Multiple Horizontal Mini-chromosome Transfers Drive Genome Evolution of Clonal Blast Fungus Lineages.

Crop disease pandemics are often driven by asexually reproducing clonal lineages of plant pathogens that reproduce asexually. How these clonal pathogens continuously adapt to their hosts despite harboring limited genetic variation, and in absence of sexual recombination remains elusive. Here, we reveal multiple instances of horizontal chromosome transfer within pandemic clonal lineages of the blast fungus Magnaporthe (Syn. Pyricularia) oryzae. We identified a horizontally transferred 1.2Mb accessory mini-chromosome which is remarkably conserved between M. oryzae isolates from both the rice blast fungus lineage and the lineage infecting Indian goosegrass (Eleusine indica), a wild grass that often grows in the proximity of cultivated cereal crops. Furthermore, we show that this mini-chromosome was horizontally acquired by clonal rice blast isolates through at least nine distinct transfer events over the past three centuries. These findings establish horizontal mini-chromosome transfer as a mechanism facilitating genetic exchange among different host-associated blast fungus lineages. We propose that blast fungus populations infecting wild grasses act as genetic reservoirs that drive genome evolution of pandemic clonal lineages that afflict cereal crops.

Integrating IoT for Soil Monitoring and Hybrid Machine Learning in Predicting Tomato Crop Disease in a Typical South India Station.

This study develops a hybrid machine learning (ML) algorithm integrated with IoT technology to improve the accuracy and efficiency of soil monitoring and tomato crop disease prediction in Anakapalle, a south Indian station. An IoT device collected one-minute and critical soil parameters-humidity, temperature, pH values, nitrogen (N), phosphorus (P), and potassium (K), during the vegetative growth stage, which are essential for assessing soil health and optimizing crop growth. Kendall's correlations were computed to rank these parameters for utilization in hybrid ML techniques. Various ML algorithms including K-nearest neighbors (KNN), support vector machines (SVM), decision tree (DT), random forest (RF), and logistic regression (LR) were evaluated. A novel hybrid algorithm, 'Bayesian optimization with KNN', was introduced to combine multiple ML techniques and enhance predictive performance. The hybrid algorithm demonstrated superior results with 95% accuracy, precision, and recall, and an F1 score of 94%, while individual ML algorithms achieved varying results: KNN (80% accuracy), SVM (82%), DT (77%), RF (80%), and LR (81%) with differing precision, recall, and F1 scores. This hybrid ML approach proved highly effective in predicting tomato crop diseases in natural environments, underscoring the synergistic benefits of IoT and advanced ML techniques in optimizing agricultural practices.

Few-Shot Image Classification of Crop Diseases Based on Vision-Language Models.

Accurate crop disease classification is crucial for ensuring food security and enhancing agricultural productivity. However, the existing crop disease classification algorithms primarily focus on a single image modality and typically require a large number of samples. Our research counters these issues by using pre-trained Vision-Language Models (VLMs), which enhance the multimodal synergy for better crop disease classification than the traditional unimodal approaches. Firstly, we apply the multimodal model Qwen-VL to generate meticulous textual descriptions for representative disease images selected through clustering from the training set, which will serve as prompt text for generating classifier weights. Compared to solely using the language model for prompt text generation, this approach better captures and conveys fine-grained and image-specific information, thereby enhancing the prompt quality. Secondly, we integrate cross-attention and SE (Squeeze-and-Excitation) Attention into the training-free mode VLCD(Vision-Language model for Crop Disease classification) and the training-required mode VLCD-T (VLCD-Training), respectively, for prompt text processing, enhancing the classifier weights by emphasizing the key text features. The experimental outcomes conclusively prove our method's heightened classification effectiveness in few-shot crop disease scenarios, tackling the data limitations and intricate disease recognition issues. It offers a pragmatic tool for agricultural pathology and reinforces the smart farming surveillance infrastructure.

Deep recognition of rice disease images: how many training samples do we really need?

BACKGROUND: With the rapid development of deep learning, the recognition of rice disease images using deep neural networks has become a hot research topic. However, most previous studies only focus on the modification of deep learning models, while lacking research to systematically and scientifically explore the impact of different data sizes on the image recognition task for rice diseases. In this study, a functional model was developed to predict the relationship between the size of dataset and the accuracy rate of model recognition. RESULTS: Training VGG16 deep learning models with different quantities of images of rice blast-diseased leaves and healthy rice leaves, it was found that the test accuracy of the resulting models could be well fitted with an exponential model (A = 0.9965 - e(-0.0603×I50-1.6693)). Experimental results showed that with an increase of image quantity, the recognition accuracy of deep learning models would show a rapid increase at first. Yet when the image quantity increases beyond a certain threshold, the accuracy of image classification would not improve much, and the marginal benefit would be reduced. This trend remained similar when the composition of the dataset was changed, no matter whether (i) the disease class was changed, (ii) the number of classes was increased or (iii) the image data were augmented. CONCLUSIONS: This study provided a scientific basis for the impact of data size on the accuracy of rice disease image recognition, and may also serve as a reference for researchers for database construction. © 2024 Society of Chemical Industry.

Studying Wild Plant Pathosystems to Understand Crop Plant Pathosystems: Status, Gaps, Challenges, and Perspectives.

Phytopathology is a highly complex scientific discipline. Initially, its focus was on the study of plant-pathogen interactions in agricultural and forestry production systems. Host-pathogen interactions in natural plant communities were generally overlooked until the 1970s when plant pathologists and evolutionary biologists started to take an interest in these interactions, and their dynamics in natural plant populations, communities, and ecosystems. This article introduces the general principles of plant pathosystems, provides a basic critical overview of current knowledge of host-pathogen interactions in natural plant pathosystems, and shows how this knowledge is important for future developments in plant pathology especially as it applies in cropping systems, ecology, and evolutionary biology. Plant pathosystems can be further divided according to the structure and origin of control, as autonomous (wild plant pathosystems, WPPs) or deterministic (crop plant pathosystems, CPPs). WPPs are characterized by the disease triangle and closed-loop (feedback) controls, and CPPs are characterized by the disease tetrahedron and open-loop (non-feedback) controls. Basic general, ecological, genetic, and population structural and functional differences between WPPs and CPPs are described. It is evident that we lack a focus on long-term observations and research of diseases and their dynamics in natural plant populations, metapopulations, communities, ecosystems, and biomes, as well as their direct or indirect relationships to CPPs. Differences and connections between WPPs and CPPs, and why, and how, these are important for agriculture varies. WPP and CPP may be linked by strong biological interactions, especially where the pathogen is in common. This is demonstrated through a case study of lettuce (Lactuca spp., L. serriola and L. sativa) and lettuce downy mildew (Bremia lactucae). In other cases where there is no such direct biological linkage, the study of WPPs can provide a deeper understanding of how ecology and genetics interacts to drive disease through time. These studies provide insights into ways in which farming practices may be changed to limit disease development. Research on interactions between pathosystems, the "cross-talk" of WPPs and CPPs, is still very limited and, as shown in interactions between wild and cultivated Lactuca spp.-B. lactucae associations, can be highly complex. The implications and applications of this knowledge in plant breeding, crop management, and disease control measures are considered. This review concludes with a discussion of theoretical, general and specific aspects, challenges and limits of future WPP research, and application of their results in agriculture.

Crop Disease Identification by Fusing Multiscale Convolution and Vision Transformer.

With the development of smart agriculture, deep learning is playing an increasingly important role in crop disease recognition. The existing crop disease recognition models are mainly based on convolutional neural networks (CNN). Although traditional CNN models have excellent performance in modeling local relationships, it is difficult to extract global features. This study combines the advantages of CNN in extracting local disease information and vision transformer in obtaining global receptive fields to design a hybrid model called MSCVT. The model incorporates the multiscale self-attention module, which combines multiscale convolution and self-attention mechanisms and enables the fusion of local and global features at both the shallow and deep levels of the model. In addition, the model uses the inverted residual block to replace normal convolution to maintain a low number of parameters. To verify the validity and adaptability of MSCVT in the crop disease dataset, experiments were conducted in the PlantVillage dataset and the Apple Leaf Pathology dataset, and obtained results with recognition accuracies of 99.86% and 97.50%, respectively. In comparison with other CNN models, the proposed model achieved advanced performance in both cases. The experimental results show that MSCVT can obtain high recognition accuracy in crop disease recognition and shows excellent adaptability in multidisease recognition and small-scale disease recognition.

UAV hyperspectral remote sensor images for mango plant disease and pest identification using MD-FCM and XCS-RBFNN.

To diminish disease transmission together with promoting effective management techniques, it is crucial to monitor plant health and detect pathogens earlier. The initial part in reducing losses sourced from plant diseases is to make an accurate and earlier identification. Thus, the usage of unmanned aerial vehicle (UAV) hyperspectral imaging (HSI) sensors for surveying and assessing crops, orchards, and forests has rapidly elevated over the last decade, particularly for the stress management like water, diseases, nutrition deficits, and pests. Using Minkowski Distance-based Fuzzy C Means (MD-FCM) clustering and Xavier initialization-adapted Cosine Similarity-induced Radial Bias Function Neural Network (XCS-RBFNN) techniques, a UAV HS imaging remote sensor for Spatial and Temporal Resolution (STR) of mango plant disease and pest identification is proposed in this scheme. Collecting the input UAV source (image or video) is eventuated initially along with the Region of Interest (ROI) calculated which is followed by preprocessing. Leaf segmentation is eventuated using Logistic U-net after preprocessing. Next, MD-FCM performs clustering to cluster the diseased leaves and pests individually. The disease and pest characteristics are then retrieved separately and classified further. The requisite features are then chosen from the retrieved features utilizing the Levy Flight Distribution-produced Butterfly Optimization Algorithm (LFD-BOA). Finally, the XCS-RBFNN classifier is utilized to categorize the various diseases together with pests found in the UAV input source using the chosen features. The proposed framework's experimental findings are then compared to some prevailing schemes, with the results revealing that the proposed work outperforms other benchmark techniques.

FgCsn12 Is Involved in the Regulation of Ascosporogenesis in the Wheat Scab Fungus Fusarium graminearum.

Fusarium head blight (FHB), caused by the fungal pathogen Fusarium graminearum, is a destructive disease worldwide. Ascospores are the primary inoculum of F. graminearum, and sexual reproduction is a critical step in its infection cycle. In this study, we characterized the functions of FgCsn12. Although the ortholog of FgCsn12 in budding yeast was reported to have a direct interaction with Csn5, which served as the core subunit of the COP9 signalosome, the interaction between FgCsn12 and FgCsn5 was not detected through the yeast two-hybrid assay. The deletion of FgCSN12 resulted in slight defects in the growth rate, conidial morphology, and pathogenicity. Instead of forming four-celled, uninucleate ascospores, the Fgcsn12 deletion mutant produced oval ascospores with only one or two cells and was significantly defective in ascospore discharge. The 3'UTR of FgCsn12 was dispensable for vegetative growth but essential for sexual reproductive functions. Compared with those of the wild type, 1204 genes and 2240 genes were up- and downregulated over twofold, respectively, in the Fgcsn12 mutant. Taken together, FgCsn12 demonstrated an important function in the regulation of ascosporogenesis in F. graminearum.

Fungi, fungicide discovery and global food security.

Securing sufficient food for a growing world population is of paramount importance for social stability and the well-being of mankind. Recently, it has become evident that fungal pathogens pose the greatest biotic challenge to our calorie crops. Moreover, the loss of commodity crops to fungal disease destabilises the economies of developing nations, thereby increasing the dimension of the threat. Our best weapon to control these pathogens is fungicides, but increasing resistance puts us in an arms race against them. New anti-fungal compounds need to be discovered, such as mono-alky lipophilic cations (MALCs) described herein. Collaborations between academia and industry are imperative to establish new and efficient ways to develop these new fungicides and to bring them to the market-place.

When Does Spatial Diversification Usefully Maximize the Durability of Crop Disease Resistance?

Maximizing the durability of crop disease resistance genes in the face of pathogen evolution is a major challenge in modern agricultural epidemiology. Spatial diversification in the deployment of resistance genes, where susceptible and resistant fields are more closely intermixed, is predicted to drive lower epidemic intensities over evolutionary timescales. This is due to an increase in the strength of dilution effects, caused by pathogen inoculum challenging host tissue to which it is not well-specialized. The factors that interact with and determine the magnitude of this spatial suppressive effect are not currently well understood, however, leading to uncertainty over the pathosystems where such a strategy is most likely to be cost-effective. We model the effect on landscape scale disease dynamics of spatial heterogeneity in the arrangement of fields planted with either susceptible or resistant cultivars, and the way in which this effect depends on the parameters governing the pathosystem of interest. Our multiseason semidiscrete epidemiological model tracks spatial spread of wild-type and resistance-breaking pathogen strains, and incorporates a localized reservoir of inoculum, as well as the effects of within and between field transmission. The pathogen dispersal characteristics, any fitness cost(s) of the resistance-breaking trait, the efficacy of host resistance, and the length of the timeframe of interest all influence the strength of the spatial diversification effect. A key result is that spatial diversification has the strongest beneficial effect at intermediate fitness costs of the resistance-breaking trait, an effect driven by a complex set of nonlinear interactions. On the other hand, however, if the resistance-breaking strain is not fit enough to invade the landscape, then a partially effective resistance gene can result in spatial diversification actually worsening the epidemic. These results allow us to make general predictions of the types of system for which spatial diversification is most likely to be cost-effective, paving the way for potential economic modeling and pathosystem specific evaluation. These results highlight the importance of studying the effect of genetics on landscape scale spatial dynamics within host-pathogen disease systems.[Formula: see text] Copyright © 2020 The Author(s). This is an open access article distributed under the CC BY 4.0 International license.

Acrylamide in food: Progress in and prospects for genetic and agronomic solutions.

Acrylamide is a processing contaminant and Group 2a carcinogen that was discovered in foodstuffs in 2002. Its presence in a range of popular foods has become one of the most difficult problems facing the food industry and its supply chain. Wheat, rye and potato products are major sources of dietary acrylamide, with biscuits, breakfast cereals, bread (particularly toasted), crispbread, batter, cakes, pies, French fries, crisps and snack products all affected. Here we briefly review the history of the issue, detection methods, the levels of acrylamide in popular foods and the risk that dietary acrylamide poses to human health. The pathways for acrylamide formation from free (non-protein) asparagine are described, including the role of reducing sugars such as glucose, fructose and maltose and the Maillard reaction. The evolving regulatory situation in the European Union and elsewhere is discussed, noting that food businesses and their suppliers must plan to comply not only with current regulations but with possible future regulatory scenarios. The main focus of the review is on the genetic and agronomic approaches being developed to reduce the acrylamide-forming potential of potatoes and cereals and these are described in detail, including variety selection, plant breeding, biotechnology and crop management. Obvious targets for genetic interventions include asparagine synthetase genes, and the asparagine synthetase gene families of different crop species are compared. Current knowledge on crop management best practice is described, including maintaining optimum storage conditions for potatoes and ensuring sulphur sufficiency and disease control for wheat.

Sustaining global agriculture through rapid detection and deployment of genetic resistance to deadly crop diseases.

Contents Summary 45 I. Introduction 45 II. Targeted chromosome-based cloning via long-range assembly (TACCA) 46 III. Resistance gene cloning through mutational mapping (MutMap) 47 IV. Cloning through mutant chromosome sequencing (MutChromSeq) 47 V. Rapid cloning through resistance gene enrichment and sequencing (RenSeq) 49 VI. Cloning resistance genes through transcriptome profiling (RNAseq) 49 VII. Resistance gene deployment strategies 49 VIII. Conclusions 50 Acknowledgements 50 References 50 SUMMARY: Genetically encoded resistance is a major component of crop disease management. Historically, gene loci conferring resistance to pathogens have been identified through classical genetic methods. In recent years, accelerated gene cloning strategies have become available through advances in sequencing, gene capture and strategies for reducing genome complexity. Here, I describe these approaches with key emphasis on the isolation of resistance genes to the cereal crop diseases that are an ongoing threat to global food security. Rapid gene isolation enables their efficient deployment through marker-assisted selection and transgenic technology. Together with innovations in genome editing and progress in pathogen virulence studies, this creates further opportunities to engineer long-lasting resistance. These approaches will speed progress towards a future of farming using fewer pesticides.

Crop connectivity under climate change: future environmental and geographic risks of potato late blight in Scotland.

The impact of climate change on dispersal processes is largely ignored in risk assessments for crop diseases, as inoculum is generally assumed to be ubiquitous and nonlimiting. We suggest that consideration of the impact of climate change on the connectivity of crops for inoculum transmission may provide additional explanatory and predictive power in disease risk assessments, leading to improved recommendations for agricultural adaptation to climate change. In this study, a crop-growth model was combined with aerobiological models and a newly developed infection risk model to provide a framework for quantifying the impact of future climates on the risk of disease occurrence and spread. The integrated model uses standard meteorological variables and can be easily adapted to various crop pathosystems characterized by airborne inoculum. In a case study, the framework was used with data defining the spatial distribution of potato crops in Scotland and spatially coherent, probabilistic climate change data to project the future connectivity of crop distributions for Phytophthora infestans (causal agent of potato late blight) inoculum and the subsequent risk of infection. Projections and control recommendations are provided for multiple combinations of potato cultivar and CO2 emissions scenario, and temporal and spatial averaging schemes. Overall, we found that relative to current climatic conditions, the risk of late blight will increase in Scotland during the first half of the potato growing season and decrease during the second half. To guide adaptation strategies, we also investigated the potential impact of climate change-driven shifts in the cropping season. Advancing the start of the potato growing season by 1 month proved to be an effective strategy from both an agronomic and late blight management perspective.

Increased yield stability of field-grown winter barley (Hordeum vulgare L.) varietal mixtures through ecological processes.

Crop variety mixtures have the potential to increase yield stability in highly variable and unpredictable environments, yet knowledge of the specific mechanisms underlying enhanced yield stability has been limited. Ecological processes in genetically diverse crops were investigated by conducting field trials with winter barley varieties (Hordeum vulgare), grown as monocultures or as three-way mixtures in fungicide treated and untreated plots at three sites. Mixtures achieved yields comparable to the best performing monocultures whilst enhancing yield stability despite being subject to multiple predicted and unpredicted abiotic and biotic stresses including brown rust (Puccinia hordei) and lodging. There was compensation through competitive release because the most competitive variety overyielded in mixtures thereby compensating for less competitive varieties. Facilitation was also identified as an important ecological process within mixtures by reducing lodging. This study indicates that crop varietal mixtures have the capacity to stabilise productivity even when environmental conditions and stresses are not predicted in advance. Varietal mixtures provide a means of increasing crop genetic diversity without the need for extensive breeding efforts. They may confer enhanced resilience to environmental stresses and thus be a desirable component of future cropping systems for sustainable arable farming.

CropGCNN: color space-based crop disease classification using group convolutional neural network.

Classifying images is one of the most important tasks in computer vision. Recently, the best performance for image classification tasks has been shown by networks that are both deep and well-connected. These days, most datasets are made up of a fixed number of color images. The input images are taken in red green blue (RGB) format and classified without any changes being made to the original. It is observed that color spaces (basically changing original RGB images) have a major impact on classification accuracy, and we delve into the significance of color spaces. Moreover, datasets with a highly variable number of classes, such as the PlantVillage dataset utilizing a model that incorporates numerous color spaces inside the same model, achieve great levels of accuracy, and different classes of images are better represented in different color spaces. Furthermore, we demonstrate that this type of model, in which the input is preprocessed into many color spaces simultaneously, requires significantly fewer parameters to achieve high accuracy for classification. The proposed model basically takes an RGB image as input, turns it into seven separate color spaces at once, and then feeds each of those color spaces into its own Convolutional Neural Network (CNN) model. To lessen the load on the computer and the number of hyperparameters needed, we employ group convolutional layers in the proposed CNN model. We achieve substantial gains over the present state-of-the-art methods for the classification of crop disease.

Characteristic features of statistical models and machine learning methods derived from pest and disease monitoring datasets.

While many studies have used traditional statistical methods when analysing monitoring data to predict future population dynamics of crop pests and diseases, increasing studies have used machine learning methods. The characteristic features of these methods have not been fully elucidated and arranged. We compared the prediction performance between two statistical and seven machine learning methods using 203 monitoring datasets recorded over several decades on four major crops in Japan and meteorological and geographical information as the explanatory variables. The decision tree and random forest of machine learning were found to be most efficient, while regression models of statistical and machine learning methods were relatively inferior. The best two methods were better for biased and scarce data, while the statistical Bayesian model was better for larger dataset sizes. Therefore, researchers should consider data characteristics when selecting the most appropriate method.

Improved MobileNetV2 crop disease identification model for intelligent agriculture.

Using intelligent agriculture is an important way for the industry to achieve high-quality development. To improve the accuracy of the identification of crop diseases under conditions of limited computing resources, such as in mobile and edge computing, we propose an improved lightweight MobileNetV2 crop disease identification model. In this study, MobileNetV2 is used as the backbone network for the application of an improved Bottleneck structure. First, the number of operation channels is reduced using point-by-point convolution, the number of parameters of the model is reduced, and the re-parameterized multilayer perceptron (RepMLP) module is introduced; the latter can capture long-distance dependencies between features and obtain local a priori information to enhance the global perception of the model. Second, the efficient channel-attention mechanism is added to adjust the image-feature channel weights so as to improve the recognition accuracy of the model, and the Hardswish activation function is introduced instead of the ReLU6 activation function to further improve performance. The final experimental results show that the improved MobilNetV2 model achieves 99.53% accuracy in the PlantVillage crop disease dataset, which is 0.3% higher than the original model, and the number of covariates is only 0.9M, which is 59% less than the original model. Also, the inference speed is improved by 8.5% over the original model. The crop disease identification method proposed in this article provides a reference for deployment and application on edge and mobile devices.

A deep learning model for predicting risks of crop pests and diseases from sequential environmental data.

Crop pests reduce productivity, so managing them through early detection and prevention is essential. Data from various modalities are being used to predict crop diseases by applying machine learning methodology. In particular, because growth environment data is relatively easy to obtain, many attempts are made to predict pests and diseases using it. In this paper, we propose a model that predicts diseases through previous growth environment information of crops, including air temperature, relative humidity, dew point, and CO2 concentration, using deep learning techniques. Using large-scale public data on crops of strawberry, pepper, grape, tomato, and paprika, we showed the model can predict the risk score of crop pests and diseases. It showed high predictive performance with an average AUROC of 0.917, and based on the predicted results, it can help prevent pests or post-processing. This environmental data-based crop disease prediction model and learning framework are expected to be universally applicable to various facilities and crops for disease/pest prevention.

A novel ensemble learning method for crop leaf disease recognition.

Deep learning models have been widely applied in the field of crop disease recognition. There are various types of crops and diseases, each potentially possessing distinct and effective features. This brings a great challenge to the generalization performance of recognition models and makes it very difficult to build a unified model capable of achieving optimal recognition performance on all kinds of crops and diseases. In order to solve this problem, we have proposed a novel ensemble learning method for crop leaf disease recognition (named ELCDR). Unlike the traditional voting strategy of ensemble learning, ELCDR assigns different weights to the models based on their feature extraction performance during ensemble learning. In ELCDR, the models' feature extraction performance is measured by the distribution of the feature vectors of the training set. If a model could distinguish more feature differences between different categories, then it receives a higher weight during ensemble learning. We conducted experiments on the disease images of four kinds of crops. The experimental results show that in comparison to the optimal single model recognition method, ELCDR improves by as much as 1.5 (apple), 0.88 (corn), 2.25 (grape), and 1.5 (rice) percentage points in accuracy. Compared with the voting strategy of ensemble learning, ELCDR improves by as much as 1.75 (apple), 1.25 (corn), 0.75 (grape), and 7 (rice) percentage points in accuracy in each case. Additionally, ELCDR also has improvements on precision, recall, and F1 measure metrics. These experiments provide evidence of the effectiveness of ELCDR in the realm of crop leaf disease recognition.

Dual-branch collaborative learning network for crop disease identification.

Crop diseases seriously affect the quality, yield, and food security of crops. redBesides, traditional manual monitoring methods can no longer meet intelligent agriculture's efficiency and accuracy requirements. Recently, deep learning methods have been rapidly developed in computer vision. To cope with these issues, we propose a dual-branch collaborative learning network for crop disease identification, called DBCLNet. Concretely, we propose a dual-branch collaborative module using convolutional kernels of different scales to extract global and local features of images, which can effectively utilize both global and local features. Meanwhile, we embed a channel attention mechanism in each branch module to refine the global and local features. Whereafter, we cascade multiple dual-branch collaborative modules to design a feature cascade module, which further learns features at more abstract levels via the multi-layer cascade design strategy. Extensive experiments on the Plant Village dataset demonstrated the best classification performance of our DBCLNet method compared to the state-of-the-art methods for the identification of 38 categories of crop diseases. Besides, the Accuracy, Precision, Recall, and F-score of our DBCLNet for the identification of 38 categories of crop diseases are 99.89%, 99.97%, 99.67%, and 99.79%, respectively. 811.