Crop Health Management Research Articles

Comprehensive Analysis of a YOLO-based Deep Learning Model for Cotton Plant Leaf Disease Detection

Diagnosis of cotton plant diseases is essential to maintain agricultural sustainability and output. This study proposes a YOLO-based deep learning model for leaf disease detection to maximize cotton plant leaf disease detection accuracy. This method ensures a comprehensive evaluation of cotton plant health by combining various image processing techniques, improving the accuracy of disease identification. This study provides a viable path to improve crop health monitoring and management in cotton farming systems and emphasizes the importance of utilizing cutting-edge image processing techniques in agricultural activities. ROC curve performance and classification metrics were better for YOLOv5 than for VGG16 and ResNet50, as it had the highest F1 score (99.21%), recall, and precision. Consistent performance in classification tests was demonstrated by all models, which showed balanced precision, recall, and F1 scores. ResNet50 marginally outperformed VGG16 in terms of true positive rates, F1 score (98.88% vs. 98.65%), recall, and precision. More sophisticated models, such as YOLOv5 and ResNet50, showed higher efficiency and accuracy than VGG16, which makes them more appropriate for applications demanding low false positive rates and high precision. The proposed YOLO-based method improves the accuracy of disease identification, ensuring a thorough assessment of cotton plant health using image processing techniques. The results show that the proposed approach is quite successful in correctly detecting and classifying a variety of diseases that affect cotton plants.

Rainfall Forecasting and Crop Health Management in Agriculture Using CSGRU and Federated Learning

Rainfall Forecasting and Crop Health Management in Agriculture Using CSGRU and Federated Learning

Exploring the Opportunities of Applying RFID Technology in Smart Agriculture

This paper explores the opportunities of applying RFID (radio-frequency identification) technology in smart agriculture. With the projected increase in global population and the resulting higher demand for food production, the agricultural industry is under pressure to find more efficient and sustainable ways to meet these needs. Radio-frequency identification (RFID) technology has been recently adopted in the agriculture industry as a means of improving efficiency and productivity towards achieving smart agriculture. RFID technology is revolutionizing smart agriculture, offering automation, real-time monitoring and data-driven decision-making. Integrating RFID tags with plants and soil samples optimizes resource utilization, crop health management, traceability and quality assurance. RFID in smart agriculture offers opportunities for resource optimization, crop health management, traceability and automation. Leveraging RFID technology, farmers can elevate productivity, reduce costs, improve sustainability and meet global demands. Adopting RFID in agriculture revolutionizes traditional practices, enabling efficient and sustainable farming. RFID-enabled traceability enhances food safety, quality assurance and transparency in the food supply chain. The objective of this paper is to explore the potential of RFID technology in smart agriculture and highlight the significance of effective RFID antenna design for optimizing food production, addressing global challenges and fostering a more efficient, sustainable and resilient agricultural sector.

DeepEMPR: coffee leaf disease detection with deep learning and enhanced multivariance product representation.

Plant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images. To do so, we propose a novel approach as the preprocessing step for the classification in which enhanced multivariance product representation (EMPR) is used to decompose the considered image into components, a new image is constructed using some of those components, and the contrast of the new image is enhanced by applying high-dimensional model representation (HDMR) to highlight the diseased parts of the leaves. Popular convolutional neural network (CNN) architectures, including AlexNet, VGG16, and ResNet50, are evaluated. Results show that VGG16 achieves the highest classification accuracy of approximately 96%, while all models perform well in predicting disease severity levels, with accuracies exceeding 85%. Notably, the ResNet50 model achieves accuracy levels surpassing 90%. This research contributes to the advancement of automated crop health management systems.

Diagnosis of Custard Apple Disease Based on Adaptive Information Entropy Data Augmentation and Multiscale Region Aggregation Interactive Visual Transformers

Accurate diagnosis of plant diseases is crucial for crop health. This study introduces the EDA–ViT model, a Vision Transformer (ViT)-based approach that integrates adaptive entropy-based data augmentation for diagnosing custard apple (Annona squamosa) diseases. Traditional models like convolutional neural network and ViT face challenges with local feature extraction and large dataset requirements. EDA–ViT overcomes these by using a multi-scale weighted feature aggregation and a feature interaction module, enhancing both local and global feature extraction. The adaptive data augmentation method refines the training process, boosting accuracy and robustness. With a dataset of 8226 images, EDA–ViT achieved a classification accuracy of 96.58%, an F1 score of 96.10%, and a Matthews Correlation Coefficient (MCC) of 92.24%, outperforming other models. The inclusion of the Deformable Multi-head Self-Attention (DMSA) mechanism further enhanced feature capture. Ablation studies revealed that the adaptive augmentation contributed to a 0.56% accuracy improvement and a 0.34% increase in MCC. In summary, EDA–ViT presents an innovative solution for custard apple disease diagnosis, with potential applications in broader agricultural disease detection, ultimately aiding precision agriculture and crop health management.

AgriScan: Next.js powered cross-platform solution for automated plant disease diagnosis and crop health management

Plant diseases present a formidable challenge to the agricultural sector worldwide, leading to significant losses, with the US experiencing annual losses amounting to one-third of crop production. Diagnosis of crop diseases through optical observation of leaf symptoms is particularly daunting for farmers with limited resources. Therefore, there is an urgent need for enhanced detection, monitoring, and prediction methods to mitigate agricultural losses effectively. Harnessing the power of computer vision and deep learning, this paper introduces a cross-platform system designed to automate plant leaf disease diagnosis. The system employs convolutional neural networks to classify 46 disease categories, trained on a dataset comprising 96,206 images of healthy and infected plant leaves. The user interface, accessible across multiple platforms including Android, iOS, Windows, and Linux, allows farmers to capture photos of infected leaves and receive real-time disease classification along with confidence percentages. By empowering farmers to maintain crop health and prevent the application of incorrect fertilizers, the system aims to optimize crop productivity. Performance evaluation includes metrics such as classification accuracy and processing time, with the model achieving an impressive overall accuracy of 93.45% across 46 common disease classes spanning 16 crop species.

Biochar-based phosphate fertilizer improve phosphorus bioavailability, microbial functioning, and citrus seedling growth

Phosphorus is essential for plant growth but often becomes immobilized in soils, reducing its availability to plants. This study explored the enhancement of phosphorus bioavailability through the co-pyrolysis of rice straw with magnesium oxide (MgO) at 800 °C, resulting in a novel biochar-based phosphate fertilizer, termed MRS8-P. The treatment involved enriching biochar with MgO to increase phosphorus loading and evaluating its effects on soil physicochemical properties and citrus seedling growth. Soil analysis revealed improved physicochemical properties, including increased available phosphorus (AP), enhanced soil pH, higher electrical conductivity (EC), and rapidly increased available potassium (RAK); however, a temporary immobilization of alkaline hydrolytic nitrogen (AHN) was noticed by biochar application. Notably, soil microbiota dynamics shifted with an increase in beneficial taxa, such as Proteobacteria and Actinobacteria, which enhanced phosphorus solubilization and organic matter decomposition, and a decrease in taxa, such as Methylomirabilota and Desulfobacterota. These microbial changes significantly contribute to soil fertility and nutrient availability. The application of MRS8-P significantly enhanced nitrogen, phosphorus, and potassium (NPK) uptake in citrus seedlings, as demonstrated by increased growth metrics, such as plant height, stem coarseness, and chlorophyll content measured by the SPAD index. These findings underscore the potential of MRS8-P in reducing reliance on traditional phosphate fertilizers, which are linked to environmental degradation through runoff and pollution. The study confirms that biochar-based phosphate fertilizers, such as MRS8-P, can promote more sustainable agricultural practices and improve crop health and soil management while minimizing environmental impacts.

Transfer Learning in Multimodal Sunflower Drought Stress Detection

Efficient water supply and timely detection of drought stress in crops to increase yields is an important task considering that agriculture is the primary consumer of water globally. This is particularly significant for plants such as sunflowers, which are an important source of quality edible oils, essential for human nutrition. Traditional detection methods are labor-intensive, time-consuming, and rely on advanced sensor technologies. We introduce an innovative approach based on neural networks and transfer learning for drought stress detection using a novel dataset including 209 non-invasive rhizotron images and 385 images of manually cleaned sections of sunflowers, subjected to normal watering or water stress. We used five neural network models: VGG16, VGG19, InceptionV3, DenseNet, and MobileNet, pre-trained on the ImageNet dataset, whose performance was compared to select the most efficient architecture. Accordingly, the most efficient model, MobileNet, was further refined using different data augmentation mechanisms. The introduction of targeted data augmentation and the use of grayscale images proved to be effective, demonstrating improved results, with an F1 score and an accuracy of 0.95. This approach encourages advances in water stress detection, highlighting the value of artificial intelligence in improving crop health monitoring and management for more resilient agricultural practices.

Detection and Classification of Wilting in Soybean Crop using Cutting-edge Deep Learning Techniques

Background: This paper employs deep learning in the classification of soybean wilting, a plant health indicator affected by external pressures, using a Convolutional Neural Network (CNN) with a pre-trained model. It highlights the promise of deep learning in agriculture by examining the relevance of wilting, evolution in the agricultural sector and applications in crop wellness monitoring. Methods: A CNN is used in the study to classify soybean withering, with special attention to the VGG16 pre-trained model. Deep learning’s ability to interpret complex data patterns is harnessed for intelligent and accurate wilting detection. A smart detection system tailored for soybean wilting is developed, incorporating recent advancements and addressing associated challenges. Result: The CNN model, notably VGG16, achieves 76% overall accuracy in distinguishing healthy and wilted soybean leaves, signifying a transformative shift in soybean crop health management. The approach offers a precise, efficient and sustainable solution supported by state-of-the-art CNN technology, advancing soybean cultivation practices.

Crop Disease Detection and Recovery of Plats through Automatic Spraying and Watering

Abstract: This project introduces an integrated system for crop health management, combining automated disease detection, targeted treatment, and intelligent watering. Through advanced image processing, potential diseases affecting crops are identified early on. Upon detection, an automated spraying mechanism delivers precise treatment to affected areas, minimizing crop impact. Additionally, an intelligent watering system optimizes hydration based on sensor data and environmental factors. By proactively addressing issues and providing timely care, this comprehensive solution aims to minimize crop loss, increase yield, and promote sustainable agricultural practices.

Enhancing soybean classification with modified inception model: A transfer learning approach

The impact of deep learning (DL) is substantial across numerous domains, particularly in agriculture. Within this context, our study focuses on the classification of problematic soybean seeds. The dataset employed encompasses five distinct classes, totaling 5513 images. Our model, based on the InceptionV3 architecture, undergoes modification with the addition of five supplementary layers to enhance efficiency and performance. Techniques such as transfer learning, adaptive learning rate adjustment (to 0.001), and model checkpointing are integrated to optimize accuracy. During initial evaluation, the InceptionV3 model achieved 88.07% accuracy in training and 86.67% in validation. Subsequent implementation of model tuning strategies significantly improves performance. Augmenting the architecture with additional layers, including Average Pooling, Flatten, Dense, Dropout, and Softmax, plays a pivotal role in enhancing accuracy. Evaluation metrics, including precision, recall, and F1-score, underscore the model’s effectiveness. Precision ranges from 0.9706 to 1.0000, while recall values demonstrate a high capture rate across all classes. The F1-score, reflecting a balance between precision and recall, exhibits remarkable performance across all classes, with values ranging from 0.9851 to 1.0000. Comparative analysis with existing studies reveals competitive accuracy of 98.73% achieved by our proposed model. While variations exist in specific purposes and datasets among studies, our model showcases promising performance in soybean seed classification, contributing to advancements in agricultural technology for crop health assessment and management.

Tomato Leaves Disease Detection using Hybrid Model CNN-LSTM

Abstract: This paper delves into the exploration and comparison of Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model for the task of tomato leaf disease detection. Through rigorous experimentation and evaluation, it was determined that the CNN-LSTM hybrid model demonstrates superior performance both CNN and LSTM individually in terms of accuracy and robustness. Leveraging a comprehensive dataset comprising images of healthy and diseased tomato leaves, including various disease types, such as Bacterial Spot, Early Blight, Septorial Leaf Spot, Leaf Mold, and Yellow Leaf Curl Virus, the study demonistrate the efficacy of the suggested hybrid approach. The hybrid model capitalizes on the strengths of both CNN and LSTM, integrating spatial and temporal information for enhanced disease identification accuracy. The results highlight the effect of hybrid deep learning structures in agricultural disease management, offering a promising solution for early detection and mitigation of plant diseases. This paper dds to the expanding collection of literature on deep learning applications in agriculture and offers valuable insights for researchers and practitioners seeking to address challenges in crop health monitoring and management.

Machine Learning Algorithms for Early Detection of Legume Crop Disease

Background: Legume crops are an essential component of global agriculture and are widely supplied for human consumption, livestock feed and soil improvement due to their vital nutritional nature. The economic and nutritional significance of legumes is threatened by a multitude of diseases that can cause substantial yield losses. Traditional methods for disease detection, relying on visual inspection, are often subjective and inefficient, leading to delayed intervention. Methods: This study investigates the utilization of machine learning algorithms for the early identification of diseases affecting legume crops. A comprehensive evaluation is conducted on machine learning algorithms, namely Support Vector Machines (SVM) and Convolutional Neural Networks (CNN) with respect to the domain of disease detection. Through a comparative analysis of their performance across different environmental conditions and phases of crop development, this study also explores their strengths and weaknesses. Result: The findings and comparative examination offered significant perspectives on the potential of machine learning algorithms in the realm of early legume crop disease detection. In addition to enhancing crop health and disease management, the research provides support for sustainable agricultural practices and possesses the capacity to augment environmental sustainability and food security through the application of machine learning techniques.

Meta-Analysis Assessing Potential of Drone Remote Sensing in Estimating Plant Traits Related to Nitrogen Use Efficiency

Unmanned Aerial Systems (UASs) are increasingly vital in precision agriculture, offering detailed, real-time insights into plant health across multiple spectral domains. However, this technology’s precision in estimating plant traits associated with Nitrogen Use Efficiency (NUE), and the factors affecting this precision, are not well-documented. This review examines the capabilities of UASs in assessing NUE in crops. Our analysis specifically highlights how different growth stages critically influence NUE and biomass assessments in crops and reveals a significant impact of specific signal processing techniques and sensor types on the accuracy of remote sensing data. Optimized flight parameters and precise sensor calibration are underscored as key for ensuring the reliability and validity of collected data. Additionally, the review delves into how different canopy structures, like planophile and erect leaf orientations, uniquely influence spectral data interpretation. The study also recognizes the untapped potential of image texture features in UAV-based remote sensing for detailed analysis of canopy micro-architecture. Overall, this research not only underscores the transformative impact of UAS technology on agricultural productivity and sustainability but also demonstrates its potential in providing more accurate and comprehensive insights for effective crop health and nutrient management strategies.

Prediction of wheat SPAD using integrated multispectral and support vector machines.

Rapidly obtaining the chlorophyll content of crop leaves is of great significance for timely diagnosis of crop health and effective field management. Multispectral imagery obtained from unmanned aerial vehicles (UAV) is being used to remotely sense the SPAD (Soil and Plant Analyzer Development) values of wheat crops. However, existing research has not yet fully considered the impact of different growth stages and crop populations on the accuracy of SPAD estimation. In this study, 300 materials from winter wheat natural populations in Xinjiang, collected between 2020 to 2022, were analyzed. UAV multispectral images were obtained in the experimental area, and vegetation indices were extracted to analyze the correlation between the selected vegetation indices and SPAD values. The input variables for the model were screened, and a support vector machine (SVM) model was constructed to estimate SPAD values during the heading, flowering, and filling stages under different water stresses. The aim was to provide a method for the rapid acquisition of winter wheat SPAD values. The results showed that the SPAD values under normal irrigation were higher than those under water restriction. Multiple vegetation indices were significantly correlated with SPAD values. In the prediction model construction of SPAD, the different models had high estimation accuracy under both normal irrigation and water limitation treatments, with correlation coefficients of predicted and measured values under normal irrigation in different environments the value of r from 0.59 to 0.81 and RMSE from 2.15 to 11.64, compared to RE from 0.10% to 1.00%; and under drought stress in different environments, correlation coefficients of predicted and measured values of r was 0.69-0.79, RMSE was 2.30-12.94, and RE was 0.10%-1.30%. This study demonstrated that the optimal combination of feature selection methods and machine learning algorithms can lead to a more accurate estimation of winter wheat SPAD values. In summary, the SVM model based on UAV multispectral images can rapidly and accurately estimate winter wheat SPAD value.

REAL TIME VEHICLE COLLISONDETECTION USINGBOUNDING BOXWITH ALERT SYSTEM

This research presents an innovative application of deep learning techniques for the earlydetection and classification of plant diseases, highlighting the exceptional performance of theResNet9 model. The study begins with a meticulous implementation of ResNet9 on the diverse andextensive PlantVillage dataset, achieving an impressive 99.2% accuracy. This success is attributedto strategic parameter tuning, incorporating techniques such as learning rate scheduling, gradientclipping, and weight decay. The investigation is expanded to address unique challenges in Indianagriculture, with the curation of datasets for major crops such as cotton, rice, and groundnut. Thecommitment to practical application is manifested in the development of a userfriendly webinterface, strategically designed to empower farmers. This interface, based on Convolutional NeuralNetworks (CNNs), facilitates accurate disease identification across different crops, offering acomprehensive solution for precision agriculture. Through this tool, farmers gain valuable insightsinto disease prevention methods, enhancing their decisionmaking in sustainable crop healthmanagement. The findings underscore the efficacy and versatility of the approach, positioning it atthe forefront of leveraging technology for the advancement of global food security and agriculturalsustainability.

CROP DISEASE DETECTION USING DEEP LEARNING

—This research presents an innovative application of deep learning techniques for the earlydetection and classification of plant diseases, highlighting the exceptional performance of theResNet9 model. The study begins with a meticulous implementation of ResNet9 on the diverse andextensive PlantVillage dataset, achieving an impressive 99.2% accuracy. This success is attributedto strategic parameter tuning, incorporating techniques such as learning rate scheduling, gradientclipping, and weight decay. The investigation is expanded to address unique challenges in Indianagriculture, with the curation of datasets for major crops such as cotton, rice, and groundnut. Thecommitment to practical application is manifested in the development of a userfriendly webinterface, strategically designed to empower farmers. This interface, based on Convolutional NeuralNetworks (CNNs), facilitates accurate disease identification across different crops, offering acomprehensive solution for precision agriculture. Through this tool, farmers gain valuable insightsinto disease prevention methods, enhancing their decisionmaking in sustainable crop healthmanagement. The findings underscore the efficacy and versatility of the approach, positioning it atthe forefront of leveraging technology for the advancement of global food security and agriculturalsustainability.

Variability in bacterial endophytes in leaves of transgenic Bt and non-Bt cotton crop varieties and their role in suppression of bacterial leaf blight pathogen X. a. pv. malvacearum and the incited disease reaction

Microbial epiphytes and endophytes are an integral part of the plant system and are known to play various roles in crop growth and crop health management. The transgenic crop plays an important role in crop pest management, however, environmentalists and ecologists have reservations about the cultivation of these crops. Whether the transgenic Bt cotton and non-Bt cotton vary in their microbial habitat ecology is not yet studied. In the present investigations, the leaf endophytic bacteria were detected in the leaves of both transgenic Bt and non-Bt cotton hybrids. However, there were differences in the endophytic bacterial types and their population densities i.e. bacterial colony-forming units (cfu) in the leaves of Bt and non-Bt cotton varieties. At least ten different leaf endophytic bacteria were detected from two cotton varieties i.e. RCH-2 and Bunny (of transgenic Bt and non-Bt versions). A maximum of four types of leaf endophytic bacteria was present in RCH-2 Bt cotton leaves. The population density of leaf endophytic bacteria ranged from 50 cfu/leaf to 5 x 103 cfu/leaf and varied with individual leaf endophyte and cotton variety. These bacterial leaf endophytes were observed to inhibit or suppress the growth of bacterial leaf blight pathogen Xanthomonas axonopodis pv. malvacearum (Xam) under in-vitro test. Leaf endophyte no.7 was more effective followed by leaf endophyte no.4 in suppressing the Xam population and population of other endophytes in the interaction studies. Interaction of leaf endophytes and Xam in cotton leaves suggested that endophytes of transgenic Bunny-Bt were effective on Xam in transgenic Bunny–Bt hybrid only and so these changed the induction of susceptible water-soaking disease reaction into hypersensitive browning resistance reaction (HR). However, these endophytes of Bt-cotton were not effective in the non-Bt version in changing the susceptible reaction of Xam into an HR reaction. This indicated that the endophytes of the respective Bt and non-Bt crops were able to change the susceptible reaction of Xam into a hypersensitive one in their respective host, indicating that the use of leaf endophytes can be effective in their own habitat crop as a biocontrol agent against Xam. The specificity of leaf endophytes has to be considered in biological disease management programs.

12 Tools for Climate-Smart Decision Making for the Stocker/Feedlot Sector

Abstract There is an increased interest in the use of climate-smart practices and technologies to be more effective in climate change mitigation. These practices include grazing management, pasture management, animal and herd management, animal disease and health, animal breeding, and supplemental feeding during the stocker phase. In the feedlot sector, climate-smart practices range from supply chain challenges including climate smart adaptation by crop producers, cattle type, manure management, health management, and use of growth promoting technologies. There are certainly other technologies not mentioned and are not meant to be marginalized. During the stocker phase, grazing management is highly variable and dependent on climatic conditions and variability, plant species and plant health, water management, soil health, and cattle type. A correct balance among the different land managers, government agencies, and recommendations from university researchers and Extension personnel should optimize these practices. For instance, there is a focus on rotational grazing to increase the efficiency of grazing management. However, in the southwestern U.S. this practice may not be practical given the vast area and landscape used in production. In certain geographical areas, pasture management is becoming increasingly important as decreasing water sources (particularly aquafer levels) are apparent. Some data suggests that now is the time to change from cereal crop production to perennial forages while water is still available to establish the forages. This, in turn, may improve soil health and carbon sequestration. However, as with all mitigation strategies, this may decrease supply of cereal grains available to small feedlot producers, albeit a significant amount of cereals are transported to the cattle feeding sector. Animal breeding programs to improved production, heat tolerance, disease resistance, and improved reproduction is important. As with any production practice, supplementation programs may become necessary under certain situations. It is well known that cattle treated for respiratory disease have poorer performance and carcass characteristics than cattle not treated. Use of growth promoting technologies improve animal performance and decreases total methane produced. No doubt manure production from feeding operations produce methane. Dairy and swine operations can harvest the methane and with use of biogas collectors flare off the methane or produce energy for electric generators, however, this is not practical under feedlot situations; however, application of manure to land may improve soil organic matter. Building resilience in evaluating climate-smart practices will satisfy multiple objectives including impacting food security without many constraints to adoption.

Crop-saving with AI: latest trends in deep learning techniques for plant pathology.

Plant diseases pose a major threat to agricultural production and the food supply chain, as they expose plants to potentially disruptive pathogens that can affect the lives of those who are associated with it. Deep learning has been applied in a range of fields such as object detection, autonomous vehicles, fraud detection etc. Several researchers have tried to implement deep learning techniques in precision agriculture. However, there are pros and cons to the approaches they have opted for disease detection and identification. In this survey, we have made an attempt to capture the significant advancements in machine-learning based disease detection. We have discussed prevalent datasets and techniques that have been employed as well as highlighted emerging approaches being used for plant disease detection. By exploring these advancements, we aim to present a comprehensive overview of the prominent approaches in precision agriculture, along with their associated challenges and potential improvements. This paper delves into the challenges associated with the implementation and briefly discusses the future trends. Overall, this paper presents a bird's eye view of plant disease datasets, deep learning techniques, their accuracies and the challenges associated with them. Our insights will serve as a valuable resource for researchers and practitioners in the field. We hope that this survey will inform and inspire future research efforts, ultimately leading to improved precision agriculture practices and enhanced crop health management.