Predicting Pre-planting Risk of Stagonospora nodorum blotch in Winter Wheat Using Machine Learning Models

A Comparative Analysis of XGBoost and Neural Network Models for Predicting Some Tomato Fruit Quality Traits from Environmental and Meteorological Data

The tomato as a raw material for processing is globally important and is pivotal in dietary and agronomic research due to its nutritional, economic, and health significance. This study explored the potential of machine learning (ML) for predicting tomato quality, utilizing data from 48 cultivars and 28 locations in Hungary over 5 seasons. It focused on °Brix, lycopene content, and colour (a/b ratio) using extreme gradient boosting (XGBoost) and artificial neural network (ANN) models. The results revealed that XGBoost consistently outperformed ANN, achieving high accuracy in predicting °Brix (R² = 0.98, RMSE = 0.07) and lycopene content (R² = 0.87, RMSE = 0.61), and excelling in colour prediction (a/b ratio) with a R² of 0.93 and RMSE of 0.03. ANN lagged behind particularly in colour prediction, showing a negative R² value of -0.35. Shapley additive explanation's (SHAP) summary plot analysis indicated that both models are effective in predicting °Brix and lycopene content in tomatoes, highlighting different aspects of the data. SHAP analysis highlighted the models' efficiency (especially in °Brix and lycopene predictions) and underscored the significant influence of cultivar choice and environmental factors like climate and soil. These findings emphasize the importance of selecting and fine-tuning the appropriate ML model for enhancing precision agriculture, underlining XGBoost's superiority in handling complex agronomic data for quality assessment.

Identification of Quinone Outside Inhibitor Fungicide-Resistant Isolates of Parastagonospora nodorum from Illinois and Kentucky

Stagonospora leaf and glume blotch, caused by Parastagonospora nodorum, is a major disease of winter wheat (Triticum aestivum) in the United States capable of significantly reducing grain yield and quality. Pathogens such as P. nodorum that overwinter in crop residue are often an increased concern in cropping systems that utilize no-till farming. In addition, the lack of wheat cultivars with complete resistance to P. nodorum has led to the reliance on foliar fungicides for disease management. Quinone outside inhibitor (QoI) fungicides (Fungicide Resistance Action Committee group 11) are one of the major classes used to manage foliar diseases in wheat. Use of the QoI class of fungicides tends to select isolates of fungal pathogens with resistance due to mutations in the fungal cytochrome b gene. Isolates of P. nodorum were collected from Illinois in 2014 and Kentucky in 2018, 2019, and 2020. Amplification and sequencing of a segment of the cytochrome b gene from these isolates revealed a mutation at codon 143 that confers a change from glycine to alanine in the amino acid sequence (known as the G143A mutation). In vitro plate assays and greenhouse trials were used to confirm and characterize the QoI resistance caused by the G143A mutation. The frequency of the tested isolates with the G143A mutation was 46% (57 of 123 isolates) and 5% (3 of 60 isolates) for Kentucky and Illinois, respectively. This research is the first to identify the G143A mutation in P. nodorum isolates with resistance to QoI fungicides in Illinois and Kentucky.

Effect of Previous Crops and Soil Physicochemical Properties on the Population of Verticillium dahliae in the Iberian Peninsula

The soil infestation of Verticillium dahliae has significant Verticillium wilt of olive (VWO) with epidemiological consequences which could limit the expansion of the crop. In this context, there is a misunderstood history of the crops and soil property interactions associated with inoculum density (ID) increases in the soil. In this study, the effect of the combination of both factors was assessed on the ID of V. dahliae in the olive-growing areas of the Iberian Peninsula. Afterwards, the relationship of the ID to the mentioned factors was explored. The detection percentage and ID were higher in Spain than Portugal, even though the fields with a very favourable VWO history had a higher ID than that of the fields with a barely favourable history, regardless of the origin. The soil physicochemical parameters were able to detect the degree to which the ID was increased by the previous cropping history. By using a decision tree classifier, the percentage of clay was the best indicator for the V. dahliae ID regardless of the history of the crops. However, active limestone and the cation exchange capacity were only suitable ID indicators when <2 or 4 host crops of the pathogen were established in the field for five years, respectively. The V. dahliae ID was accurately predicted in this study for the orchard choices in the establishment of the olive.

The Self-Supervised Spectral–Spatial Vision Transformer Network for Accurate Prediction of Wheat Nitrogen Status from UAV Imagery

Nitrogen (N) fertilizer is routinely applied by farmers to increase crop yields. At present, farmers often over-apply N fertilizer in some locations or at certain times because they do not have high-resolution crop N status data. N-use efficiency can be low, with the remaining N lost to the environment, resulting in higher production costs and environmental pollution. Accurate and timely estimation of N status in crops is crucial to improving cropping systems’ economic and environmental sustainability. Destructive approaches based on plant tissue analysis are time consuming and impractical over large fields. Recent advances in remote sensing and deep learning have shown promise in addressing the aforementioned challenges in a non-destructive way. In this work, we propose a novel deep learning framework: a self-supervised spectral–spatial attention-based vision transformer (SSVT). The proposed SSVT introduces a Spectral Attention Block (SAB) and a Spatial Interaction Block (SIB), which allows for simultaneous learning of both spatial and spectral features from UAV digital aerial imagery, for accurate N status prediction in wheat fields. Moreover, the proposed framework introduces local-to-global self-supervised learning to help train the model from unlabelled data. The proposed SSVT has been compared with five state-of-the-art models including: ResNet, RegNet, EfficientNet, EfficientNetV2, and the original vision transformer on both testing and independent datasets. The proposed approach achieved high accuracy (0.96) with good generalizability and reproducibility for wheat N status estimation.

The Application of Hyperspectral Remote Sensing Imagery (HRSI) for Weed Detection Analysis in Rice Fields: A Review

Weeds are found on every cropland across the world. Weeds compete for light, water, and nutrients with attractive plants, introduce illnesses or viruses, and attract harmful insects and pests, resulting in yield loss. New weed detection technologies have been developed in recent years to increase weed detection speed and accuracy, resolving the contradiction between the goals of enhancing soil health and achieving sufficient weed control for profitable farming. In recent years, a variety of platforms, such as satellites, airplanes, unmanned aerial vehicles (UAVs), and close-range platforms, have become more commonly available for gathering hyperspectral images with varying spatial, temporal, and spectral resolutions. Plants must be divided into crops and weeds based on their species for successful weed detection. Therefore, hyperspectral image categorization also has become popular since the development of hyperspectral image technology. Unmanned aerial vehicle (UAV) hyperspectral imaging techniques have recently emerged as a valuable tool in agricultural remote sensing, with tremendous promise for weed detection and species separation. Hence, this paper will review the weeds problem in rice fields in Malaysia and focus on the application of hyperspectral remote sensing imagery (HRSI) for weed detection with algorithms and modelling employed for weeds discrimination analysis.

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.

Biology and molecular interactions of Parastagonospora nodorum blotch of wheat

Parastagonospora nodorum is one of the important necrotrophic pathogens of wheat which causes severe economical loss to crop yield. So far, a number of effectors of Parastagonospora nodorum origin and their target interacting genes on the host plant have been characterized. Since targeting effector-sensitive gene carefully can be helpful in breeding for resistance. Therefore, constant efforts are required to further characterize the effectors, their interacting genes, and underlying biochemical pathways. Furthermore, to develop effective counter-strategies against emerging diseases, continuous efforts are required to determine the qualitative resistance that demands to screen of diverse genotypes for host resistance. Stagonospora nodorum blotch also refers to as Stagonospora glume blotch and leaf is caused by Parastagonospora nodorum. The pathogen deploys necrotrophic effectors for the establishment and development on wheat plants. The necrotrophic effectors and their interaction with host receptors lead to the establishment of infection on leaves and extensive lesions formation which either results in host cell death or suppression/activation of host defence mechanisms. The wheat Stagonospora nodorum interaction involves a set of nine host gene-necrotrophic effector interactions. Out of these, Snn1-SnTox1, Tsn1-SnToxA and Snn-SnTox3 are one of the most studied interaction, due to its role in the suppression of reactive oxygen species production, regulating the cytokinin content through ethylene-dependent wayduring initial infection stage. Further, although the molecular basis is not fully unveiled, these effectors regulate the redox state and influence the ethylene biosynthesis in infected wheat plants. Here, we have discussed the biology of the wheat pathogen Parastagonospora nodorum, role of its necrotrophic effectors and their interacting sensitivity genes on the redox state, how they hijack the resistance mechanisms, hormonal regulated immunity and other signalling pathways in susceptible wheat plants. The information generated from effectors and their corresponding sensitivity genes and other biological processes could be utilized effectively for disease management strategies.

Next-Generation Breeding Strategies for Climate-Ready Crops

Climate change is a threat to global food security due to the reduction of crop productivity around the globe. Food security is a matter of concern for stakeholders and policymakers as the global population is predicted to bypass 10 billion in the coming years. Crop improvement via modern breeding techniques along with efficient agronomic practices innovations in microbiome applications, and exploiting the natural variations in underutilized crops is an excellent way forward to fulfill future food requirements. In this review, we describe the next-generation breeding tools that can be used to increase crop production by developing climate-resilient superior genotypes to cope with the future challenges of global food security. Recent innovations in genomic-assisted breeding (GAB) strategies allow the construction of highly annotated crop pan-genomes to give a snapshot of the full landscape of genetic diversity (GD) and recapture the lost gene repertoire of a species. Pan-genomes provide new platforms to exploit these unique genes or genetic variation for optimizing breeding programs. The advent of next-generation clustered regularly interspaced short palindromic repeat/CRISPR-associated (CRISPR/Cas) systems, such as prime editing, base editing, and de nova domestication, has institutionalized the idea that genome editing is revamped for crop improvement. Also, the availability of versatile Cas orthologs, including Cas9, Cas12, Cas13, and Cas14, improved the editing efficiency. Now, the CRISPR/Cas systems have numerous applications in crop research and successfully edit the major crop to develop resistance against abiotic and biotic stress. By adopting high-throughput phenotyping approaches and big data analytics tools like artificial intelligence (AI) and machine learning (ML), agriculture is heading toward automation or digitalization. The integration of speed breeding with genomic and phenomic tools can allow rapid gene identifications and ultimately accelerate crop improvement programs. In addition, the integration of next-generation multidisciplinary breeding platforms can open exciting avenues to develop climate-ready crops toward global food security.

Machine learning in plant-pathogen interactions: empowering biological predictions from field scale to genome scale

Machine learning (ML) encompasses statistical methods that learn to identify patterns in complex datasets. Here, I review application areas in plant-pathogen interactions that have recently benefited from ML, such as disease monitoring, the discovery of gene regulatory networks, genomic selection for disease resistance and prediction of pathogen effectors. However, achieving robust performance from ML is not trivial and requires knowledge of both the methodology and the biology. I discuss common pitfalls and challenges in using ML approaches. Finally, I highlight future opportunities for ML as a tool for dissecting plant-pathogen interactions using high-throughput data, for example, through integration of diverse data sources and the analysis with higher resolution, such as from individual cells or on elaborate spatial and temporal scales.

Period of Measurement in Time-Series Predictions of Disease Counts from 2007 to 2017 in Northern Nevada: Analytics Experiment

BACKGROUND

The literature in statistics presents methods by which autocorrelation can identify the best period of measurement to improve the performance of a time-series prediction. The period of measurement plays an important role in improving the performance of disease-count predictions. However, from the operational perspective in public health surveillance, there is a limitation to the length of the measurement period that can offer meaningful and valuable predictions.

OBJECTIVE

This study aimed to establish a method that identifies the shortest period of measurement without significantly decreasing the prediction performance for time-series analysis of disease counts.

METHODS

The data used in this evaluation include disease counts from 2007 to 2017 in northern Nevada. The disease counts for chlamydia, salmonella, respiratory syncytial virus, gonorrhea, viral meningitis, and influenza A were predicted.

RESULTS

Our results showed that autocorrelation could not guarantee the best performance for prediction of disease counts. However, the proposed method with the change-point analysis suggests a period of measurement that is operationally acceptable and performance that is not significantly different from the best prediction.

CONCLUSIONS

The use of change-point analysis with autocorrelation provides the best and most practical period of measurement.

Systems Biology and Machine Learning in Plant-Pathogen Interactions

Systems biology is an inclusive approach to study the static and dynamic emergent properties on a global scale by integrating multiomics datasets to establish qualitative and quantitative associations among multiple biological components. With an abundance of improved high throughput -omics datasets, network-based analyses and machine learning technologies are playing a pivotal role in comprehensive understanding of biological systems. Network topological features reveal most important nodes within a network as well as prioritize significant molecular components for diverse biological networks, including coexpression, protein-protein interaction, and gene regulatory networks. Machine learning techniques provide enormous predictive power through specific feature extraction from biological data. Deep learning, a subtype of machine learning, has plausible future applications because a domain expert for feature extraction is not needed in this algorithm. Inspired by diverse domains of biology, we here review classic systems biology techniques applied in plant immunity thus far. We also discuss additional advanced approaches in both graph theory and machine learning, which may provide new insights for understanding plant-microbe interactions. Finally, we propose a hybrid approach in plant immune systems that harnesses the power of both network biology and machine learning, with a potential to be applicable to both model systems and agronomically important crop plants.

A Novel Machine Learning Algorithm to Automatically Predict Visual Outcomes in Intravitreal Ranibizumab-Treated Patients with Diabetic Macular Edema

Purpose: Artificial neural networks (ANNs) are one type of artificial intelligence. Here, we use an ANN-based machine learning algorithm to automatically predict visual outcomes after ranibizumab treatment in diabetic macular edema. Methods: Patient data were used to optimize ANNs for regression calculation. The target was established as the final visual acuity at 52, 78, or 104 weeks. The input baseline variables were sex, age, diabetes type or condition, systemic diseases, eye status and treatment time tables. Three groups were randomly devised to build, test and demonstrate the accuracy of the algorithms. Results: At 52, 78 and 104 weeks, 512, 483 and 464 eyes were included, respectively. For the training group, testing group and validation group, the respective correlation coefficients were 0.75, 0.77 and 0.70 (52 weeks); 0.79, 0.80 and 0.55 (78 weeks); and 0.83, 0.47 and 0.81 (104 weeks), while the mean standard errors of final visual acuity were 6.50, 6.11 and 6.40 (52 weeks); 5.91, 5.83 and 7.59; (78 weeks); and 5.39, 8.70 and 6.81 (104 weeks). Conclusions: Machine learning had good correlation coefficients for predicating prognosis with ranibizumab with just baseline characteristics. These models could be the useful clinical tools for prediction of success of the treatments.

Understanding Yield Loss and Pathogen Biology to Improve Disease Management: Septoria Nodorum Blotch - A Case Study in Wheat

The estimated potential yield losses caused by plant pathogens is up to 16% globally and most research in plant pathology aims to reduce yield loss in our crops directly or indirectly. Yield losses caused by a certain disease depend not only on disease severity, but also on the weather factors, the pathogen's aggressiveness, and the ability of the crop to compensate for reduced photosynthetic area. The yield loss-disease relationship in a certain host-pathogen system might therefore change from year to year, making predictions for yield loss very difficult at the regional or even at the farmer's level. However, estimating yield losses is essential to determine disease management thresholds at which acute control measures such as fungicide applications, or strategic measures such as crop rotation or use of resistant cultivars are economically and environmentally sensible. Legislation in many countries enforces implementation of integrated pest management (IPM), based on economic thresholds at which the costs due to a disease justify the costs for its management. Without a better understanding of the relationship between disease epidemiology and yield loss, we remain insufficiently equipped to design adequate IPM strategies that will be widely adapted in agriculture. Crop loss studies are resource demanding and difficult to interpret for one particular disease, as crops are usually not invaded by only one pest or pathogen at a time. Combining our knowledge on disease epidemiology, crop physiology, yield development, damage mechanisms involved, and the effect of management practices can help us to increase our understanding of the disease-crop loss relationship. The main aim of this paper is to review and analyze the literature on a representative host-pathogen relationship in an important staple food crop to identify knowledge gaps and research areas to better assess yield loss and design management strategies based on economic thresholds.

Predicting Ascospore Release of Monilinia vaccinii-corymbosi of Blueberry with Machine Learning

Mummy berry, caused by Monilinia vaccinii-corymbosi, causes economic losses of highbush blueberry in the U.S. Pacific Northwest (PNW). Apothecia develop from mummified berries overwintering on soil surfaces and produce ascospores that infect tissue emerging from floral and vegetative buds. Disease control currently relies on fungicides applied on a calendar basis rather than inoculum availability. To establish a prediction model for ascospore release, apothecial development was tracked in three fields, one in western Oregon and two in northwestern Washington in 2015 and 2016. Air and soil temperature, precipitation, soil moisture, leaf wetness, relative humidity and solar radiation were monitored using in-field weather stations and Washington State University's AgWeatherNet stations. Four modeling approaches were compared: logistic regression, multivariate adaptive regression splines, artificial neural networks, and random forest. A supervised learning approach was used to train the models on two data sets: training (70%) and testing (30%). The importance of environmental factors was calculated for each model separately. Soil temperature, soil moisture, and solar radiation were identified as the most important factors influencing ascospore release. Random forest models, with 78% accuracy, showed the best performance compared with the other models. Results of this research helps PNW blueberry growers to optimize fungicide use and reduce production costs.

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

Dispersal of urediniospores by wind is the primary means of spread for Phakopsora pachyrhizi, the cause of soybean rust. Our research focused on the short-distance movement of urediniospores from within the soybean canopy and up to 61 m from field-grown rust-infected soybean plants. Environmental variables were used to develop and compare models including the least absolute shrinkage and selection operator regression, zero-inflated Poisson/regular Poisson regression, random forest, and neural network to describe deposition of urediniospores collected in passive and active traps. All four models identified distance of trap from source, humidity, temperature, wind direction, and wind speed as the five most important variables influencing short-distance movement of urediniospores. The random forest model provided the best predictions, explaining 76.1 and 86.8% of the total variation in the passive- and active-trap datasets, respectively. The prediction accuracy based on the correlation coefficient (r) between predicted values and the true values were 0.83 (P < 0.0001) and 0.94 (P < 0.0001) for the passive and active trap datasets, respectively. Overall, multiple machine learning techniques identified the most important variables to make the most accurate predictions of movement of P. pachyrhizi urediniospores short-distance.

A Model for Predicting Onset of Stagonospora nodorum Blotch in Winter Wheat Based on Preplanting and Weather Factors

Stagonospora nodorum blotch (SNB) caused by Parastagonospora nodorum is a serious disease of wheat worldwide. In the United States, the disease is prevalent on winter wheat in many eastern states, and its management relies mainly on fungicide application after flag leaf emergence. Although SNB can occur prior to flag leaf emergence, the relationship between the time of disease onset and yield has not been determined. Such a relationship is useful in identifying a threshold to facilitate prediction of disease onset in the field. Disease occurred in 390 of 435 disease cases that were recorded across 11 counties in North Carolina from 2012 to 2014. Using cases with disease occurrence, the effect of disease onset on yield was analyzed to identify a disease onset threshold that related time of disease onset to yield. Regression analysis showed that disease onset explained 32% of the variation in yield (P < 0.0001) and from this relationship, day of year (DOY) 102 was identified as the disease onset threshold. Below-average yield occurred in 87% of the disease cases when disease onset occurred before DOY 102 but in only 28% of those cases when onset occurred on or after DOY 102. Subsequently, binary logistic regression models were developed to predict the occurrence and onset of SNB using preplanting factors and cumulative daily infection values (cDIV) starting 1 to 3 weeks prior to DOY 102. Logistic regression showed that previous crop, latitude, and cDIV accumulated 2 weeks prior to DOY 102 (cDIV.2) were significant (P < 0.0001) predictors of disease occurrence, and wheat residue, latitude, longitude, and cDIV.2 were significant (P < 0.0001) predictors of disease onset. The disease onset model had a correct classification rate of 0.94 and specificity and sensitivity rates >0.90. Performance of the disease onset model based on the area under the receiver operating characteristic curve (AUC), κ, and the true skill statistic (TSS) was excellent, with prediction accuracy values >0.88. Similarly, internal validation of the disease onset model based on AUC, κ, and TSS indicated good performance, with accuracy values >0.88. This disease onset prediction model could serve as a useful decision support tool to guide fungicide applications to manage SNB in wheat.