Disease Forecasting Research Articles

Infodemiology and Infoveillance: Scoping Review.

BackgroundWeb-based sources are increasingly employed in the analysis, detection, and forecasting of diseases and epidemics, and in predicting human behavior toward several health topics. This use of the internet has come to be known as infodemiology, a concept introduced by Gunther Eysenbach. Infodemiology and infoveillance studies use web-based data and have become an integral part of health informatics research over the past decade.ObjectiveThe aim of this paper is to provide a scoping review of the state-of-the-art in infodemiology along with the background and history of the concept, to identify sources and health categories and topics, to elaborate on the validity of the employed methods, and to discuss the gaps identified in current research.MethodsThe PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines were followed to extract the publications that fall under the umbrella of infodemiology and infoveillance from the JMIR, PubMed, and Scopus databases. A total of 338 documents were extracted for assessment.ResultsOf the 338 studies, the vast majority (n=282, 83.4%) were published with JMIR Publications. The Journal of Medical Internet Research features almost half of the publications (n=168, 49.7%), and JMIR Public Health and Surveillance has more than one-fifth of the examined studies (n=74, 21.9%). The interest in the subject has been increasing every year, with 2018 featuring more than one-fourth of the total publications (n=89, 26.3%), and the publications in 2017 and 2018 combined accounted for more than half (n=171, 50.6%) of the total number of publications in the last decade. The most popular source was Twitter with 45.0% (n=152), followed by Google with 24.6% (n=83), websites and platforms with 13.9% (n=47), blogs and forums with 10.1% (n=34), Facebook with 8.9% (n=30), and other search engines with 5.6% (n=19). As for the subjects examined, conditions and diseases with 17.2% (n=58) and epidemics and outbreaks with 15.7% (n=53) were the most popular categories identified in this review, followed by health care (n=39, 11.5%), drugs (n=40, 10.4%), and smoking and alcohol (n=29, 8.6%).ConclusionsThe field of infodemiology is becoming increasingly popular, employing innovative methods and approaches for health assessment. The use of web-based sources, which provide us with information that would not be accessible otherwise and tackles the issues arising from the time-consuming traditional methods, shows that infodemiology plays an important role in health informatics research.

An integrated research framework combining genomics, systems biology, physiology, modelling and breeding for legume improvement in response to elevated CO2 under climate change scenario

How unprecedented changes in climatic conditions will impact yield and productivity of some crops and their response to existing stresses, abiotic and biotic interactions is a key global concern. Climate change can also alter natural species’ abundance and distribution or favor invasive species, which in turn can modify ecosystem dynamics and the provisioning of ecosystem services. Basic anatomical differences in C3 and C4 plants lead to their varied responses to climate variations. In plants having a C3 pathway of photosynthesis, increased atmospheric carbon dioxide (CO2) positively regulates photosynthetic carbon (C) assimilation and depresses photorespiration. Legumes being C3 plants, they may be in a favorable position to increase biomass and yield through various strategies. This paper comprehensively presents recent progress made in the physiological and molecular attributes in plants with special emphasis on legumes under elevated CO2 conditions in a climate change scenario. A strategic research framework for future action integrating genomics, systems biology, physiology and crop modelling approaches to cope with changing climate is also discussed. Advances in sequencing and phenotyping methodologies make it possible to use vast genetic and genomic resources by deploying high resolution phenotyping coupled with high throughput multi-omics approaches for trait improvement. Integrated crop modelling studies focusing on farming systems design and management, prediction of climate impacts and disease forecasting may also help in planning adaptation. Hence, an integrated research framework combining genomics, plant molecular physiology, crop breeding, systems biology and integrated crop-soil-climate modelling will be very effective to cope with climate change.

Information Graphs Incorporating Predictive Values of Disease Forecasts.

Diagrammatic formats are useful for summarizing the processes of evaluation and comparison of forecasts in plant pathology and other disciplines where decisions about interventions for the purpose of disease management are often based on a proxy risk variable. We describe a new diagrammatic format for disease forecasts with two categories of actual status and two categories of forecast. The format displays relative entropies, functions of the predictive values that characterize expected information provided by disease forecasts. The new format arises from a consideration of earlier formats with underlying information properties that were previously unexploited. The new diagrammatic format requires no additional data for calculation beyond those used for the calculation of a receiver operating characteristic (ROC) curve. While an ROC curve characterizes a forecast in terms of sensitivity and specificity, the new format described here characterizes a forecast in terms of relative entropies based on predictive values. Thus it is complementary to ROC methodology in its application to the evaluation and comparison of forecasts.

Development of decision support system (DSS) for forecasting of gray mold disease of castor (Ricinus communis L.) using internet of things (IOTs)

Gray mold disease of castor caused by the fungus Botryotinia ricini is responsible for disease epidemics andheavy yield losses in castor growing regions of Telangana. An experiment was conducted in castor growing areas to understand the crop-weather-disease relations using wireless sensors, disease prediction models and Decision Support System (DSS). The DSS uses these weather data along with crop and management information to drive disease forecasting systems and a validated model of the disease to generate location specific management recommendations for fungicide application.

Intrapopulation Antagonism Can Reduce the Growth and Aggressiveness of the Wheat Head Blight Pathogen Fusarium graminearum.

Fusarium graminearum is a causal agent of Fusarium head blight (FHB), a disease that reduces yield and quality of cereal crops and contaminates grain with mycotoxins that pose health risks to humans and livestock. Interpopulation antagonistic interactions between isolates that produce different trichothecene mycotoxins can reduce FHB in wheat, but it is not known if interactions between isolates with a shared population identity that produce the same trichothecenes have a similar effect. Using isolates from the predominant F. graminearum populations in North America (NA1 and NA2), we examined intrapopulation interactions by comparing growth, disease progression, and toxin production of individual isolates with multi-isolate mixes. In vitro, mycelial growth was significantly greater when most NA1 and NA2 isolates were cultured individually versus when cultured as a mixture of isolates from the same population. In susceptible wheat Norm, FHB generally progressed faster in heads inoculated with an individual isolate versus a multi-isolate mixture, but the antagonistic effect of intrapopulation interactions was more pronounced for NA1 than NA2 isolates. By contrast, in moderately resistant wheat Alsen, mixtures of isolates from either population caused obvious reductions in FHB development. Mycotoxin contamination was not consistently affected by intrapopulation interactions and varied depending on the interacting isolates from either population. Our results indicate that antagonistic intrapopulation interactions can influence FHB in controlled environmental conditions. Understanding if the regional composition of pathogen populations similarly influences FHB in the field could improve disease forecasting and management practices.

On the automatic parameter selection for permutation entropy.

Permutation Entropy (PE) is a cost effective tool for summarizing the complexity of a time series. It has been used in many applications including damage detection, disease forecasting, detection of dynamical changes, and financial volatility analysis. However, to successfully use PE, an accurate selection of two parameters is needed: the permutation dimension n and embedding delay τ. These parameters are often suggested by experts based on a heuristic or by a trial and error approach. Both of these methods can be time-consuming and lead to inaccurate results. In this work, we investigate multiple schemes for automatically selecting these parameters with only the corresponding time series as the input. Specifically, we develop a frequency-domain approach based on the least median of squares and the Fourier spectrum, as well as extend two existing methods: Permutation Auto-Mutual Information Function and Multi-scale Permutation Entropy (MPE) for determining τ. We then compare our methods as well as current methods in the literature for obtaining both τ and n against expert-suggested values in published works. We show that the success of any method in automatically generating the correct PE parameters depends on the category of the studied system. Specifically, for the delay parameter τ, we show that our frequency approach provides accurate suggestions for periodic systems, nonlinear difference equations, and electrocardiogram/electroencephalogram data, while the mutual information function computed using adaptive partitions provides the most accurate results for chaotic differential equations. For the permutation dimension n, both False Nearest Neighbors and MPE provide accurate values for n for most of the systems with a value of n=5 being suitable in most cases.

Aerobiology, epidemiology and disease forecasting of false smut disease of rice in West Bengal, India

In India, since 2001, false smut disease of rice has been observed in severe form among major rice growing states. This disease is difficult to tackle, because pathogens infect the plant during flowering stage, and the symptoms are only visible after emergence of the panicle. Thus, disease forecasting is necessary to predict the chance of disease in a certain set of conditions. We analysed 3 years of aerobiological data including pathogenic spore (Ustilaginoidea virens) concentration over the rice canopy in West Bengal, India. The crop growth stages in both rabi (winter or dry) and kharif (rainy) seasons during which rapid development of false smut disease takes place were also recorded. Multiple regression analysis of per cent disease index values was done using age of the plant, pathogen concentration and meteorological factors. In dry season, the false smut disease severity depends on age of the plant as well as pathogenic spore concentration, while in rainy season, the severity depends upon spore concentration, RH and minT. From all the analysed data, it can be predicted that spore concentration is the common factor for false smut disease incidence and severity in rice. If pathogen concentration is increased by one unit, there will be 0.981 unit increased in the expected value of disease severity. With odds ratio value, it can be assumed that with a change in spore concentration by 1 unit, the odds of “Severe” versus “High” or “Moderate” or “Low” or “Absent” combined will be 1.1031 times greater, when other variables held constant. The regression model made from the present study would be beneficial to the farmers for early prediction of false smut disease of rice by estimating the spore concentration over rice canopy in West Bengal, India.

Application of Numerical Weather Prediction Data to Estimate Infection Risk of Bacterial Grain Rot of Rice in Korea.

This study was conducted to evaluate usefulness of numerical weather prediction data generated by the Unified Model (UM) for plant disease forecast. Using the UM06- and UM18-predicted weather data, which were released at 0600 and 1800 Universal Time Coordinated (UTC), respectively, by the Korea Meteorological Administration (KMA), disease forecast on bacterial grain rot (BGR) of rice was examined as compared with the model output based on the automated weather stations (AWS)-observed weather data. We analyzed performance of BGRcast based on the UM-predicted and the AWS-observed daily minimum temperature and average relative humidity in 2014 and 2015 from 29 locations representing major rice growing areas in Korea using regression analysis and two-way contingency table analysis. Temporal changes in weather conduciveness at two locations in 2014 were also analyzed with regard to daily weather conduciveness (Ci) and the 20-day and 7-day moving averages of Ci for the inoculum build-up phase (Cinc) prior to the panicle emergence of rice plants and the infection phase (Cinf) during the heading stage of rice plants, respectively. Based on Cinc and Cinf, we were able to obtain the same disease warnings at all locations regardless of the sources of weather data. In conclusion, the numerical weather prediction data from KMA could be reliable to apply as input data for plant disease forecast models. Weather prediction data would facilitate applications of weather-driven disease models for better disease management. Crop growers would have better options for disease control including both protective and curative measures when weather prediction data are used for disease warning.

Wireless sensor network in precision farming for forecasting and monitoring of apple disease: a survey

Apple is an important fruit of India from production and consumption point of view. India is the second largest country in terms of area under cultivation of apple crop (306 ha). Wireless sensor network (WSN) has been used for precision farming throughout the world. Many researchers deployed sensor network in apple farming to study their role in monitoring and automating the farming tasks like disease forecasting, etc. by using the real-time environmental information. After a thorough review of literature, it was found that role of sensor enabled systems for apple disease forecasting was not discussed in detail. This paper is one of its kind and presents comparative study of different studies to provide a deeper insight of such deployed systems. It includes the survey of different types of diseases found in apple crop, comparative study of different use cases of sensors in precision farming like environment monitoring, precision irrigation etc., survey of techniques for plant disease identification for use in forecasting systems. In this research article we also present a comprehensive study of apple disease forecasting systems developed so far and highlighted their key features and drawbacks. A comparison of the efficiency of these systems was evaluated by considering important parameters. Outcome of this survey would be used in selecting appropriate technologies for building optimized WSN based system for precision farming of apple that will help the framers to avoid the havocs caused by the disease outbreaks.

Assessing the utility of a smart thermometer and mobile application as a surveillance tool for influenza and influenza-like illness.

Kinsa Inc. sells Food and Drug Administration-cleared smart thermometers, which synchronize with a mobile application, and may aid influenza forecasting efforts. We compare smart thermometer and mobile application data to regional influenza and influenza-like illness surveillance data from the California Department of Public Health. We evaluated the correlation between the regional California surveillance data and smart thermometer data, tested the hypothesis that smart thermometer readings and symptom reports provide regionally specific predictions, and determined whether smart thermometer and mobile application improved disease forecasts. Smart thermometer readings are highly correlated with regional surveillance data, are more predictive of surveillance data for their own region and season than for other times and places, and improve predictions of influenza, but not predictions of influenza-like illness. These results are consistent with the hypothesis that smart thermometer readings and symptom reports reflect underlying disease transmission in California. Data from such cloud-based devices could supplement syndromic influenza surveillance data.

Spore concentrations of Blumeria graminis f. sp. tritici in relation to weather factors and disease development in Gansu, China

Wheat powdery mildew, caused by Blumeria graminis f. sp. tritici (Bgt), is an important disease in China. In this study, airborne spore concentrations were monitored using spore samplers and real-time PCR during 2013– 2015 at three locations in Gangu, Gansu province of China. The effects of meteorological variables on spore concentration were analyzed and models were developed for forecasting dynamics of airborne conidia and disease progress. The temperature, solar radiation and rainfall were positively correlated to spore concentrations and disease development. Although there was a negative correlation between relative humidity and spore concentration, relative humidity was positively related with disease development. Stepwise regression models were obtained for predicting the dynamics of airborne conidia based on the positive degree days and accumulation of rainfall (R2 = 0.31, P < 0.01), the positive degree days (R2 = 0.16, P = 0.04) and mean temperatures (R2 = 0.24, P = 0.01) at three locations, respectively. Disease forecasting models were developed based on various meteorological variables and spore concentration, the most important variables being temperature and spore concentration. This knowledge can improve the disease forecasting of wheat powdery mildew in Gangu and help develop better disease control strategies.

Heart disease prediction using stacked ensemble technique

Heart diseases are one of the crucial diseases that may cause fatality in both men and women. About 12 million deaths occur across the world due to heart diseases. With the advancement in information technology, it is possible for the Healthcare industry to store enormous volume of data containing millions of patient’s medical information along with their treatment details. If utilized in an efficient manner, this information helps the doctors to diagnose the diseases in a precise manner. Data mining algorithms are employed to analyse huge data sets and to discover unseen patterns. Data mining plays an essential role in medical diagnosis. Doctors bank on different computer models which uses data mining algorithms to prefigure different kinds of diseases in patients. So, the need is to design a methodical data mining algorithm that helps for better forecast of diseases. The main goal of this work is to create an ensemble of algorithms which results in better accuracy. The ensemble is constructed by making use of stacking ensemble technique, which comprises of two categorization algorithms namely Naïve Bayes and Artificial Neural Network. The Cleveland heart disease data set acquired from UCI machine learning repository containing 14 attributes and 303 instances is given as input to these algorithms. From our experimental analysis it is evident that the proposed ensemble scheme results in a better accuracy.

Collaboration is the key in creating national registries through emergency departments

Despite the need for a national trauma registry identified back in 2009, Pakistan still struggles to have a national trauma registry. Some of the challenges identified were the acquisition of a registry software, the commitment of all stakeholders for successful implementation, training of the workforce, planning of a data collection strategy, and validation of the data collected. Collaboration amongst emergency departments will remain key in tackling this herculean task. We propose to the stakeholders in each emergency department to study various registries implemented in the country as well as other low-income settings such as Kenya, India, etc., and start working on this highly neglected area of research. This data which can reflect the national trends and burden will also serve purposes other than research, like resource allocation, disease forecasting, budgeting, and public health decision making.

Palmar Dermatoglyphic: A forecast of hereditary diseases by the cumulative and comparative data in eastern Uttar Pradesh

Background: The study of ridges in the form of different designs as Loops, Whorls and Arches, various triangle, ridge counts as Total finger ridge count (TFRC) and Absolute finger ridge count (AFRC) etc. is called as Dermatoglyphics. Aims &amp; objectives: This study is mainly focused on checking the validity and reliability of Dermatoglyphics for the prediction of various diseases which are mostly inherited like Bronchial Asthma, Essential Hypertension and Diabetes Mellitus. In this study the finger tip pattern like Loops, Whorls and Arches with Finger ridge count (FRC), TFRC and AFRC is included. Material &amp; Method: The Study has been planned in Govt. Medical College, Azamgarh on 190 healthy individual, out of those 140 were male and 50 were female. The finger tip pattern of both hands was collected in the form of Loops, Whorls and Arches with FRC, TFRC and AFRC. The created data was compared with previous case-control study. Results: It is been observed that there is no solid proof of Dermatoglyphic reliability because of unavailability of standard parameters (quality &amp; quantity) of finger tip pattern, wide range of counts of patterns and Matching of present study results with both case and control of previous studies. Some studies was found important in which the count grading (from higher to lower) was changed from most normal results as Loops-Whorls-Arches to significant results as Whorls-Loops-Arches. The variability of results can also put a question on the inheritance of these diseases as it could be environment induced. Conclusion: Our study conclude that Dermatoglyphics should not be used as a tool for prediction of disease because of high variability in results until the cytogenetic study of these inherited diseases doesn’t show any specific parameter range of finger tip patterns in both aspects quality and quantity

Applying infectious disease forecasting to public health: a path forward using influenza forecasting examples

BackgroundInfectious disease forecasting aims to predict characteristics of both seasonal epidemics and future pandemics. Accurate and timely infectious disease forecasts could aid public health responses by informing key preparation and mitigation efforts.Main bodyFor forecasts to be fully integrated into public health decision-making, federal, state, and local officials must understand how forecasts were made, how to interpret forecasts, and how well the forecasts have performed in the past. Since the 2013–14 influenza season, the Influenza Division at the Centers for Disease Control and Prevention (CDC) has hosted collaborative challenges to forecast the timing, intensity, and short-term trajectory of influenza-like illness in the United States. Additional efforts to advance forecasting science have included influenza initiatives focused on state-level and hospitalization forecasts, as well as other infectious diseases. Using CDC influenza forecasting challenges as an example, this paper provides an overview of infectious disease forecasting; applications of forecasting to public health; and current work to develop best practices for forecast methodology, applications, and communication.ConclusionsThese efforts, along with other infectious disease forecasting initiatives, can foster the continued advancement of forecasting science.

Disease Prognosis by Machine Learning Over Big Data from Healthcare Communities

With huge information headway in biomedical and healthcare communities, appropriate examination of therapeutic information helps early sickness identification, tolerant consideration and network administrations. Prediction accuracy is diminished when the nature of medicinal information is inadequate. At that point the various areas appear, one of kind qualities of certain local infections, which may debilitate the expectation of illness episodes. In this paper, machine learning method is applied for viable forecast of interminable disease in the history of predicting diseases. The main intension is to have different prediction models over genuine medical clinic information gathered from focal China in 2013-2015. To conquer the trouble of deficient information, a latent factor model is used to regenerate the irrecoverable data. Here, experiment on a territorial chronic infection of cerebral localized necrosis is done. CNN-MDRP (convolutional neural system based multimodal infection chance prediction) algorithm is explained utilizing organized and unstructured information from medical clinic. Apparently, none of the current work establishes on the two information types in the zone of therapeutic enormous information investigation. Contrasted with numerous prediction algorithm, the precision accuracy of the proposed method arrives at 94.8% with a combination speed which is quicker than that of the CNN-UDRP(convolutional neural network based unimodal disease risk prediction) technique.

Rotavirus Seasonality: An Application of Singular Spectrum Analysis and Polyharmonic Modeling.

The dynamics of many viral infections, including rotaviral infections (RIs), are known to have a complex non-linear, non-stationary structure with strong seasonality indicative of virus and host sensitivity to environmental conditions. However, analytical tools suitable for the identification of seasonal peaks are limited. We introduced a two-step procedure to determine seasonal patterns in RI and examined the relationship between daily rates of rotaviral infection and ambient temperature in cold climates in three Russian cities: Chelyabinsk, Yekaterinburg, and Barnaul from 2005 to 2011. We described the structure of temporal variations using a new class of singular spectral analysis (SSA) models based on the “Caterpillar” algorithm. We then fitted Poisson polyharmonic regression (PPHR) models and examined the relationship between daily RI rates and ambient temperature. In SSA models, RI rates reached their seasonal peaks around 24 February, 5 March, and 12 March (i.e., the 55.17 ± 3.21, 64.17 ± 5.12, and 71.11 ± 7.48 day of the year) in Chelyabinsk, Yekaterinburg, and Barnaul, respectively. Yet, in all three cities, the minimum temperature was observed, on average, to be on 15 January, which translates to a lag between the peak in disease incidence and time of temperature minimum of 38–40 days for Chelyabinsk, 45–49 days in Yekaterinburg, and 56–59 days in Barnaul. The proposed approach takes advantage of an accurate description of the time series data offered by the SSA-model coupled with a straightforward interpretation of the PPHR model. By better tailoring analytical methodology to estimate seasonal features and understand the relationships between infection and environmental conditions, regional and global disease forecasting can be further improved.

English

Black pod disease (BPD) is reputed for its regular occurrence in Africa and around the world with high propensity for massive destruction of cocoa pods in the field and total yield loss per season if proper management strategies are not applied. This research was designed to provide useful and timely information on BPD outbreak, its intensity and specific areas expected to be massively affected by the disease in Nigeria. Twelve (12) research locations were mapped out from four important cocoa producing states in Southwest, Nigeria for BPD assessment and forecast. The BPD forecast system “ETAPOD” accurately predicted BPD outbreak in Ondo (a»Œwena and Waasimi) and Osun (Adaagba, Iyanfa»wa»ra»gi, and Owode-Igangan), but it failed to give accurate predictions for Ogun (Cabafemi-Owode) and Oyo (Moye village, Daagi-Logba and Oloro village) states. The performance of ETAPOD was greatly affected by the credibility of the data fed into the system, this can be improved on. ETAPOD predicted BPD outbreak closely within the range of natural BPD occurrences. Key words: Disease forecast, black pod disease (BPD) outbreak, total yield loss, ETAPOD, data credibility.

Real-Time PCR and LAMP Assays for the Detection of Spores of Alternaria solani and Sporangia of Phytophthora infestans to Inform Disease Risk Forecasting.

Real-time loop-mediated isothermal amplification (LAMP) assays for the detection of sporangia of the causal pathogen of late blight, Phytophthora infestans, and spores of the main causal pathogen of early blight, Alternaria solani, were developed to facilitate the in-field detection of airborne inoculum to improve disease forecasting. These assays were compared with an existing real-time PCR assay for P. infestans and a newly developed real-time PCR assay for A. solani. Primers were designed for real-time LAMP of P. infestans and A. solani. The specificity of the P. infestans real-time LAMP assay was similar to that of an existing real-time PCR assay: DNA of P. infestans was consistently amplified as was DNA of the taxonomically closely related species Phytophthora mirabilis, Phytophthora phaseoli, and Phytophthora ipomoea; no amplification of DNA from the potato pathogens Phytophthora erythroseptica or Phytophthora nicotianae occurred. Real-time LAMP and PCR assays were developed for A. solani, and the specificity was compared with an existing conventional PCR assay. Importantly, the A. solani real-time LAMP and PCR assays did not amplify the species Alternaria alternata. However, cross-reactivity with Alternaria dauci was observed with the real-time PCR assay and Alternaria brassicae with the real-time LAMP assay. The sensitivity of all assays for the detection of DNA extracted from sporangia/spores of the target pathogens was evaluated. The P. infestans real-time LAMP assay reliably detected 5 pg of DNA, equivalent to ∼1 sporangia per reaction. By comparison, 20 fg of DNA was detectable with the existing real-time PCR assay. In the case of A. solani, real-time LAMP detected 4.4 pg of DNA, equivalent to ∼1 spore per reaction, and real-time PCR detected 200 fg of DNA. In-field air samplers were deployed in two trial plots planted with potato: one infected with P. infestans, and the other infected with A. solani. Four additional samplers were located in commercial potato fields. Air samples were taken through the season, and detection of airborne inoculum of P. infestans and A. solani with both real-time PCR and LAMP was assessed.

An IoT-based cognitive monitoring system for early plant disease forecast

In this paper, we develop an IoT-based monitoring system for precision agriculture applications such as epidemic disease control. Such an agricultural monitoring system provides environmental monitoring services that maintain the crop growing environment in an optimal status and early predicts the conditions that lead to epidemic disease outbreak. The agricultural monitoring system provides a service to store the environmental and soil information collected from a wireless sensor network installed in the planted area in a database. Furthermore, it allows users to monitor the environmental information about the planted crops in real-time through any Internet-enabled devices. We develop artificial intelligence and prediction algorithms to realize an expert system that allows the system to emulate the decision-making ability of a human expert regarding the diseases and issue warning messages to the users before the outbreak of the disease. Field experiments showed that the proposed system reduces the number of chemical applications, and hence, promotes agriculture products with no (or minimal) chemicals residues and high-quality crops. This platform is designed to be generic enough to be used with multiple plant diseases where the software architecture can handle different plant disease models or other precision agriculture applications.