relative feeding value, feed quality, and anti- methanogenic capabilities of tree leaves added to Italian ryegrass forage at various proportions. With the addition of 2% and 4% willow leaf (Salix alba), 2% and 4% vine leaf (Vitis vinifera), 2% and 4% plane leaf (Platanus orientalis), and a control group devoid of these supplements, a total of 21 forage samples were created. The data were subjected to analysis of variance after nutritional composition, energy content, feeding value, and feed quality were determined using the in vitro gas generation method. The effect of the addition of tree leaves to forage on crude ash, IVGP, methane, metabolizable energy, net energy lactation, organic matter digestion, true digestible dry matter, partitioning factor, microbial protein, microbial protein synthesising efficiency, degree of true digestion, NDF digestion, total digestible nutrients, and relative feed quality was substantial. With the addition of 2% willow leaves, the digestibility, metabolic energy, net energy lactation value, organic matter digestion, microbial protein value, and relative feed quality all improved. The findings showed that tree leaves can be utilized as an alternate feed source for ruminants. Tannin content should be taken into account when preparing rations utilizing tannin-containing tree leaves.

Biomass characterization with semantic segmentation models and point cloud analysis for precision viticulture

The scientific progress in artificial intelligence and robotics has enabled precision viticulture to pursue sustainability and improve the final yield. For instance, monitoring the canopy volume of each plant can allow the correct ripening of the bunches. In this context, this paper proposes a novel approach for the characterization of biomass volume using images acquired in a vineyard with the low-cost Azure Kinect RGB-D camera. Semantic image segmentation is implemented using three encoder–decoder deep architectures (U-Net, DeepLabV3+, and MANet) to produce accurate masks of the vine leaf structure. In a transfer learning approach, a public dataset acquired with the Intel RealSense D435 depth camera is used to train the segmentation networks. Then, a complete pipeline to estimate possible changes in biomass volume is presented. Experiments are run to analyze the biomass removed during the trimming process of grapevine plants. The best segmentation result is obtained by the U-Net architecture with ResNet50 backbone, showing an accuracy of 92.10%, although the training and test sets consist of images acquired by different cameras. However, the DeepLabV3+ network with ResNeXt50 backbone, which scores an accuracy of 90.25% on the test set, gives the best estimate of the removed biomass, requiring the shortest time for training. These outcomes prove the potential capability of this automatic approach for controlling leaf growth and ensuring sustainable viticulture practices.

Machine Learning Models for Plant Disease Prediction and Detection: A Review

In the agriculture field farmers are dependent on crops and once it is caused by disease, they can lose the proper yield. Plant illnesses are the common cause of low yields and reduced income for farmers. So, to overcome this, machine learning approach in the agriculture field is showing exponential improvement for interdisciplinary research, but in modern disease prediction systems, it is a different process that can takes more time to identify and understand the type of disease. Disease prediction is related to computer vision and machine learning to detect types of leaf disease on different plants. It’s a long-term system that includes a variety of real-world scenarios such as, Prediction system for vine leaf disease, pomegranate leaf disease, corn leaf disease, etc. Disease prediction is the accurate determination of the disease state of plant leaves. Accurate disease prediction is one of the key requirements in data science. Presently, machine learning based methods have improved prediction accuracy for plant leafs like grapes, pomegranates, maize. However, the disease prediction performance is still required to be improved in this challenging environment. Existing disease prediction models require high computational time and storage facilities in the agriculture field. To overcome this, we have proposed a comparative study of ML for prediction and classification of crop diseases to improve the efficiency of early prediction of crop diseases.

Retracted: Improved Support Vector Machine and Image Processing Enabled Methodology for Detection and Classification of Grape Leaf Disease

Retracted: Improved Support Vector Machine and Image Processing Enabled Methodology for Detection and Classification of Grape Leaf Disease

Detection of Small Lesions on Grape Leaves Based on Improved YOLOv7

The precise detection of small lesions on grape leaves is beneficial for early detection of diseases. In response to the high missed detection rate of small target diseases on grape leaves, this paper adds a new prediction branch and combines an improved channel attention mechanism and an improved E-ELAN (Extended-Efficient Long-range Attention Network) to propose an improved algorithm for the YOLOv7 (You Only Look Once version 7) model. Firstly, to address the issue of low resolution for small targets, a new detection head is added to detect smaller targets. Secondly, in order to increase the feature extraction ability of E-ELAN components in YOLOv7 for small targets, the asymmetric convolution is introduced into E-ELAN to replace the original 3 × 3 convolution in E-ELAN network to achieve multi-scale feature extraction. Then, to address the issue of insufficient extraction of information from small targets in YOLOv7, a channel attention mechanism was introduced and improved to enhance the network’s sensitivity to small-scale targets. Finally, the CIoU (Complete Intersection over Union) in the original YOLOv7 network model was replaced with SIoU (Structured Intersection over Union) to optimize the loss function and enhance the network’s localization ability. In order to verify the effectiveness of the improved YOLOv7 algorithm, three common grape leaf diseases were selected as detection objects to create a dataset for experiments. The results show that the average accuracy of the algorithm proposed in this paper is 2.7% higher than the original YOLOv7 algorithm, reaching 93.5%.