Plant Disease Prediction Research Articles

Internet of Things (IoT) and Machine Learning Model of Plant Disease Prediction–Blister Blight for Tea Plant

Crop plant diseases are a significant threat to productivity and sustainable development in agriculture. Early prediction of disease attacks is useful for the effective control of the disease by taking proactive actions against their attacks. Modern Information and Communication Technologies (ICTs) have a predominant role in Precision Agriculture (PA) applications to support sustainable developments. There is an immense need for solutions for the early prediction of the disease attack for proactive control against the plant disease attack. The present solution of disease detection using the computer vision approach can only detect the existence of the disease once the disease has already appeared. This study aims to propose a Machine Learning (ML) approach for the early prediction of the probability of disease attack based on Internet of Things (IoT) directly sensed crop field environmental conditions. Plant disease life cycles are strongly correlated with environmental conditions. The crop field environmental conditions are used to predict the occurrence of plant diseases. The Multiple Linear Regression (MLR) is applied as the ML model due to the existence of a linear relationship between disease attack and environmental conditions. Internet of Things (IoT) based crop field environmental conditions help to accurately predict the occurrence of plant diseases using the ML approach. The proposed model is implemented for the prediction of blister blight ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Exobasidium vexans</i> ) for tea ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Camellia sinensis</i> ) plant to check the effectiveness of the proposed solution. The implementation of the proposed model from 2015 to 2019 reveals that the accuracy of prediction of occurrence of the disease reached up to 91% in 2019.

Tomato Leaf Disease Detection using Deep Learning Techniques

Plant diseases cause low agricultural productivity. Plant diseases are challenging to control and identify by the majority of farmers. In order to reduce future losses, early disease diagnosis is necessary. This study looks at how to identify tomato plant leaf disease using machine learning techniques, including the Fuzzy Support Vector Machine (Fuzzy-SVM), Convolution Neural Network (CNN), and Region-based Convolution Neural Network (R-CNN). The findings were confirmed using images of tomato leaves with six diseases and healthy samples. Image scaling, color thresholding, flood filling approaches for segmentation, gradient local ternary pattern, and Zernike moments’ features are used to train the pictures. R-CNN classifiers are used to classify the illness kind. The classification methods of Fuzzy SVM and CNN are analyzed and compared with R-CNN to determine the most accurate model for plant disease prediction. The R-CNN-based Classifier has the most remarkable accuracy of 96.735 percent compared to the other classification approaches.

Towards Digital Twins for Multi-Sensor Land and Plant Monitoring

Small and medium-sized farms struggle with increased needs for monitoring in different dimensions, even by having to respond to regulatory requirements, e.g., by the global push to reduce pesticides and to improve soil health. Moreover, with the rising needs for food production there has been an effort to shift agriculture into a new era, in which the sector needs to be modernized by using new digital technologies. The goal of our research work is to provide farmers with a reliable “digital twin”, i.e., a monitoring ecosystem that allows them to visualize multi-sensor data collected from their fields, but also to "plug in" predictive models, e.g., for plant disease prediction. The paper presents an extensible solution, designed in co-creation with stakeholders, that can use a wide range of "sensors", ranging from free satellite images, low-cost off-the-shelf sensors, to even novel technologies, such as odour sensors. The TWINSOR concept is introduced, but also a first prototype applied to the vineyard is described as a first result.

Plant disease prediction using convolutional neural network

Every year India losses the significant amount of annual crop yield due to unidentified plant diseases. The traditional method of disease detection is manual examination by either farmers or experts, which may be time-consuming and inaccurate. It is proving infeasible for many small and medium-sized farms around the world. To mitigate this issue, computer aided disease recognition model is proposed. It uses leaf image classification with the help of deep convolutional networks. In this paper, VGG16 and Resnet34 CNN was proposed to detect the plant disease. It has three processing steps namely feature extraction, downsizing image and classification. In CNN, the convolutional layer extracts the feature from plant image. The pooling layer downsizing the image. The disease classification was done in dense layer. The proposed model can recognize 38 differing types of plant diseases out of 14 different plants with the power to differentiate plant leaves from their surroundings. The performance of VGG16 and Resnet34 was compared. The accuracy, sensitivity and specificity was taken as performance Metrix. It helps to give personalized recommendations to the farmers based on soil features, temperature and humidity

IoT Based Smart Agriculture and Plant Disease Prediction

Agriculture is a very prominent sector in our country and has been one of the highest contributors to the GDP. During the 1960s, an all-time high was reached with approximately 50% contribution to the GDP of the country, as more than half of the population was rural and focused primarily on agriculture as means of their livelihood. But from the latest records of 2019, the contribution by this sector has decreased to 15.96 percent. IoT plays a significant tole in remote sensing with machine learning in monitoring crops and surveying, which in turn aids agriculturists in ways for efficient field management. The proposed work integrates the role of Internet of Things and Deep learning deployment in farm management and disease identification of leaves. With the use of Internet of Things through remote sensing this work monitors the agriculture field parameters in remote cloud environment. With modified Resnet model deployed on the cloud for the purpose building a smart disease prediction. This system achieves 99.35% accuracy for the dataset. Overall this approach will provide an opportunity for agriculturists to test the plant disease with a smart phone connected to Internet and take appropriate actions.

Plant disease threats to food security in the Northern Great Plains of North America

AbstractPlant disease epidemics are responsible for millions of tons of yield loss from crops annually. To provide sufficient nutritious food, feed, fiber, and fuel for a growing world human population on a non‐expanding land resource, yield loss caused by plant pathogens must be minimized. The Northern Great Plains (NGP) region of the United States is a major crop‐producing region, but crop production in this region is threatened by climate variability, new pathogen or pathogen race development, limited in‐field management practices, pathogen synergism, and fungicide resistance in some fungal pathogens. To sustain stable food, feed, fiber, and fuel production from plants, concerted efforts from all stakeholders must be harnessed to develop new varieties that are resistant to plant pathogens and less sensitive to climate variability, promote use of integrated disease management (that incorporates resistant/tolerant varieties, plant disease prediction, and accurate disease diagnosis and assessment), and enhance early detection capabilities of new pathogens/races. Here, we review the current and near‐future likely plant disease epidemic concerns in the NGP of the United States and propose some actions to prevent or lessen the extent of the next plant disease epidemic development.

A novel explainable image classification framework: case study on skin cancer and plant disease prediction

A novel explainable image classification framework: case study on skin cancer and plant disease prediction

PlanTech: Early Detection of Plant Disease Based on HWSN Using Deep Learning

Plant diseases are a major threat to food security. Thus, the identification of these diseases is crucial to alleviate the problem. Deep learning combined with image processing has proven to be efficient in order to identify such diseases accurately, automatically and quickly. This article presents a general architecture for plant disease prediction based on the Hybrid Wireless Sensor Network, the Internet of Things, and Deep Learning algorithms. In this work, the focus is on learning models for plant disease detection to be implemented afterward on the structure for actual trials. Thus, several deep learning architectures have been tested, i.e. ResNet50, 101, and 152, AlexNet, VGG, SqueezeNet, DenseNet, and Inception. In addition to that, a new parallel architecture has been developed and evaluated by combining two deep learning architectures. Several optimizers such as SGD and ADAM have been leveraged in order to improve the performances. The public published database PlantVillage is used for model learning, which contains 54.306 images of agricultural plant leaves. As a result, the best validation accuracy score of 98,09% is achieved using the presented para model with ADAM optimizer running with the 80/20 splitting data on the 14th epoch.

Plant disease prediction using classification algorithms

&lt;p&gt;This paper investigates the capability of six existing classification algorithms (Artificial Neural Network, Naïve Bayes, k-Nearest Neighbor, Support Vector Machine, Decision Tree and Random Forest) in classifying and predicting diseases in soybean and mushroom datasets using datasets with numerical or categorical attributes. While many similar studies have been conducted on datasets of images to predict plant diseases, the main objective of this study is to suggest classification methods that can be used for disease classification and prediction in datasets that contain raw measurements instead of images. A fungus and a plant dataset, which had many differences, were chosen so that the findings in this paper could be applied to future research for disease prediction and classification in a variety of datasets which contain raw measurements. A key difference between the two datasets, other than one being a fungus and one being a plant, is that the mushroom dataset is balanced and only contained two classes while the soybean dataset is imbalanced and contained eighteen classes. All six algorithms performed well on the mushroom dataset, while the Artificial Neural Network and k-Nearest Neighbor algorithms performed best on the soybean dataset. The findings of this paper can be applied to future research on disease classification and prediction in a variety of dataset types such as fungi, plants, humans, and animals.&lt;/p&gt;

Early Prediction of Plant Diseases using CNN and GANs

Plant diseases enormously affect the agricultural crop production and quality with huge economic losses to the farmers and the country. This in turn increases the market price of crops and food, which increase the purchase burden of customers. Therefore, early identification and diagnosis of plant diseases at every stage of plant life cycle is a very critical approach to protect and increase the crop yield. In this paper using a deep-learning model, we present a classification system based on real-time images for early identification of plant infection prior of onset of severe disease symptoms at different life stages of a tomato plant infected with Tomato Mosaic Virus (TMV). The proposed classification was applied on each stage of the plant separately to obtain the largest data set and manifestation of each disease stage. The plant stages named in relation to disease stage as healthy (uninfected), early infection, and diseased (late infection). Classification was designed using the Convolutional Neural Network (CNN) model and the accuracy rate was 97%. Using Generative Adversarial Networks (GANs) to increase the number of real-time images and then apply CNN on these new images and the accuracy rate was 98%.

Disease sniffing robots to apps fixing plant diseases: applications of artificial intelligence in plant pathology—a mini review

The recent advancements in artificial intelligence (AI) and machine learning have wide applications in plant pathology with sensors, drones, robots and intelligent monitoring systems. Computer vision based phenotyping of plant stress, diagnostics and severity assessment of plant diseases has gained momentum in horticultural and field crops. Internet of things based on networking sensors for biomarkers of disease like volatile organic compounds are being used for early detection and prediction of plant diseases and host-pathogen interaction studies. Unmanned arial vehicles are employed for phenotyping orchards for precise application of plant protection chemicals. Smartphone based field diagnostics are gaining popularity across the world especially in the remote locations where the laboratory diagnostics of diseases is difficult. AI in plant pathology is still at its infancy. Integration of AI and augmented reality will enhance the accuracy and automation for remote diagnostics of plant diseases and precision plant protection. The “self sufficient, disease free, perfect plant” concept will soon become reality with the help of plant-robot bio-hybrids. This mini review explores the present status of AI technologies in plant pathology and tries to find answers for the questions like what are the common platforms used, which are the diseases where technology is applied, what are the challenges and the future prospects.

SCrop: A Novel Device for Sustainable Automatic Disease Prediction, Crop Selection, and Irrigation in Internet-of-Agro-Things for Smart Agriculture

Agriculture Cyber-Physical System (A-CPS) is becoming increasingly important in enhancing crop quality and productivity by utilizing minimum cropland. This paper introduces the innovative idea of the Internet-of-Agro-Things (IoAT) with an explanation of the automatic detection of plant disease for the development of ACPS. Majority of the crops were infected by microbial diseases in conventional agriculture. Also, the constantly mutating pathogens cannot be known to the knowledge of the farmer, due to which, there arises a demand to develop a disease prediction system. To prevent this, we use a trained Convolutional Neural Network (CNN) model to perform an analysis of the crop image captured by a health maintenance system. The image capturing along with continuous sensing and intelligent automation is performed by the solar sensor node. The sensor node houses a developed soil moisture sensor which has a high longevity compared to its peers. A real time implementation of the proposed system is demonstrated using a solar sensor node with a camera module, a microcontroller and a smartphone application using which a farmer can monitor the field. The prototype was deployed for three months and has achieved a robust performance by remaining rust-free and sustaining the varied weather conditions. An accuracy of 99.24% is achieved by the proposed plant disease prediction framework.

A survey on plant disease prediction using machine learning and deep learning techniques

The major agricultural products in India are rice, wheat, pulses, and spices. As our population is increasing rapidly the demand for agriculture products also increasing alarmingly. A huge amount of data are incremented from various field of agriculture. Analysis of this data helps in predicting the crop yield, analyzing soil quality, predicting disease in a plant, and how meteorological factor affects crop productivity. Crop protection plays a vital role in maintaining agriculture product. Pathogen, pest, weed, and animals are responsible for the productivity loss in agriculture product. Machine learning techniques like Random Forest, Bayesian Network, Decision Tree, Support Vector Machine etc. help in automatic detection of plant disease from visual symptoms in the plant. A survey of different existing machine learning techniques used for plant disease prediction was presented in this paper. Automatic detection of disease in plant helps in early diagnosis and prevention of disease which leads to an increase in agriculture productivity.

Application of extreme learning machine in plant disease prediction for highly imbalanced dataset

Plant diseases are responsible for global economic losses due to degradation in the quality and productivity of plants. Therefore, plant disease prediction has become an essential area of research for agricultural scientists. The current study implements Extreme Learning Machine (ELM) algorithm for plant disease prediction based on a dataset collected in real time scenario namely Tomato Powdery Mildew Disease (TPMD) dataset. Since, the collected TPMD dataset was imbalanced thus; various resampling techniques namely Importance Sampling (IMPS), Synthetic Minority Over-sampling Technique (SMOTE), Random under Sampling (RUS), and Random over Sampling (ROS) have been used here for balancing the dataset before using it in the specified prediction model. ELM models have been developed for each of the balanced TPMD datasets obtained from these resampling techniques as well as for the imbalanced TPMD dataset. Area under Curve (AUC) and Classification Accuracy (CA) are considered as performance measures to analyze the performance of ELM model. Results show that ELM performed better for TPMD dataset using resampling techniques. Best results are obtained with IMPS technique having maximum values for CA and AUC i.e. 89.19% and 88.57% respectively.

Advanced Data Analysis as a Tool for Net Blotch Density Estimation in Spring Barley

A novel data analysis method for the evaluation of plant disease risk that utilizes weather information is presented in this paper. This research considers two different datasets: open weather data from the Finnish Meteorological Institute and long-term (1991–2017) plant disease severity observations in different hardiness zones in Finland. Historical net blotch severity data on spring barley were collected from official variety trials carried out by the Natural Resources Institute Finland (Luke) and the analysis was performed with existing data without additional measurements. Feature generation was used to combine different datasets and to enrich the information content of the data. The t-test was applied to validate features and select the most suitable one for the identification of datasets with high net blotch risk. Based on the analysis, the selected daily measured variables for the estimation of net blotch density were the average temperature, minimum temperature, and rainfall. The results strongly indicate that thorough data analysis and feature generation methods enable new tools for plant disease prediction. This is crucial when predicting the disease risk and optimizing the use of pesticides in modern agriculture. Here, the developed system resolves the correlation between weather measurements and net blotch observations in a novel way.

AN EMPIRICAL STUDY ON MACHINE LEARNING ALGORITHM FOR PLANT DISEASE PREDICTION

In this study, a neuroevolution algorithm has been developed for predicting various diseases in plants. The machine learning algorithms support different classification techniques that can be demonstrated for the performance improvement in plant disease prediction. Prediction of the disease depends on the weather factors which have a relationship with climate change data, the soil of that area. Here we have illustrated an approach of implementing the neuroevolution model based on ANN for predicting various plant diseases. Multiple causes and the type of illness that can affect different plants during the different seasons are predicted. Therefore the result of the proposed model assists in decision making in advance in precaution taking in a disease that may affect the plant. The results are utilized for making an advanced decision for disease avoidance in plants as well as various farm activities throughout multiple-stage it also uses the same model that can be utilized for predicting various agricultural data such as yield prediction and weather prediction.

Deep Learning based Model for Plant Disease Detection

Plant disease prediction is vital in Agriculture sector. Farmer's economic growth depends on the quality of the products that they produce, which relies on the plant's growth and the yield they get. Identifying the disease can lead to quicker interventions that can be implemented to reduce the effects of major economic loss. There may be high degree of complexity in diagnosing the various types of diseases in plants through leaves of the plants. Manual mode of plant disease detection is a tedious process. In this proposed work, Convolutional Neural Network methodologies like Sequential model and SmallerVGG model were utilized for detecting diseases in plants and diagnosis using plant leaf image. Among these two models, SmallerVGG model achieved more accuracy rate of 87% than 65% of sequential model.

Prediction of plant diseases through modelling and monitoring airborne pathogen dispersal.

Abstract Many plant diseases that spread by airborne inocula have had major economic and social impacts worldwide. Plant diseases account for 16% of the yield losses in eight of the most important food and cash crops. Numerical models and monitoring networks have been developed to forecast the spread of these diseases both locally and over long distances. The epidemics of these airborne diseases depend on production of infectious propagules, their aerial transport, specific infectiousness and finally their reproduction. This article first reviews current understanding of these processes with an emphasis on their treatments in disease forecast models as well as the uncertainties the treatments introduce. Then we discuss the concepts and frameworks of forecast models that are broadly classified into epidemic models and aerobiological models and, finally, we present an example of the application of these modelling approaches to soybean rust forecasting.

Disease Cycle Approach to Plant Disease Prediction

Plant disease cycles represent pathogen biology as a series of interconnected stages of development including dormancy, reproduction, dispersal, and pathogenesis. The progression through these stages is determined by a continuous sequence of interactions among host, pathogen, and environment. The stages of the disease cycle form the basis of many plant disease prediction models. The relationship of temperature and moisture to disease development and pathogen reproduction serve as the basis for most contemporary plant disease prediction systems. Pathogen dormancy and inoculum dispersal are considered less frequently. We found extensive research efforts evaluating the performance of prediction models as part of operation disease management systems. These efforts appear to be greater than just a few decades ago, and include novel applications of Bayesian decision theory. Advances in information technology have stimulated innovations in model application. This trend must accelerate to provide the disease management strategies needed to maintain global food supplies.

Simulation of surface wetness with a water budget and energy balance approach

Surface wetness plays an important role in environmental studies. In particular, it is a major variable for plant disease prediction. Surface wetness is commonly measured with electronic sensors but simulation with a surface wetness model is an alternative. Recently, the increased use of interpolation procedures and atmospheric models to produce site-specific weather products has created a greater need for reliable surface wetness models. However, surface wetness models have not been widely used operationally because they are often highly complex, do not simulate both dews and rain or do not adapt well to a new spatial scale or crop. Other models estimate surface wetness in units that are cumbersome to observe in the field. In addition, few models have been calibrated to observed surface wetness over a wide range of atmospheric variables and plant leaf properties under controlled environmental conditions. The objective of this study was to develop a surface wetness model that would be appropriate for operational use in site-specific weather products for grapes. For this purpose, we developed the surface wetness energy balance (SWEB) model based on a ‘big leaf’. The SWEB model consists of four sub-modules describing: (i) surface water distribution based on an observed wet fraction; (ii) canopy water budget; (iii) energy balance module based on a combination equation developed by Tanner and Fuchs; (iv) a transfer function based on Bird et al.'s generic transfer coefficient that was previously calibrated to surface wetness under controlled conditions. The SWEB model can be adapted to the physical characteristics of a particular crop by adjusting four plant parameters: leaf area index (LAI), maximum fraction of canopy allowed as wet surface area ( W max), crop height and maximum water storage. The SWEB model is most sensitive to LAI and W max. The SWEB model is close to the required criteria for a suitable surface wetness model including simplicity, utility, scalability, easily observable output units and in addition, it has been calibrated under controlled conditions. The SWEB model was validated in a vineyard and in a companion study, compared to a widely used sensor. The overall objective of these studies was to develop a theoretical standard for surface wetness measurement.