Prediction of Short-Distance Aerial Movement of Phakopsora pachyrhizi Urediniospores Using Machine Learning

It's a Trap! Part II: An Approachable Guide to Constructing and Using Rotating-Arm Air Samplers

An increasing number of researchers are looking to understand the factors affecting microbial dispersion but are often limited by the costs of commercially available air samplers. Some have reduced these costs by designing self-made versions; however, there are no published sampler designs, and there is limited information provided on the actual construction process. Lack of appropriate reference material limits the use of these self-made samplers by many researchers. This manuscript provides a guide to designing and constructing rotating-arm impaction air samplers by covering (i) environmental considerations, (ii) construction materials and equipment, (iii) the construction process, and (iv) air sampler deployment. Information regarding how to calculate rotational velocity, motor speed, and power supply requirements and to troubleshoot common issues is presented in an approachable format for individuals without experience in electronics or machining. Although many of the components discussed in this guide may change in their availability or be updated over time, this document is intended to serve as a "builder's guide" for future research into air sampling technology for phytopathology research.

Into the Trees: Random Forests for Predicting Fusarium Head Blight Epidemics of Wheat in the United States

Constructing models that accurately predict Fusarium head blight (FHB) epidemics and are also amenable to large-scale deployment is a challenging task. In the United States, the emphasis has been on simple logistic regression (LR) models, which are easy to implement but may suffer from lower accuracies when compared with more complicated, harder-to-deploy (over large geographies) model frameworks such as functional or boosted regressions. This article examined the plausibility of random forests (RFs) for the binary prediction of FHB epidemics as a possible mediation between model simplicity and complexity without sacrificing accuracy. A minimalist set of predictors was also desirable rather than having the RF model use all 90 candidate variables as predictors. The input predictor set was filtered with the aid of three RF variable selection algorithms (Boruta, varSelRF, and VSURF), using resampling techniques to quantify the variability and stability of selected variable sets. Post-selection filtering produced 58 competitive RF models with no more than 14 predictors each. One variable representing temperature stability in the 20 days before anthesis was the most frequently selected predictor. This was a departure from the prominence of relative humidity-based variables previously reported in LR models for FHB. The RF models had overall superior predictive performance over the LR models and may be suitable candidates for use by the Fusarium Head Blight Prediction Center.

Importance of Meteorological Parameters and Airborne Conidia to Predict Risk of Alternaria on a Potato Crop Ambient Using Machine Learning Algorithms

Secondary infections of early blight during potato crop season are conditioned by aerial inoculum. However, although aerobiological studies have focused on understanding the key factors that influence the spore concentration in the air, less work has been carried out to predict when critical concentrations of conidia occur. Therefore, the goals of this study were to understand the key weather variables that affect the hourly and daily conidia dispersal of Alternaria solani and A. alternata in a potato field, and to use these weather factors in different machine learning (ML) algorithms to predict the daily conidia levels. This study showed that conidia per hour in a day is influenced by the weather conditions that characterize the hour, but not the hour of the day. Specifically, the relative humidity and solar radiation were the most relevant weather parameters influencing the conidia concentration in the air and both in a linear model explained 98% of the variation of this concentration per hour. Moreover, the dew point temperature three days before was the weather variable with the strongest effect on conidia per day. An improved prediction of Alternaria conidia level was achieved via ML algorithms when the conidia of previous days is considered in the analysis. Among the ML algorithms applied, the CART model with an accuracy of 86% were the best to predict daily conidia level.

Modeling risk of Sclerotinia sclerotiorum-induced disease development on canola and dry bean using machine learning algorithms

Diseases caused by the fungus Sclerotinia sclerotiorum are managed mainly through fungicide applications in canola and dry bean. Accurate estimation of the risk of disease development on these crops could help farmers make spraying decisions. Five machine learning (ML) models were evaluated in classification and regression modes for predicting disease establishment under different air temperatures and leaf wetness duration conditions. Model algorithms were trained and tested using 20-fold cross validation. Correspondence between predicted and observed values were measured using Cohen’s Kappa (classification) and Lin’s concordance coefficients (regression). The artificial neural network (ANN) algorithms had average accuracies ≥ 89% (classification) and R² ≥ 88% (regression) on canola and dry bean and their correspondence agreements were ≥ 0.83, which is considered substantial to almost perfect. In contrast, logistic regression algorithms had accuracies of 88% for dry bean and 78% for canola; other models were similarly inconsistent. Implementation of ANN models in disease warning systems could help farmers with spraying decisions. At the same time, these models provide insights on temperature and leaf wetness requirements for development of S. sclerotiorum diseases in these crops. Results of this study show the potential of ML models as tools for epidemiological studies on other pathosystems.

Spatio-Temporal Modeling and Simulation of Asian Soybean Rust Based on Fuzzy System

Mato Grosso, Brazil, is the largest soy producer in the country. Asian Soy Rust is a disease that has already caused a lot of damage to Brazilian agribusiness. The plant matures prematurely, hindering the filling of the pod, drastically reducing productivity. It is caused by the Phakopsora pachyrhizi fungus. For a plant disease to establish itself, the presence of a pathogen, a susceptible plant, and favorable environmental conditions are necessary. This research developed a fuzzy system gathering these three variables as inputs, having as an output the vulnerability of the region to the disease. The presence of the pathogen was measured using a diffusion-advection equation appropriate to the problem. Some coefficients were based on the literature, others were measured by a fuzzy system and others were obtained by real data. From the mapping of producing properties, the locations where there are susceptible plants were established. And the favorable environmental conditions were also obtained from a fuzzy system, whose inputs were temperature and leaf wetness. Data provided by IBGE, INMET, and Antirust Consortium were used to fuel the model, and all treatments, tests, and simulations were carried out within the Matlab® environment. Although Asian Soybean Rust was the chosen disease here, the model was general in nature, so could be reproduced for any disease of plants with the same profile.

Logistic Models Derived via LASSO Methods for Quantifying the Risk of Natural Contamination of Maize Grain with Deoxynivalenol

Models were developed to quantify the risk of deoxynivalenol (DON) contamination of maize grain based on weather, cultural practices, hybrid resistance, and Gibberella ear rot (GER) intensity. Data on natural DON contamination of 15 to 16 hybrids and weather were collected from 10 Ohio locations over 4 years. Logistic regression with 10-fold cross-validation was used to develop models to predict the risk of DON ≥1 ppm. The presence and severity of GER predicted DON risk with an accuracy of 0.81 and 0.87, respectively. Temperature, relative humidity, surface wetness, and rainfall were used to generate 37 weather-based predictor variables summarized over each of six 15-day windows relative to maize silking (R1). With these variables, least absolute shrinkage and selection operator (LASSO) followed by all-subsets variable selection and logistic regression with 10-fold cross-validation were used to build single-window weather-based models, from which 11 with one or two predictors were selected based on performance metrics and simplicity. LASSO logistic regression was also used to build more complex multiwindow models with up to 22 predictors. The performance of the best single-window models was comparable to that of the best multiwindow models, with accuracy ranging from 0.81 to 0.83 for the former and 0.83 to 0.87 for the latter group of models. These results indicated that the risk of DON ≥1 ppm can be accurately predicted with simple models built using temperature- and moisture-based predictors from a single window. These models will be the foundation for developing tools to predict the risk of DON contamination of maize grain.

Impact of the United States Department of Agriculture, Agricultural Research Service on Plant Pathology: 2015-2020

There is an increasing need to supply the world with more food as the population continues to grow. Research on mitigating the effects of plant diseases to improve crop yield and quality can help provide more food without increasing the land area devoted to farming. National Program 303 (NP 303) within the U.S. Department of Agriculture, Agricultural Research Service is dedicated to research across multiple fields in plant pathology. This review article highlights the research impact within NP 303 between 2015 and 2020, including case studies on wheat and citrus diseases and the National Plant Disease Recovery System, which provide specific examples of this impact.

Spatio-Temporal Prediction of the Epidemic Spread of Dangerous Pathogens Using Machine Learning Methods

Real-time identification of the occurrence of dangerous pathogens is of crucial importance for the rapid execution of countermeasures. For this purpose, spatial and temporal predictions of the spread of such pathogens are indispensable. The R package papros developed by the authors offers an environment in which both spatial and temporal predictions can be made, based on local data using various deterministic, geostatistical regionalisation, and machine learning methods. The approach is presented using the example of a crops infection by fungal pathogens, which can substantially reduce the yield if not treated in good time. The situation is made more difficult by the fact that it is particularly difficult to predict the behaviour of wind-dispersed pathogens, such as powdery mildew (Blumeria graminis f. sp. tritici). To forecast pathogen development and spatial dispersal, a modelling process scheme was developed using the aforementioned R package, which combines regionalisation and machine learning techniques. It enables the prediction of the probability of yield- relevant infestation events for an entire federal state in northern Germany at a daily time scale. To run the models, weather and climate information are required, as is knowledge of the pathogen biology. Once fitted to the pathogen, only weather and climate information are necessary to predict such events, with an overall accuracy of 68% in the case of powdery mildew at a regional scale. Thereby, 91% of the observed powdery mildew events are predicted.

Epidemiology: Past, Present, and Future Impacts on Understanding Disease Dynamics and Improving Plant Disease Management-A Summary of Focus Issue Articles

Epidemiology has made significant contributions to plant pathology by elucidating the general principles underlying the development of disease epidemics. This has resulted in a greatly improved theoretical and empirical understanding of the dynamics of disease epidemics in time and space, predictions of disease outbreaks or the need for disease control in real-time basis, and tactical and strategic solutions to disease problems. Availability of high-resolution experimental data at multiple temporal and spatial scales has now provided a platform to test and validate theories on the spread of diseases at a wide range of spatial scales ranging from the local to the landscape level. Relatively new approaches in plant disease epidemiology, ranging from network to information theory, coupled with the availability of large-scale datasets and the rapid development of computer technology, are leading to revolutionary thinking about epidemics that can result in considerable improvement of strategic and tactical decision making in the control and management of plant diseases. Methods that were previously restricted to topics such as population biology or evolution are now being employed in epidemiology to enable a better understanding of the forces that drive the development of plant disease epidemics in space and time. This Focus Issue of Phytopathology features research articles that address broad themes in epidemiology including social and political consequences of disease epidemics, decision theory and support, pathogen dispersal and disease spread, disease assessment and pathogen biology and disease resistance. It is important to emphasize that these articles are just a sample of the types of research projects that are relevant to epidemiology. Below, we provide a succinct summary of the articles that are published in this Focus Issue .