An early warning system to predict and mitigate wheat rust diseases in Ethiopia

Ethiopian Crop Type 2020 (EthCT2020) dataset: Crop type data for environmental and agricultural remote sensing applications in complex Ethiopian smallholder wheat-based farming systems (Meher season 2020/21)

Crop type observation is crucial for various environmental and agricultural remote sensing applications including land use and land cover mapping, crop growth monitoring, crop modelling, yield forecasting, disease surveillance, and climate modelling. Quality-controlled georeferenced crop type information is essential for calibrating and validating machine learning algorithms. However, publicly available field data is scarce, particularly in the highly dynamic smallholder farming systems of sub-Saharan Africa. For the 2020/21 main cropping season (Meher), the Ethiopian Crop Type 2020 (EthCT2020) dataset compiled from multiple sources provides 2,793 harmonized, quality-controlled, and georeferenced in-situ samples on annual crop types (7 crop groups; 22 crop classes) at smallholder field level across the complex and highly fragmented agricultural landscape of Ethiopia. The focus was on rainfed, wheat-based farming systems. A nationwide ground data collection campaign (GDCC; Source 1) was designed using a stratification approach based on wheat crop calendar information, and 1,263 in-situ data samples were collected in selected sampling regions. This in-situ data pool was enriched with 1,530 wheat samples extracted from a) the Wheat Rust Toolbox (WRTB; Source 2; 734 samples), a database for wheat disease surveillance data [1] and b) an inhouse farm household survey database (FHSD; Source 3; 796 samples). Obtained field data was labelled according to the Joint Experiment for Crop Assessment and Monitoring (JECAM) guidelines for cropland and crop type definition and field data collection [2] and the FAO Indicative Crop Classification [3]. The EthCT2020 dataset underwent extensive processing including data harmonization, mixed pixel assessment through visual interpretation using 5 m Planet satellite image composites, and quality-control using Sentinel-2 NDVI homogeneity analysis. The EthCT2020 dataset is unique in terms of crop diversity, pixel purity, and spatial accuracy while targeting a countrywide distribution. It is representative of Ethiopia's complex and highly fragmented agricultural landscape and can be useful for developing new machine learning algorithms for land use land cover mapping, crop type mapping, agricultural monitoring, and yield forecasting in smallholder cropping systems. The dataset can also serve as a baseline input parameter for crop models, climate models, and crop disease and pest forecasting systems.

Towards development of functional climate-driven early warning systems for climate-sensitive infectious diseases: Statistical models and recommendations

Climate, weather and environmental change have significantly influenced patterns of infectious disease transmission, necessitating the development of early warning systems to anticipate potential impacts and respond in a timely and effective way. Statistical modelling plays a pivotal role in understanding the intricate relationships between climatic factors and infectious disease transmission. For example, time series regression modelling and spatial cluster analysis have been employed to identify risk factors and predict spatial and temporal patterns of infectious diseases. Recently advanced spatio-temporal models and machine learning offer an increasingly robust framework for modelling uncertainty, which is essential in climate-driven disease surveillance due to the dynamic and multifaceted nature of the data. Moreover, Artificial Intelligence (AI) techniques, including deep learning and neural networks, excel in capturing intricate patterns and hidden relationships within climate and environmental data sets. Web-based data has emerged as a powerful complement to other datasets encompassing climate variables and disease occurrences. However, given the complexity and non-linearity of climate-disease interactions, advanced techniques are required to integrate and analyse these diverse data to obtain more accurate predictions of impending outbreaks, epidemics or pandemics. This article presents an overview of an approach to creating climate-driven early warning systems with a focus on statistical model suitability and selection, along with recommendations for utilizing spatio-temporal and machine learning techniques. By addressing the limitations and embracing the recommendations for future research, we could enhance preparedness and response strategies, ultimately contributing to the safeguarding of public health in the face of evolving climate challenges.

Wheat leaf diseases classification and severity analysis using HT-CNN and Hex-D-VCC-based boundary tracing mechanism

Wheat is one among the significant crops for humans. Significant fungal illnesses of wheat are brought on by multiple pathogens. Wheat output could be enhanced by the early identification of wheat leaf disease. Thus, a novel hyperparameter tanh-based convolutional neural network (HT-CNN)-based wheat leaf disease prediction is proposed with its severity level. Here, initially, the red, green, and blue (RGB) images are converted into a hue saturation value (HSV) image. Next, the small probability space filtering is applied to the V component. Afterward, the contrast of the V component has been enhanced. The obtained HSV image is converted into the RGB image. Then, by employing weighted Canberra distance-based K-means (WCD-K means), the affected and normal regions are segmented. Next, the image is binarized. Afterward, for tracing a boundary around disease-affected region, the hex directional vertex chain code (Hex-D-VCC) is applied over the binarized image, and then the features are extracted. By employing baker's map-based Harris hawks optimization (BM-HHO), the optimal features are selected. For classifying disease, the selected features are further given into the HT-CNN, and the severity level is calculated to minimize the yield loss. As per the experimental result, the proposed model shows higher accuracy and efficacy when analogized to the other methods.

The potential of UAV and very high-resolution satellite imagery for yellow and stem rust detection and phenotyping in Ethiopia

Very high (spatial and temporal) resolution satellite (VHRS) and high-resolution unmanned aerial vehicle (UAV) imagery provides the opportunity to develop new crop disease detection methods at early growth stages with utility for early warning systems. The capability of multispectral UAV, SkySat and Pleiades imagery as a high throughput phenotyping (HTP) and rapid disease detection tool for wheat rusts is assessed. In a randomized trial with and without fungicide control, six bread wheat varieties with differing rust resistance were monitored using UAV and VHRS. In total, 18 spectral features served as predictors for stem and yellow rust disease progression and associated yield loss. Several spectral features demonstrated strong predictive power for the detection of combined wheat rust diseases and the estimation of varieties' response to disease stress and grain yield. Visible spectral (VIS) bands (Green, Red) were more useful at booting, shifting to VIS-NIR (near-infrared) vegetation indices (e.g., NDVI, RVI) at heading. The top-performing spectral features for disease progression and grain yield were the Red band and UAV-derived RVI and NDVI. Our findings provide valuable insight into the upscaling capability of multispectral sensors for disease detection, demonstrating the possibility of upscaling disease detection from plot to regional scales at early growth stages.

Developing a predictive model for an emerging epidemic on cassava in sub-Saharan Africa

The agricultural productivity of smallholder farmers in sub-Saharan Africa (SSA) is severely constrained by pests and pathogens, impacting economic stability and food security. An epidemic of cassava brown streak disease, causing significant yield loss, is spreading rapidly from Uganda into surrounding countries. Based on sparse surveillance data, the epidemic front is reported to be as far west as central DRC, the world's highest per capita consumer, and as far south as Zambia. Future spread threatens production in West Africa including Nigeria, the world's largest producer of cassava. Using innovative methods we develop, parameterise and validate a landscape-scale, stochastic epidemic model capturing the spread of the disease throughout Uganda. The model incorporates real-world management interventions and can be readily extended to make predictions for all 32 major cassava producing countries of SSA, with relevant data, and lays the foundations for a tool capable of informing policy decisions at a national and regional scale.

Modeling plant diseases under climate change: evolutionary perspectives

Infectious plant diseases are a major threat to global agricultural productivity, economic development, and ecological integrity. There is widespread concern that these social and natural disasters caused by infectious plant diseases may escalate with climate change and computer modeling offers a unique opportunity to address this concern. Here, we analyze the intrinsic problems associated with current modeling strategies and highlight the need to integrate evolutionary principles into polytrophic, eco-evolutionary frameworks to improve predictions. We particularly discuss how evolutionary shifts in functional trade-offs, relative adaptability between plants and pathogens, ecosystems, and climate preferences induced by climate change may feedback to future plant disease epidemics and how technological advances can facilitate the generation and integration of this relevant knowledge for better modeling predictions.

Pathogen Identification and Factors Influencing Infection Frequency and Severity of Fungal Rust in Four Native Grasses in Hulunber Grassland, China

A serious rust infection present in 2014 and 2015 on the dominant grass species (Leymus chinensis) in the Hulunber grassland of Inner Mongolia, China, and also present on three other grass species (Agropyron cristatum [wheat grass], Bromus inermis, and Festuca ovina) was investigated. Field surveys, laboratory determination of morphological characteristics, pathogenicity tests, and molecular identification methods were integrated to identify two rust-causing pathogens on L. chinensis. It was found that Puccinia elymi was the major pathogen of L. chinensis, and also infected A. cristatum and F. ovina. This is the first report of P. elymi on A. cristatum in China. P. striiformis caused stripe rust on L. chinensis and B. inermis. The incidence and severity of rust infection increased through the growing season, presumably from asexual spread by urediniospores, and was higher on grass species phylogenetically more closely related to common crop hosts of the pathogens. High host grass density and presence of a potential alternate host for P. elymi, Thalictrum squarrosum, were two further factors promoting rust incidence. These results provide insight into ecological factors linked to the rust epidemic and provide a theoretical basis for the formulation of control strategies.

Image Classification of Wheat Rust Based on Ensemble Learning

Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.

Designing a Pest and Disease Outbreak Warning System for Farmers, Agronomists and Agricultural Input Distributors in East Africa

Simple Summary

Designing early warning systems for threats to food crops in Africa must respond to the needs of potential users of the system. This paper provides evidence from professional distributors, retailers, researchers, and agronomists in East Africa who may be able to use and communicate the results of the predictive modeling of pest outbreaks. Understanding the timing and spatial extent of required warnings will help guide research and engagement in these rapidly commercializing countries.

Abstract

Early warnings of the risks of pest and disease outbreaks are becoming more urgent, with substantial increases in threats to agriculture from invasive pests. With geospatial data improvements in quality and timeliness, models and analytical systems can be used to estimate potential areas at high risk of yield impacts. The development of decision support systems requires an understanding of what information is needed, when it is needed, and at what resolution and accuracy. Here, we report on a professional review conducted with 53 professional agronomists, retailers, distributors, and growers in East Africa working with the Syngenta Foundation for Sustainable Agriculture. The results showed that respondents reported fall armyworm, stemborers and aphids as being among the most common pests, and that crop diversification was a key strategy to reduce their impact. Chemical and cultural controls were the most common strategies for fall armyworm (FAW) control, and biological control was the least known and least used method. Of the cultural control methods, monitoring and scouting, early planting, and crop rotation with non-host crops were most used. Although pests reduced production, only 55% of respondents were familiar with early warning tools, showing the need for predictive systems that can improve farmer response.

Food security and emerging infectious disease: risk assessment and risk management

Climate change, emerging infectious diseases (EIDs) and food security create a dangerous nexus. Habitat interfaces, assumed to be efficient buffers, are being disrupted by human activities which in turn accelerate the movement of pathogens. EIDs threaten directly and indirectly availability and access to nutritious food, affecting global security and human health. In the next 70 years, food-secure and food-insecure countries will face EIDs driving increasingly unsustainable costs of production, predicted to exceed national and global gross domestic products. Our modern challenge is to transform this business as usual and embrace an alternative vision of the biosphere formalized in the Stockholm paradigm (SP). First, a pathogen-centric focus shifts our vision of risk space, determining how pathogens circulate in realized and potential fitness space. Risk space and pathogen exchange are always heightened at habitat interfaces. Second, apply the document-assess-monitor-act (DAMA) protocol developing strategic data for EID risk, to be translated, synthesized and broadcast as actionable information. Risk management is realized through targeted interventions focused around information exchanged among a community of scientists, policy practitioners of food and public health security and local populations. Ultimately, SP and DAMA protect human rights, supporting food security, access to nutritious food, health interventions and environmental integrity.

Use of meteorological data in biosecurity

Pests, pathogens and diseases cause some of the most widespread and damaging impacts worldwide — threatening lives and leading to severe disruption to economic, environmental and social systems. The overarching goal of biosecurity is to protect the health and security of plants and animals (including humans) and the wider environment from these threats. As nearly all living organisms and biological systems are sensitive to weather and climate, meteorological, ‘met’, data are used extensively in biosecurity. Typical applications include, (i) bioclimatic modelling to understand and predict organism distributions and responses, (ii) risk assessment to estimate the probability of events and horizon scan for future potential risks, and (iii) early warning systems to support outbreak management. Given the vast array of available met data types and sources, selecting which data is most effective for each of these applications can be challenging. Here we provide an overview of the different types of met data available and highlight their use in a wide range of biosecurity studies and applications. We argue that there are many synergies between meteorology and biosecurity, and these provide opportunities for more widespread integration and collaboration across the disciplines. To help communicate typical uses of meteorological data in biosecurity to a wide audience we have designed the ‘Meteorology for biosecurity’ infographic.

Creation and judicious application of a wheat resistance gene atlas

Disease-resistance (R) gene cloning in wheat (Triticum aestivum) has been accelerated by the recent surge of genomic resources, facilitated by advances in sequencing technologies and bioinformatics. However, with the challenges of population growth and climate change, it is vital not only to clone and functionally characterize a few handfuls of R genes, but also to do so at a scale that would facilitate the breeding and deployment of crops that can recognize the wide range of pathogen effectors that threaten agroecosystems. Pathogen populations are continually changing, and breeders must have tools and resources available to rapidly respond to those changes if we are to safeguard our daily bread. To meet this challenge, we propose the creation of a wheat R-gene atlas by an international community of researchers and breeders. The atlas would consist of an online directory from which sources of resistance could be identified and deployed to achieve more durable resistance to the major wheat pathogens, such as wheat rusts, blotch diseases, powdery mildew, and wheat blast. We present a costed proposal detailing how the interacting molecular components governing disease resistance could be captured from both the host and the pathogen through biparental mapping, mutational genomics, and whole-genome association genetics. We explore options for the configuration and genotyping of diversity panels of hexaploid and tetraploid wheat, as well as their wild relatives and major pathogens, and discuss how the atlas could inform a dynamic, durable approach to R-gene deployment. Set against the current magnitude of wheat yield losses worldwide, recently estimated at 21%, this endeavor presents one route for bringing R genes from the lab to the field at a considerable speed and quantity.

Computer Vision Framework for Wheat Disease Identification and Classification Using Jetson GPU Infrastructure

Diseases have adverse effects on crop production and yield loss. Various diseases such as leaf rust, stem rust, and strip rust can affect yield quality and quantity for a studied area. In addition, manual wheat disease identification and interpretation is time-consuming and cumbersome. Currently, decisions related to plants mainly rely on the level of expertise in the domain. To resolve these challenges and to identify wheat disease as early as possible, we implemented different deep learning models such as Inceptionv3, Resnet50, and VGG16/19. This research was conducted in collaboration with Bishoftu Agricultural Research Institute, Ethiopia. Our main objective was to automate plant-disease identification using advanced deep learning approaches and image data. For the experiment, RGB image data were collected from the Bishoftu area. From the experimental results, the VGG19 model classified wheat disease with 99.38% accuracy.

The persistent threat of emerging plant disease pandemics to global food security

Plant disease outbreaks are increasing and threaten food security for the vulnerable in many areas of the world. Now a global human pandemic is threatening the health of millions on our planet. A stable, nutritious food supply will be needed to lift people out of poverty and improve health outcomes. Plant diseases, both endemic and recently emerging, are spreading and exacerbated by climate change, transmission with global food trade networks, pathogen spillover, and evolution of new pathogen lineages. In order to tackle these grand challenges, a new set of tools that include disease surveillance and improved detection technologies including pathogen sensors and predictive modeling and data analytics are needed to prevent future outbreaks. Herein, we describe an integrated research agenda that could help mitigate future plant disease pandemics.

Potential Infection Risks of the Wheat Stripe Rust and Stem Rust Pathogens on Barberry in Asia and Southeastern Europe

Barberry (Berberis spp.) is an alternate host for both the stripe rust pathogen, Puccinia striiformis f. sp. tritici (Pst), and the stem rust pathogen, P. graminis f. sp. tritici (Pgt), infecting wheat. Infection risk was assessed to determine whether barberry could be infected by either of the pathogens in Asia and Southeastern Europe, known for recurring epidemics on wheat and the presence of barberry habitats. For assessing infection risk, mechanistic infection models were used to calculate infection indices for both pathogens on barberry following a modeling framework. In East Asia, Bhutan, China, and Nepal were found to have low risks of barberry infection by Pst but high risks by Pgt. In Central Asia, Azerbaijan, Iran, Kazakhstan, southern Russia, and Uzbekistan were identified to have low to high risks of barberry infection for both Pst and Pgt. In Northwest Asia, risk levels of both pathogens in Turkey and the Republic of Georgia were determined to be high to very high. In Southwest Asia, no or low risk was found. In Southeastern Europe, similar high or very high risks for both pathogens were noted for all countries. The potential risks of barberry infection by Pst and/or Pgt should provide guidelines for monitoring barberry infections and could be valuable for developing rust management programs in these regions. The framework used in this study may be useful to predict rust infection risk in other regions.

Wheat rust epidemics damage Ethiopian wheat production: A decade of field disease surveillance reveals national-scale trends in past outbreaks

Wheat rusts are the key biological constraint to wheat production in Ethiopia-one of Africa's largest wheat producing countries. The fungal diseases cause economic losses and threaten livelihoods of smallholder farmers. While it is known that wheat rust epidemics have occurred in Ethiopia, to date no systematic long-term analysis of past outbreaks has been available. We present results from one of the most comprehensive surveillance campaigns of wheat rusts in Africa. More than 13,000 fields have been surveyed during the last 13 years. Using a combination of spatial data-analysis and visualization, statistical tools, and empirical modelling, we identify trends in the distribution of wheat stem rust (Sr), stripe rust (Yr) and leaf rust (Lr). Results show very high infection levels (mean incidence for Yr: 44%; Sr: 34%; Lr: 18%). These recurrent rust outbreaks lead to substantial economic losses, which we estimate to be of the order of 10s of millions of US-D annually. On the widely adopted wheat variety, Digalu, there is a marked increase in disease prevalence following the incursion of new rust races into Ethiopia, which indicates a pronounced boom-and-bust cycle of major gene resistance. Using spatial analyses, we identify hotspots of disease risk for all three rusts, show a linear correlation between altitude and disease prevalence, and find a pronounced north-south trend in stem rust prevalence. Temporal analyses show a sigmoidal increase in disease levels during the wheat season and strong inter-annual variations. While a simple logistic curve performs satisfactorily in predicting stem rust in some years, it cannot account for the complex outbreak patterns in other years and fails to predict the occurrence of stripe and leaf rust. The empirical insights into wheat rust epidemiology in Ethiopia presented here provide a basis for improving future surveillance and to inform the development of mechanistic models to predict disease spread.

Early warning systems in biosecurity; translating risk into action in predictive systems for invasive alien species

Invasive alien species (IAS) are one of the most severe threats to biodiversity and are the subject of varying degrees of surveillance activity. Predictive early warning systems (EWS), incorporating automated surveillance of relevant dataflows, warning generation and dissemination to decision makers are a key target for developing effective management around IAS, alongside more conventional early detection and horizon scanning technologies. Sophisticated modelling frameworks including the definition of the ‘risky’ species pool, and pathway analysis at the macro and micro-scale are increasingly available to support decision making and to help prioritise risks from different regions and/or taxa. The main challenges in constructing such frameworks, to be applied to border inspections, are (i) the lack of standardisation and integration of the associated complex digital data environments and (ii) effective integration into the decision making process, ensuring that risk information is disseminated in an actionable way to frontline surveillance staff and other decision makers. To truly achieve early warning in biosecurity requires close collaboration between developers and end-users to ensure that generated warnings are duly considered by decision makers, reflect best practice, scientific understanding and the working environment facing frontline actors. Progress towards this goal will rely on openness and mutual understanding of the role of EWS in IAS risk management, as much as on developments in the underlying technologies for surveillance and modelling procedures.

Misidentification by farmers of the crop varieties they grow: Lessons from DNA fingerprinting of wheat in Ethiopia

Accurate identification of crop varieties grown by farmers is crucial, among others, for crop management, food security and varietal development and dissemination purposes. One may expect varietal identification to be more challenging in the context of developing countries where literacy and education are limited and informal seed systems and seed recycling are common. This paper evaluates the extent to which smallholder farmers misidentify their wheat varieties in Ethiopia and explores the associated factors and their implications. The study uses data from a nationally representative wheat growing sample household survey and DNA fingerprinting of seed samples from 3,884 wheat plots in major wheat growing zones of Ethiopia. 28-34% of the farmers correctly identified their wheat varieties. Correct identification was positively associated with farmer education and seed purchases from trusted sources (cooperatives or known farmers) and negatively associated with seed recycling. Farmers' varietal identification thereby is problematic and leads to erroneous results in adoption and impact assessments. DNA fingerprinting can enhance varietal identification but remains mute in the identification of contextual and explanatory factors. Thus, combining household survey and DNA fingerprinting approaches is needed for reliable varietal adoption and impact assessments, and generate useful knowledge to inform policy recommendations related to varietal replacement and seed systems development.

Breeding Wheat for Durable Leaf Rust Resistance in Southern Africa: Variability, Distribution, Current Control Strategies, Challenges and Future Prospects

Leaf or brown rust of wheat caused by Puccinia triticina (Pt) is one of the most damaging diseases globally. Considerable progress has been made to control leaf rust through crop protection chemicals and host plant resistance breeding in southern Africa. However, frequent changes in the pathogen population still present a major challenge to achieve durable resistance. Disease surveillance and monitoring of the pathogen have revealed the occurrence of similar races across the region, justifying the need for concerted efforts by countries in southern Africa to develop and deploy more efficient and sustainable strategies to manage the disease. Understanding the genetic variability and composition of Pt is a pre-requisite for cultivar release with appropriate resistance gene combinations for sustainable disease management. This review highlights the variability and distribution of the Pt population, and the current control strategies, challenges and future prospects of breeding wheat varieties with durable leaf rust resistance in southern Africa. The importance of regular, collaborative and efficient surveillance of the pathogen and germplasm development across southern Africa is discussed, coupled with the potential of using modern breeding technologies to produce wheat cultivars with durable resistance.