Crop Diseases Research Articles

A knowledge graph for crop diseases and pests in China

A standardized representation and sharing of crop disease and pest data is crucial for enhancing crop yields, especially in China, which features vast cultivation areas and complex agricultural ecosystems. A knowledge graph for crop diseases and pests, acting as a repository of entities and relationships, is crucial conceptually for achieving unified data management. However, there is currently a lack of knowledge graphs specifically designed for this field. In this paper, we propose CropDP-KG, a knowledge graph for crop diseases and pests in China, which leverages natural language processing techniques to analyze data from the Chinese crop diseases and pests image-text database. CropDP-KG covers relevant information on crop diseases and pests in China, featuring 8 primary entities such as diseases, symptoms, and crops, and is organized into 7 relationships such as primary occurrence locations, affected parts and suitable temperature. In total, it includes 13,840 entities and 21,961 relationships. In the case studies presented in this research, we also show a versatile application of CropDP, namely a knowledge service system, and have released its codebase under an open-source license. The content of this paper provides a guide for users to build their own knowledge graphs, aiming to help them effectively reuse and extend the knowledge graphs they create.

PPtase-activated production of borrelidin from extremophilic actinobacteria against multidrug-resistant cotton pathogen Verticillium dahliae.

As the most devastating disease in cotton crops, Verticillium wilt caused by Verticillium dahliae led to fiber quality reduction and extensive yield loss. In recent years, Verticillium wilt has been increasingly serious in Xinjiang, China, the world's largest cotton production area. In this study, 52 actinobacterial strains were selected for the discovery of NPs with anti-V. dahliae activity, from our strain collection isolated from three types of extreme habitats (high salinity, high temperature or plant endophytes) in Xinjiang. In the culture broth extracts of phosphopantetheinyl transferase (PPtase)-activated actinobacterial strains, four showed good anti-V. dahliae activities. By isolation, purification and spectral analysis of the antifungal metabolite, its structure was elucidated as borrelidin from Streptomyces rochei TRM46813. This is the first report that borrelidin shows anti-V. dahliae activity. Notably, borrelidin could effectively inhibit different commercial fungicides-resistant V. dahliae pathogens with MICs of 0.125 to 2 μg/mL. The growth-inhibitory effect was antagonized by L-threonine in a dose-dependent manner, suggesting that threonyl-tRNA synthetase (ThrRS) may be the target of borrelidin in V. dahliae. Interestingly, although borrelidin was previously reported to bind to ThrRS and thus inhibit protein translation in Gram-positive pathogens, our mode-of-action analysis indicates that borrelidin led to the accumulation of cell wall precursor, which may be due to the inhibited effects on protein translation. Our findings suggest that borrelidin is a promising candidate for the development of novel antifungal agents to overcome the growing problem of Verticillium wilt.

Survey paper on Crop Classification using Convolutional Neural Network

Crop Classification using CNN - A Multi-Model Approach for Crop Classification and Health Assessment Using Convolutional Neural Networks and GPT Integration. The integration of deep learning and natural language processing (NLP) in agriculture has gained significant attention for automating crop classification and disease diagnosis. This survey provides an extensive review of various deep learning models applied in crop classification, plant health assessment, and NLP-based report generation. The study explores the effectiveness of object detection models like YOLO, classification networks such as ResNet and EfficientNet, and NLP models like GPT for generating quality assessments. Additionally, this paper discusses the challenges and future research directions in this domain. The survey serves as a precursor to our research implementation, which integrates CNN-based models for crop identification, health assessment, and GPT-based NLP solutions for automated reporting. Key Words: Deep Learning in Agriculture, Convolutional Neural Networks (CNNs), Plant Disease Detection, Generative AI for Crop Analysis, Precision Agriculture.

Automated Detection and Severity Prediction of Wheat Rust Using Cost-Effective Xception Architecture.

Wheat crop production is under constant threat from leaf and stripe rust, an airborne fungal disease caused by the pathogen Puccinia triticina. Early detection and efficient crop phenotyping are crucial for managing and controlling the spread of this disease in susceptible wheat varieties. Current detection methods are predominantly manual and labour-intensive. Traditional strategies such as cultivating resistant varieties, applying fungicides and practicing good agricultural techniques often fall short in effectively identifying and responding to wheat rust outbreaks. To address these challenges, we propose an innovative computer vision-based disease severity prediction pipeline. Our approach utilizes a deep learning-based classifier to differentiate between healthy and rust-infected wheat leaves. Upon identifying an infected leaf, we apply Grabcut-based segmentation to isolate the foreground mask. This mask is then processed in the CIELAB color space to distinguish leaf rust stripes and spores. The disease severity ratio is calculated to measure the extent of infection on each test leaf. This paper introduces a ground-breaking disease severity prediction method, offering a low-cost, accessible and automated solution for wheat rust disease screening in field conditions using digital colour images. Our approach represents a significant advancement in crop disease management, promising timely interventions and better control measures for wheat rust.

Induced Systemic Resistance-Mediated Defense Against Alternaria Blight Disease in Lentil by Pesticide Degrading Plant Growth-Promoting Rhizobacteria.

Enzymatic and antioxidative responses are key defense mechanisms in plants following pathogen invasion, collectively known as induced systemic resistance (ISR). Alternaria sp., a well-known soil-borne pathogen, causes blight diseases in various crops. This study investigates the defence response in lentil plants through the treatment-induced application of two multipotent pesticide degrading plant growth-promoting rhizobacteria (PGPR), Bacillus cereus and Bacillus safensis, to mitigate the destructive effects of Alternaria. Both bacterial strains were applied in different carrier-based bioformulations via soil drenching. We assessed the modulation of defense-related enzymes by various combinational treatments with the Alternaria pathogen. The in vitro production of antimicrobial compounds was analyzed using GC-MS to confirm their pathogen-suppressive capabilities. Field trials showed a positive correlation between treatments and improvements in yield and growth index (GI). The highest (180%) enzymatic induction of phenylalanine ammonia lyase (PAL) followed by catalase (CAT)(100%) and polyphenol oxidase (PPO) (54%), was observed in treatments with B. cereus alone or in combination with B. safensis, in presence of Alternaria, in respect to the control. In vitro analysis revealed the production of antimicrobial compounds, including benzoic acid derivatives, cyclotetrasiloxanes, hexacosane, chlorpyrifos, and phthalates, which may contribute to pathogen suppression. Our findings demonstrate that these biocontrol agents (BCAs) not only stimulate the plant's enzymatic defense system but also enhance growth, seed yield and produce several antimicrobial compounds in vitro. Thus, pesticide-tolerant PGPR, used in this study, exhibit both disease control and plant growth-promoting properties, offering promising applications in sustainable agriculture.

A Comparative Study of Fine-Tuning Deep Learning Models for Leaf Disease Identification and Classification

Innovative agricultural solutions are needed to detect and classify leaf diseases early across crop species and environments. This study compares deep learning approaches, focusing on Convolutional Neural Networks (CNN) and Vision Transformers (VTs), to identify leaf diseases early and accurately for scalable crop management and productivity. Optimizing CNNs, Explainable Transfer Learning (ETPLDNet) using ResNet50 architecture, and LEViT leaf disease diagnosis are compared. The CNN model, optimized with dynamic hyperparameters, achieved an impressive 99.58% accuracy for leaf disease classification, demonstrating its effectiveness in feature extraction and classification precision. On the other hand, the VT-based LEViT model, which leverages self-attention mechanisms and Explainable AI (XAI), achieved 95.22% accuracy but offers enhanced interpretability and generalization capabilities due to its transformer-based architecture. This distinction illustrates that while CNNs excel in accuracy, VTs provide a more transparent decision-making process and better handle the complex variances in plant leaf diseases, making them ideal for precision agriculture. The combined use of CNNs and VTs showcases the strengths of each model, with CNN focusing on high classification precision and VTs offering improved interpretability and adaptability for various leaf disease conditions. The use of XAI enables the models to highlight important areas in plant leaf images that influence the model's decisions, offering a transparent and interpretable decision-making process that allows researchers and farmers to understand why a particular diagnosis or classification was made. This ability to visualize and explain the reasoning behind the model predictions is crucial to increasing trust in AI-driven solutions in agriculture. By combining the high precision of CNN and the interpretability of VT with XAI, this study offers a robust approach to improving crop disease management and precision agriculture.

Reverse-transcription recombinase-aided amplification and CRISPR/Cas12a-based universal detection for fast screening and accurate identification of six pospiviroids infecting Solanaceae crops.

Pospiviroids, members of the genus Pospiviroid, can cause severe diseases in tomato and other Solanaceae crops, causing considerable economic losses worldwide. Six pospiviroids including potato spindle tuber viroid (PSTVd), tomato chlorotic dwarf viroid (TCDVd), tomato planta macho viroid (TPMVd), Columnea latent viroid (CLVd), pepper chat fruit viroid (PCFVd), and tomato apical stunt viroid (TASVd) are regulated in many countries and organizations. Rapid, accurate detection is thus crucial for controlling the spread of these pospiviroids. For simultaneous detection of these six pospiviroids, we developed a rapid, visual method that uses a reverse transcription recombinase-aided amplification (RT-RAA) assay coupled with a clustered regularly interspaced short palindromic repeats and CRISPR-associated protein 12a (CRISPR/Cas12a) system. In particular, this technique could achieve both universal detection and specific identification of the six target pospiviroids within 40 min. The universal detection could diagnose the six target pospiviroids in a single reaction, and the specific identification could identify each target pospiviroid without cross-reactivity of other pospiviroids. The sensitivity limits for the target pospiviroids detection with the proposed detection method were higher than those of the conventional reverse transcription-polymerase chain reaction (RT-PCR) method. We designed an RT-RAA-CRISPR/Cas12a-based universal detection method for both large-scale screening and accurate identification of the six target pospiviroids, which is appropriate for on-site detection. Our study results can aid in performing rapid, large-scale screening of multiple pests simultaneously. © 2024 Society of Chemical Industry.

Plants & Fungi of Niue NaturaList: a compilation of the indigenous and introduced flora and mycota of a Polynesian island

ABSTRACT A checklist of the flora and mycota of Niue (https://plantsniue.nu/#!/checklist) is presented using the NaturaList app platform. The Plants & Fungi of Niue NaturaList was compiled from information presented in the flora treatments of TG Yuncker (1943. The flora of Niue island. In: Bernice P. Bishop Museum Bulletin. 178) and WR Sykes (1970. Contributions to the flora of Niue. New Zealand DSIR Bulletin 200. Wellington: Government Printer), with additional literature documenting the indigenous flora, rare plants, and invasive species. International databases such as iNaturalist and Plants of the World Online were consulted for taxa documented as occurring in Niue. Checklist information presented includes biostatus, Niuean vernacular names, synonyms, references, and images. Kingdom Fungi, mainly comprising Ascomycota and Basidiomycota, are included. The majority of fungi records are derived from surveys of diseases of agricultural crops and food plants, along with recent collections of lichenised fungi. Five additional phyla of Fungi comprise 15 records, with the mycota comprising a total of 270 taxa. Also listed are single species of Bacteria and Protozoa, and 9 taxa of Protista. Kingdom Plantae is represented by the vascular Polypodiophyta (ferns), Pinophyta (conifers), Lycopodiophyta (clubmosses), Cycadophyta (cycads) and Magnoliophyta (flowering plants). The Niue NaturaList includes indigenous (191 species), naturalised (376 species), Polynesian introductions (57 species), and cultivated (382 species) vascular taxa. The cultivated flora includes garden ornamentals and crop plants. The non-vascular Bryophyta (mosses) and Marchantiophyta (liverworts) are represented by 41 taxa. With the floras of Yuncker and Sykes out-of-print and recent literature often disparate and not readily accessible, the Plants & Fungi of Niue NaturaList provides a single, electronic and up-to-date compilation. This is necessary to improve knowledge of and access to Niue's indigenous biota and introduced cultivated and naturalised plants. It also informs and encourages further study relating to conservation of indigenous species and ecosystems, invasive species management, food security, and climate change adaptation. An appendix lists 37 new records of naturalised and cultivated plants made in 2024.

Do Different Wheat Ploidy Levels Respond Differently Against Stripe Rust Infection: Interplay between Reactive Oxygen Species (ROS) and the Antioxidant Defense System?

Wheat stripe rust (Puccinia striiformis f. sp. tritici, Pst) is the most damaging wheat disease, causing substantial losses in global wheat production and productivity. Our study aimed to unravel the complex reciprocity between reactive oxygen species and the antioxidant defense system as a source of resistance against stripe rust in diploid, tetraploid and hexaploid wheat genotypes. The significant genetic variability for stripe rust in the materials under study was evident as the genotypes showed contrasting responses during both the adult and seedling stages. Our thorough perspective on the biochemical responses of wheat genotypes to stripe rust infection revealed distinct patterns in oxidative damage, antioxidant enzymes and photosynthetic pigments. Principal component analysis revealed inverse correlations between antioxidants and ROS, underscoring their key function in maintaining the cellular redox balance and protecting plants against oxidative damage. Diploid (Ae. tauschii) wild wheat exhibited a better biochemical defense system and greater resistance to stripe rust than the tetraploid (T. durum) and hexaploid (Triticum aestivum) wheat genotypes. The antioxidant enzyme activity of durum wheat was moderate compared to diploid and hexaploid wheat genotypes. The hexaploid wheat genotypes exhibited increased ROS production, reduced antioxidant enzyme activity and decreased photosynthetic pigment levels. This study enhances understanding of the antioxidant defense system across different wheat ploidies facing stripe rust, serving as a valuable strategy for improving crop disease resistance. This study validated the biochemical response of stripe rust-resistant and susceptible candidate genotypes, which will be used to develop genetic resources for discovering stripe rust resistance genes in wheat.

Novel ZnO-TiO2@MSC nanomaterial based on corn stover template enhances disease resistance in tomato plants.

Crop diseases significantly threaten global food security, driving the need for innovative control strategies. This study explored using ZnO-TiO2@MSC, a novel nanomaterial synthesized using a corn stover template, to enhance disease resistance in tomato plants. In vitro assays demonstrated potent antimicrobial activity of ZnO-TiO2@MSC against the pathogen Pseudomonas syringae pv. tomato DC3000 (Pst. DC3000) by disrupting bacterial cell membranes and modulating oxidative stress-related gene expression. When applied to tomato leaves in pot trials, ZnO-TiO2@MSC achieved 79.83% control of bacterial leaf spot disease while promoting plant growth and photosynthesis. The nanomaterial triggered plant defense mechanisms, upregulating resistance genes and increasing the activities of key enzymes. Metabolomic profiling revealed elevated lipids, lipid-like molecules, and organic acid derivative levels in treated leaves, suggesting cell membrane remodeling as part of the defense response. These findings highlight the potential of biologically-templated nanomaterials like ZnO-TiO2@MSC as multifunctional tools for sustainable disease management in crops. The corn stover-based synthesis approach also provides a way to valorize agricultural waste. Further research is needed to understand the long-term impacts and viability of field-scale application of ZnO-TiO2@MSC as an alternative to conventional pesticides.

Emergence of Fusarium incarnatum and Fusarium avenaceum in wilt affected solanaceous crops of the Northern Himalayas

The objective of this study was to identify and characterize the fungal pathogens responsible for wilt diseases in solanaceous crops, specifically tomato, brinjal, and chili, in the Kashmir valley. Through both morphological and molecular analyses, including DNA barcoding of the ITS, TEF, RPB1, and RPB2 genomic regions, Fusarium incarnatum and Fusarium avenaceum were identified as the primary causal agents of wilt in tomato and brinjal, and chili, respectively. Pathogenicity tests confirmed the virulence of these pathogens, with typical wilt symptoms observed upon inoculation. This represents the first report of F. incarnatum and F. avenaceum as wilt pathogens in solanaceous crops in India. Phylogenetic analysis further confirmed the genetic variability of these pathogens, revealing their expanding host range. The findings underscore the growing adaptability of these Fusarium species to diverse agricultural systems and highlight the urgent need for targeted disease management strategies to mitigate the significant yield losses caused by Fusarium wilt in solanaceous vegetable production.

Cladosporium cladosporioides for disease control and defense response induction in upland rice grown under an agroecological system

ABSTRACT Diseases in rice crops result in yield loss and pesticide overuse. Although agroecological systems enable more sustainable production, pest and disease management difficulties make biological control essential. The aim of this study was to assess the efficiency of different C. cladosporioides C24G application techniques in controlling rice diseases under field conditions and their effect on yield, defense enzymes, photosynthetic, and photoprotective pigments. The experiment consisted of six treatments and four repetitions in two growing seasons. In both growing seasons, treatments with C. cladosporioides C24G differed from the control for all the parameters studied. Treatments involving microbiolization and additional foliar spraying did not differ from those with only two applications. For leaf scald, brown spot and grain spot, treatments suppressed up to 94.30%, 64.41%, and 86.36%, respectively. Treatments with foliar spraying increased yield by up to 46.72%. Greater increases were also observed for the enzyme and pigment experiments in treatments involving leaf spraying. As such, incorporating C. cladosporioides into rice disease management improves yield under agroecological systems, thereby contributing to increasing the use of this cultivation system.

Rice leaf disease detection using the Stretched Neighborhood Effect Color to Grayscale method and Machine Learning

The emergence of Machine Learning (ML) technologies and their integration into agriculture has demonstrated a significant impact on disease detection in crops, enabling continuous monitoring and enhancing risk planning and management. This study applied image processing techniques such as thresholding, gamma correction, and the Stretched Neighborhood Effect Color to Grayscale (SNECG) method, alongside ML, to develop a predictive model for identifying five types of rice diseases. The ML techniques used included Logistic Regression, Multilayer Perceptron, Support Vector Machines, Decision Trees, and Random Forests (RF). Hyperparameters were optimized and evaluated through 5-fold cross-validation. In the results, the SNECG method successfully converted images to grayscale, capturing essential features of lesions on rice leaves. The ML models developed with these techniques showed evaluation metrics exceeding 80%, with the RF model (precision = 88.31%) demonstrating superior performance. Additionally, the RF model was integrated into an interface designed for agricultural decision-making. The practical application of the developed model could significantly improve the ability to detect and manage diseases in rice crops.

Scalable Prediction of Northern Corn Leaf Blight and Gray Leaf Spot Diseases to Predict Fungicide Spray Timing in Corn

Managing foliar corn diseases like northern leaf blight (NLB) and gray leaf spot (GLS), which can occur rapidly and impact yield, requires proactive measures including early scouting and fungicides to mitigate these effects. Decision support tools, which use data from in-field monitors and predicted leaf wetness duration (LWD) intervals based on meteorological conditions, can help growers to anticipate and manage crop diseases effectively. Effective crop disease management programs integrate crop rotation, tillage practices, hybrid selection, and fungicides. However, growers often struggle with correctly timing fungicide applications, achieving only a 30–55% positive return on investment (ROI). This paper describes the development of a disease-warning and fungicide timing system, equally effective at predicting NLB and GLS with ~70% accuracy, that utilizes historical and forecast hourly weather data. This scalable recommendation system represents a valuable tool for proactive, practicable crop disease management, leveraging in-season weather data and advanced modeling techniques to guide fungicide applications, thereby improving profitability and reducing environmental impact. Extensive on-farm trials (>150) conducted between 2020 and 2023 have shown that the predicted fungicide timing out-yielded conventional grower timing by 5 bushels per acre (336 kg/ha) and the untreated check by 9 bushels per acre (605 kg/ha), providing a significantly improved ROI.

Design and Implementation of FourCropNet: A CNN-Based System for Efficient Multi-Crop Disease Detection and Management

Plant disease detection is a critical task in agriculture, directly impacting crop yield, food security, and sustainable farming practices. This study proposes FourCropNet, a novel deep learning model designed to detect diseases in multiple crops, including CottonLeaf, Grape, Soybean, and Corn. The model leverages an advanced architecture comprising residual blocks for efficient feature extraction, attention mechanisms to enhance focus on disease-relevant regions, and lightweight layers for computational efficiency. These components collectively enable FourCropNet to achieve superior performance across varying datasets and class complexities, from single-crop datasets to combined datasets with 15 classes. The proposed model was evaluated on diverse datasets, demonstrating high accuracy, specificity, sensitivity, and F1 scores. Notably, FourCropNet achieved the highest accuracy of 99.7% for Grape, 99.5% for Corn, and 95.3% for the combined dataset. Its scalability and ability to generalize across datasets underscore its robustness. Comparative analysis shows that FourCropNet consistently outperforms state-of-the-art models, such as MobileNet, VGG16, and EfficientNet, across various metrics. FourCropNet’s innovative design and consistent performance make it a reliable solution for real-time disease detection in agriculture. This model has the potential to assist farmers in timely disease diagnosis, reducing economic losses and promoting sustainable agricultural practices.

Synthesis of SnO₂/COF Green Nanomaterials for Effective Pesticide Decomposition and Promoting Tomato Plants Growth.

In last few decades, the agriculture sector is facing various type of crops diseases originated by crop pests. Among various crops the tomato plant is greatly affected by many pests such as aphids and whiteflies, which are badly decreasing tomato plant yield and effecting its growth. In last few years, various type of pesticides such as Neonicotinoids and Pyrethroids are employed which are badly effecting eco-system and water bodies. In this research work, we prepared SnO2 nanosheets (SONS) by in-situ and green synthesis approach. Remarkably, SONS exhibit a larger surface area, tailored pore size, and higher catalytic performance than SnO2 nanoparticles (SONP). To further improve the efficiency of SONS, we coupled it with covalent organic farmwork nanosheets (COFNS) via the hydrothermal approach. The SONS@COFNS hybrid nanocatalysts exhibit improved carrier migration, enhanced porosity, multiple active sites, and exceptional light absorption capabilities. The as prepared green nanomaterials delivered improved activities for Neonicotinoids and Pyrethroids degradation. Remarkably, the most active sample 6COFNS/SONS showed the highest degradation efficiency (94 %), which is approximately 1.92 times higher than the degradation efficiency of pristine SONS (49 %). This work will ultimately contribute to developing green, ecofriendly nanomaterials for pesticides degradation and promoting tomato plants growth.

Semantic-Guided Transformer Network for Crop Classification in Hyperspectral Images

The hyperspectral remote sensing images of agricultural crops contain rich spectral information, which can provide important details about crop growth status, diseases, and pests. However, existing crop classification methods face several key limitations when processing hyperspectral remote sensing images, primarily in the following aspects. First, the complex background in the images. Various elements in the background may have similar spectral characteristics to the crops, and this spectral similarity makes the classification model susceptible to background interference, thus reducing classification accuracy. Second, the differences in crop scales increase the difficulty of feature extraction. In different image regions, the scale of crops can vary significantly, and traditional classification methods often struggle to effectively capture this information. Additionally, due to the limitations of spectral information, especially under multi-scale variation backgrounds, the extraction of crop information becomes even more challenging, leading to instability in the classification results. To address these issues, a semantic-guided transformer network (SGTN) is proposed, which aims to effectively overcome the limitations of these deep learning methods and improve crop classification accuracy and robustness. First, a multi-scale spatial–spectral information extraction (MSIE) module is designed that effectively handle the variations of crops at different scales in the image, thereby extracting richer and more accurate features, and reducing the impact of scale changes. Second, a semantic-guided attention (SGA) module is proposed, which enhances the model’s sensitivity to crop semantic information, further reducing background interference and improving the accuracy of crop area recognition. By combining the MSIE and SGA modules, the SGTN can focus on the semantic features of crops at multiple scales, thus generating more accurate classification results. Finally, a two-stage feature extraction structure is employed to further optimize the extraction of crop semantic features and enhance classification accuracy. The results show that on the Indian Pines, Pavia University, and Salinas benchmark datasets, the overall accuracies of the proposed model are 98.24%, 98.34%, and 97.89%, respectively. Compared with other methods, the model achieves better classification accuracy and generalization performance. In the future, the SGTN is expected to be applied to more agricultural remote sensing tasks, such as crop disease detection and yield prediction, providing more reliable technical support for precision agriculture and agricultural monitoring.

An Enhanced Oppositional Crow Search Optimization Algorithm-based Colour Edge Segmentation and Modified Resnet-39 Architecture for Prediction of Crop Disease

Accurate and timely prediction of crop diseases is vital for improving agricultural productivity and ensuring food security. This research work proposes new framework that integrates an improved swarm-based color edge segmentation method with a modified ResNet-39 architecture to efficiently detect and categorize crop diseases. The suggested segmentation technique utilizes Crow Search optimization algorithm combined with oppositional learning to improve edge recognition accuracy using color segmentation. This allows precise localization of disease-affected areas even under difficult situations such as poor contrast and noise. The segmented outputs are further processed using a tailored ResNet-39 architecture, optimized for computational efficiency and prediction accuracy. The proposed Enhanced edge segmentation Crow Search Optimization with ResNet-39 (EesCSO-ResNet-39) methodology is tested using publically accessible crop disease datasets, showing substantial improvements in critical metrics such as accuracy, precision, and recall relative to conventional segmentation techniques and current deep learning architectures, including ResNet-50 and VGG-16.

Plant Leaf Disease Detection Utilizing Machine Learning Techniques

The rapid development of machine learning and artificial intelligence is dramatically changing plant disease. The most important among them include the detection of plant diseases, where crop diseases are identified, categorized, and analysed with the help of AI and ML systems. It examines the application of AI and ML techniques in detecting plant disease, with regards to how increased farm output and diminished harvest losses could ensue in sustainable farming. We carry out this study to illuminate how AI-based solutions are transforming current farming practices in relation to methods, challenges, and emerging trends in this burgeoning field.

Enhancing Image Quality in Crop Disease Diagnosis: A Comparative Evaluation of Laplacian and Average Filtering with Established Techniques

The agricultural sector is vital to ensuring global food security, yet plant diseases caused by various environmental factors lead to significant reductions in crop yields. Early detection of such diseases is critical, as crop health directly affects both yield and quality. This research introduces a novel pre-processing algorithm designed to enhance the accuracy of crop disease detection from leaf images. The proposed algorithm is compared against three widely used filtering techniques: Median filtering, Wiener filtering, and Gaussian filtering. Before implementing the proposed approach, a detailed assessment of these conventional methods is conducted.The algorithm integrates Laplacian filtering and average filtering to optimize image pre-processing. The effectiveness of this approach is evaluated using performance metrics such as Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), and Mutual Information (MI). Results indicate that the proposed method achieves a 0.34% increase in PSNR, a 0.92% reduction in MSE, and a 0.48% improvement in MI compared to existing techniques. These improvements underscore the algorithm's ability to enhance image quality and outperform traditional methods.The findings suggest that incorporating Laplacian and average filtering into the pre-processing pipeline introduces a more efficient methodology for image enhancement. This approach holds potential for advancing image analysis and interpretation in agriculture and other fields, providing a foundation for further innovation in image processing technologies.