Plant Health Monitoring Research Articles

Multi Techniques for Agricultural Image Disease Classification and Detection: A Review

The agriculture sector has a significant impact on the market in every country. Identifying crop disease with conventional methods is a hard operation and it needs more time, effort, and experts with continuous farm monitoring. Blight and other crop diseases have severe consequences on crop yields and cause enormous economic losses worldwide. Plant health monitoring and disease detection are critical components of sustainable agriculture. Machine learning and deep learning techniques are used to identify plant diseases and associated with severity detection in plant leaves. The adoption of these techniques still faces several important challenges. In recent years, improvements in technology and researchers’ interest in this area have made it possible to obtain an optimal solution. In addition to providing a detailed explanation of the proposed technique, which is deep learning architecture that uses the deep convolutional extreme learning machine (DC-ELM) for faster training, this study focuses on how machine learning and deep learning techniques detect plant diseases and infections that affect different crops. The proposed model is capable of providing good computational performance and allowing the learning process to be completed with less processing time. Finally, several challenges and problems with the existing system, as well as future research objectives, are enumerated and discussed.

Optical monitoring of the plant growth status using polarimetry

Polarimetry is a powerful characterization technique that uses a wealth of information from electromagnetic waves, including polarization. Using the rich information provided by polarimetry, it is being actively studied in biomedical fields such as cancer and tumor diagnosis. Despite its importance and potential in agriculture, polarimetry for living plants has not been well studied. A Stokes polarimetric imaging system was built to determine the correlation between the polarization states of the light passing through the leaf and the growth states of lettuce. The Stokes parameter s3 associated with circular polarization increased over time and was strongly correlated with the growth of lettuce seedlings. In the statistical analysis, the distribution of s3 followed the generalized extreme value (GEV) probability density function. Salt stress retarded plant growth, and the concentration of treated sodium chloride (NaCl) showed a negative correlation with the location parameter μ of GEV. The clear correlation reported here will open the possibility of polarization measurements on living plants, enabling real-time monitoring of plant health.

Microneedle Technologies for Food and Crop Health: Recent Advances and Future Perspectives

The global food supply constantly faces the threats of emerging crop diseases initiated by pathogens such as bacteria, fungi, and viruses. Plant diseases can cause significant economic and production losses in the agriculture industry, and early disease detection significantly mitigates losses. Monitoring the food quality and detecting pathogens during the food supply chain is essential in confirming the food's safety and reducing crop loss. This results in lowering production costs and increasing average yield in the agriculture industry. Considering the significant development of nanotechnology in biomedicine for human health monitoring, diagnostics, and treatment, there is an increasing interest in using nanotechnology in crop production, health, and plant science. This technology can allow continuous monitoring of plant health and on‐site diagnostics of plant diseases. While many microneedle‐based devices are previously reported for human health monitoring, diagnostics, and treatment, the application of this technology to agriculture started relatively recently. This review investigates the recent development of microneedle technology in food and crop health, where the most state‐of‐the‐art microneedle‐based devices are utilized for plant drug delivery, disease monitoring, and diagnosis. Finally, the current challenges and future directions in developing microneedle technology for food and crop health are discussed.

Plant disease symptom segmentation in chlorophyll fluorescence imaging with a synthetic dataset.

Despite the wide use of computer vision methods in plant health monitoring, little attention is paid to segmenting the diseased leaf area at its early stages. It can be explained by the lack of datasets of plant images with annotated disease lesions. We propose a novel methodology to generate fluorescent images of diseased plants with an automated lesion annotation. We demonstrate that a U-Net model aiming to segment disease lesions on fluorescent images of plant leaves can be efficiently trained purely by a synthetically generated dataset. The trained model showed 0.793% recall and 0.723% average precision against an empirical fluorescent test dataset. Creating and using such synthetic data can be a powerful technique to facilitate the application of deep learning methods in precision crop protection. Moreover, our method of generating synthetic fluorescent images is a way to improve the generalization ability of deep learning models.

Confirmatory detection and identification of biotic and abiotic stresses in wheat using Raman spectroscopy.

Wheat is one of the oldest and most widely cultivated staple food crops worldwide. Wheat encounters an array of biotic and abiotic stresses during its growth that significantly impact the crop yield and consequently global food security. Molecular and imaging methods that can be used to detect such stresses are laborious and have numerous limitations. This catalyzes the search for alternative techniques that can be used to monitor plant health. Raman spectroscopy (RS) is a modern analytical technique that is capable of probing structure and composition of samples non-invasively and non-destructively. In this study, we investigate the accuracy of RS in confirmatory diagnostics of biotic and abiotic stresses in wheat. Specifically, we modelled nitrogen deficiency (ND) and drought, key abiotic stresses, and Russian wheat aphid (Diuraphis noxia) infestation and viral diseases: wheat streak mosaic virus (WSMV) and Triticum mosaic virus (TriMV), economically significant biotic stresses in common bread wheat. Raman spectra as well as high pressure liquid chromatography (HPLC)-based analyses revealed drastically distinct changes in the intensity of carotenoid vibration (1185 cm-1) and in the concentration of lutein, chlorophyll, and pheophytin biomolecules of wheat, triggered in response to aforementioned biotic and abiotic stresses. The biochemical changes were reflected in unique vibrational signatures in the corresponding Raman spectra, which, in turn could be used for ~100% accurate identification of biotic and abiotic stresses in wheat. These results demonstrate that a hand-held Raman spectrometer could provide an efficient, scalable, and accurate diagnosis of both biotic as well as abiotic stresses in the field.

Non-Contacting Plant Health Monitoring via Ultrasound in Ambient Air

In this work, we report a non-destructive and non-contacting ultrasound system with a novel air-coupled transducer to continuously monitor the drying process of prickly pear (nopal) pads in a lab environment. Compared with conventional imaging and spectroscopic methods or electrical-based approaches, ultrasound-based methods are non-invasive, cost-effective, and suitable for large volume evaluation. The time-dependent elastic modulus of the cactus can be obtained and monitored by using our proposed ultrasonic method. The evaluated elastic modulus behavior shows a good agreement with the destructive testing results in the existing literature. With further development, the proposed method can be used for in vivo plant health monitoring.

Vegetation detection using vegetation indices algorithm supported by statistical machine learning.

In precision agriculture (PA), the usage of image processing, artificial intelligence, data analysis, and internet of things provides an increase in efficiency, energy, and time saving. In image processing-based applications, vegetation detection, in other words, segmentation that allows monitoring of plant growth and health as well as identification of weeds has a great importance. Vegetation indices (VIs) are widely used algorithms for segmentation. Their advantages include low computational cost and easy implementation and handling compared to the other algorithms. Nevertheless, they require a manual threshold detection that customizes the process and prevents generalization. In this study, a novel automatic segmentation method, which does not require a manual threshold detection by combining VIs with a classification algorithm, is proposed. It deals with the segmentation process as a two class classification problem (vegetation and background). As the classification algorithm, Discriminative Common Vector Approach (DCVA) that has a high discrimination power is used. Each image pixel is represented with a 3 × 1 dimensional vector whose elements correspond to Excess Green (ExG), Green minus Blue (GB), and Color Index of Vegetation (CIVE); VI values are obtained. Then, on the sample space accepting this pixel vector as a sample, DCVA is applied and a discriminative common vector for each class which is unique and describes that class in the best way possible is obtained and it is used for classification. Proposed segmentation method's performance is compared with Convolutional Neural Networks (CNN) and Random Forest (RF) algorithm. The proposed segmentation algorithm outperformed both CNN's and RF's performance.

5D-fusion imaging for surface shape, polarization, and hyperspectral measurement.

We present a five-dimensional (5D) imager that is capable of simultaneous detection of the surface shape, spectral characteristics, and polarization states of macroscopic objects, and straightforwardly fuse collected data into a 5D data set. A polarized module that uses a polarized camera obtains polarized images, while a 3D hyperspectral module reconstructs the target as a 3D point cloud using a fringe projection technique. A liquid-crystal tunable filter is placed in front of the camera of this module to acquire spectral data that can be assigned to corresponding point clouds directly. The two modules are coupled by a dual-path configuration that allows the polarization information to be merged into a comprehensive point cloud with spectral information, generating a new 5D model. The 5D imager shows excellent performance, with a spectral resolution of 10 nm, depth accuracy of 30.7 µm, and imaging time of 8 s. Sample experiments on a toy car with micro scratch defects and a yellowing plant are presented to demonstrate the capabilities of the 5D imager and its potential for use in a broad range of applications, such as industrial manufacturing inspection, plant health monitoring, and biological analysis.

A Comprehensive Review of Emerging Technologies: Machine Learning and UAV in Crop Management

It is a known fact that India is one among the major food producers in the world. Due to the rapid urbanization and Agrochemical interventions, plants are infected by insects, pathogens, massive infestations, which leads to the deficiency of growth nutrients and ions, thereby minimizing agricultural crop yield. These infections occur in several forms like aphids, black root rot, cankers, leaf curls, rusts, anthracnose, and blights make agriculture fail to thrive and increase the impact of crop diseases. Since plant disease prevention is a continuous process that occurs regularly, agriculturists follow several strategies to keep their crops disease-free. An efficient monitoring and supporting system for continuous and long-term plant and soil health monitoring is needed to meet the needs of growing population. In this paper, existing research works in Precision agriculture, emerging technologies – GPS, GIS, Machine learning and UAVs in analyzing crop health analysis, soil health monitoring, and crop yield prediction are reviewed.

SPDPOA: Student Psychology Dragonfly Political Optimizer Algorithm-Based Soil Moisture and Heat-Level Prediction for Plant Health Monitoring in Internet of Things

Abstract This article devised an effective Student Psychology-based Dragonfly Political Optimizer (SPDPOA) for predicting heat level and soil moisture to monitor plant health in the Internet of Things (IoT). The developed SPDPOA is modeled by integrating the Student Psychology-based Optimization (SPBO) algorithm, Dragonfly Algorithm (DA) and Political optimizer (PO), respectively. The prediction process is done in the base station (BS), which gathers the IoT nodes’ information through optimal Cluster Head (CH) using Deep Recurrent Neural Network (Deep RNN). Moreover, the CH selection and routing process are established using a developed SPDPOA scheme. The data transformation and feature selection processes are done based on Box-Cox transformation and wrapper model, correspondingly, which helps in the selection of best features. Moreover, the developed SPDPOA scheme attained better performance in Packet Delivery Ratio (PDR), energy and testing accuracy of 0.7232, 0.6342 J and 0.9372, respectively.

Plantosphere: Next Generation Adaptive and Smart Agriculture System

Around 75% of the population in India is engaged in agriculture and farming. The sustainability of every economy is based on agriculture. It has a major influence on financial growth and fundamental transformation in the long run. Artificial intelligence will usher in a revolution in agricultural operations in the future. This revolution has protected crops from being negatively affected by a variety of factors such as climate change, soil porosity, and water availability. Crop monitoring, soil management, and insect identification, to name a few examples, are all conceivable uses of artificial intelligence in agriculture. The primary purpose of artificial intelligence is to close the knowledge gap that exists between inventors and farmers. Detecting disease and monitoring plant health are two of the most difficult challenges in sustainable farming. As a result, image processing technology must be used to detect plant sickness at an early stage. Photographic capture, preprocessing, segmentation, feature extraction, and sickness categorization are all part of the procedure. In reality, computer image processing was used long before human eyes were able to detect the signs and symptoms of the disease. Taking into account the climatic conditions in various parts of the world. Climate change directly affects crop output. Several soil and atmospheric characteristics are detected to anticipate the optimal crop. Sedimentation is measured by soil parameters such as pH and moisture. Today, a platform that allows farmers to advertise their products is in high demand. This paper proposes a system where farmers sell directly to clients, bypassing wholesalers and traders. A predictive analytics solution is required to maximize the farmer’s profit.

Raman spectroscopy for nutritional stress detection in plant vascular tissue

Next-generation agriculture must address its high energy-intensive resource utilization footprint such as excessive use of fertilizer and water. Plants are also sources of natural polymers (cellulose, lignin, and pectin) that have important implications in sustainable materials design. Hence healthy plant growth with optimum utilization and production is essential for future growth, which demands new technologies and sensors for on-field precision agriculture. Here we used Raman spectroscopy (RS) to non-invasively monitor soybean development, a plant of immense economic importance for fuel, feed, and food. We focus on its compositional changes at multiple time points as it transitions from the vegetative (or rapid growth) to the reproductive (or flowering) stage subjected to nitrogen and nutrient stress to identify several indicators of health. The longitudinal growth was severely limited under total nutritional stress. Simultaneously, the cell wall showed early lignification to control growth and allow for efficient transport of limited resources. Healthier plants showed activation of early defense mechanisms via tetraterpenes, greater protein production capacity via glutamic acid, and late lignification by week 12. Nitrogen stressed plants also showed stunted growth though they showed a similar defense mechanism and later lignification as the healthy condition. These differences in the concentrations of structural polymers, stress signaling molecules, and structural growth inhibitors at different time points and variable stress demonstrated the suitability of Raman spectroscopy for precision plant health monitoring. Development such as the current study is a step towards creating tools, devices, and computational models for next-generation farming.

Multi-Functional Agribot

Abstract: This project aims to design an agricultural robot to perform operations such as plowing, seeding, leveling, pesticide spraying, and plant health monitoring. The proposed Agribot is built by using the Raspberry Pi microcontroller. The microcontroller, the heart of the robotic system can manipulate the whole actions of the system. A motor driving circuit is used to drive the DC motors which in turn control the wheel motion. The Raspberry pi is given with a high-tech web camera for capturing the image, since the resolution of the given Raspberry pi camera is not sufficient to get the clarity image, Wi-Fi is used for the manual control of the robot. The Agribot is powered using a 12V battery. This 12V is used for the functioning of all other components like Relay, Motors, and Motor Drivers. Keywords: Robotic system, Raspberry Pi, Wi-Fi, Web Camera, Plant health monitoring.

IOT BASED AUTOMATIC PLANT MONETORING AND PREDECTION SYSTEM

Plant Health Management is the process of researching and overcoming the issues that limit a plant's ability to reach its full genetic potential, such as crop, adornment, timber, and other uses. Crop management is one of the most critical aspects of any agricultural setting. The plant health monitoring system and the numerous elements that affect plant growth will be discussed in this study. Temperature, humidity, soil moisture, light, and other variables are detected by several sensors, which send the data to the Arduino Uno board, which then delivers it to the user's smartphone. An alarm message is sent to the user's smartphone if any variation in the data is discovered. The user can examine the data and take appropriate measures to save the plant, such as adequate watering, ample sunlight, and so on

Field Protection and Plant Health Monitoring System using IoT

Agriculture is one of the most leading sectors in anyone’s life. Crop damage caused by animals and insects possess a serious threat to farmers, one of the major aspects is that it reduces crop yield. Mainly animals like buffalos, pigs, monkeys, birds are some which is the main reason for crop damage. This output leads to loss to the farmers and animals and birds puts up challenge for the farmers for crop protection. IoT based framework is one smart technology that can be used for crop protection. The process follows as when the animal enters the field it captures the movement of the animal and segregates into frames, identifies what animal it is and produces a buzzer sound of another animal that current animal is afraid off. The plant health monitoring is also done using comparison algorithm in machine learning and it sends a warning message to the farmer regarding the plant is healthy or not. This ensures that developed system will not be harmful to animals and as well as human beings and overall crop protection is being done. Various machine learning techniques are used in combination with IoT technology.

Mobile Computing for Pest and Disease Management Using Spectral Signature Analysis: A Review

The demand for mobile applications in agriculture is increasing as smartphones are continuously developed and used for many purposes; one of them is managing pests and diseases in crops. Using mobile applications, farmers can detect early infection and improve the specified treatment and precautions to prevent further infection from occurring. Furthermore, farmers can communicate with agricultural authorities to manage their farm from home, and efficiently obtain information such as the spectral signature of crops. Therefore, the spectral signature can be used as a reference to detect pests and diseases with a hyperspectral sensor more efficiently than the conventional method, which takes more time to monitor the entire crop field. This review aims to show the current and future trends of mobile computing based on spectral signature analysis for pest and disease management. In this review, the use of mobile applications for pest and disease monitoring is evaluated based on image processing, the systems developed for pest and disease extraction, and the structure of steps outlined in developing a mobile application. Moreover, a comprehensive literature review on the utilisation of spectral signature analysis for pest and disease management is discussed. The spectral reflectance used in monitoring plant health and image processing for pest and disease diagnosis is mentioned. The review also elaborates on the integration of a spectral signature library within mobile application devices to obtain information about pests and disease in crop fields by extracting information from hyperspectral datasets. This review demonstrates the necessary scientific knowledge for visualising the spectral signature of pests and diseases using a mobile application, allowing this technology to be used in real-world agricultural settings.

Terahertz-Based Joint Communication and Sensing for Precision Agriculture: A 6G Use-Case

By 2050, experts estimate that the agricultural produce must increase by 60%–70% to meet the needs of the ever increasing population of the world. To this aim, the concept of precision agriculture or smart farming has recently been coined. The idea of precision agriculture is well represented as a smart management system, having the ability to monitor, observe, sense, measure and control the health and water contents in plants at nano-scale and crops at macro-scale. The goal is to maximise the production while preserving the vital resources. The combination of terahertz (THz) based sensing technology to estimate plant health at a cellular level, and wireless sensor networks deployed within crops to monitor different variables while making intelligent decisions is far reaching. The integration and operation of such a macro-nano-sensor system requires a sustainable communication infrastructure that considers the demands of remote and agile agricultural environments. In this paper, an integrated sensing and communication system for plant health monitoring that utilises THz signals, is presented as a 6G use case. The joint architecture is outlined and various challenges including energy harvesting, practical implementation among others, followed by recommendations for future research are presented.

Potential Applications of Engineered Nanoparticles in Plant Disease Management: A Critical Update

Plant diseases caused by pathogenic entities pose severe issues to global food security. Effective sensory applications and tools for the effective determination of plant diseases become crucial to the assurance of food supply and agricultural sustainability. Antibody–mediated molecular assays and nucleic acid are gold–standard approaches for plant disease diagnosis, but the evaluating methodologies are liable, complex, and laborious. With the rise in global food demand, escalating the food production in threats of diverse pathogen ranges, and climate change is a major challenge. Engineered nanoparticles (NPs) have been inserted into conventional laboratory sequence technologies or molecular assays that provide a remarkable increment in selectivity and sensitivity. In the present scenario, they are useful in plant disease management as well as in plant health monitoring. The use of NPs could sustainably mitigate numerous food security issues and or threats in disease management by decreasing the risk of chemical inputs and alleviating supra detection of pathogens. Overall, this review paper discusses the role of NPs in plant diseases management, available commercial products. Additionally, the future directions and their regulatory laws in the usage of the nano–diagnostic approach for plant health monitoring have been explained.

Dragonfly Political Optimizer Algorithm-Based Rider Deep Long Short-Term Memory for Soil Moisture and Heat Level Prediction in IoT

Abstract Different computerized technologies to monitor plant health in the Internet of Things (IoT) paradigm gained various benefits but generating accurate result in the soil moisture and heat level prediction is the potential challenge. Thus, an effective Dragonfly Political Optimizer Algorithm-based Rider Deep Long Short-Term Memory (DPOA-based Rider Deep LSTM) is developed for generating better prediction results of soil moisture and heat level. The proposed DPOA is the integration of the Dragonfly Algorithm and Political Optimizer. The proposed system maintains the Base Station (BS) that collects the information from the IoT nodes through Cluster Head. At BS, the data transformation is carried out using Yeo Johnson transformation. The transformed result is transferred to feature selection, which is evaluated by holoentropy, and finally, the prediction process of soil moisture and the heat level is done at BS using the proposed method. The proposed method achieved higher performance in terms of Packet Delivery Ratio, energy, accuracy, sensitivity and specificity with the values of 0.7156, 0.7123, 0.9474, 0.9523 and 0.9254, respectively.

Recent advances in flexible pressure/strain sensors using carbon nanotubes

In the context of the information society, wearable devices show broad prospects in the fields of vital signs monitoring, plant health monitoring, artificial electronic skin. As an inseparable part of wearable devices, flexible pressure/strain sensors have attracted wide attention. Structures and active materials are core factors affecting sensing performance. For the past few years, the introduction of carbon materials, especially carbon nanotubes, has provided more possibilities for improving performance. Great efforts have been devoted to researching pressure/strain sensors based on carbon nanotubes with excellent performance or unique features. Herein, the process in recent years in novel flexible pressure/strain sensors based on carbon nanotubes is reviewed. Fabrication strategies are discussed because it suggests sensing performance with significant differences and gives additional features like biodegradability and corrosion resistance to sensors. Furthermore, the scope of application has been extended to plant monitor, except for common human movement monitor. This review can help the researchers compare the influence of different fabrication strategies on the sensing performance and provide references for fabricating sensors in different applications. Keywords: carbon nanotube, flexible sensor, strain sensor, pressure sensor DOI: 10.25165/j.ijabe.20221502.7364 Citation: Ma C, Zhou RY, Xie L J. Recent advances in flexible pressure/strain sensors using carbon nanotubes. Int J Agric & Biol Eng, 2022; 15(2): 1–12.