Exploring the Potential of High-Resolution Satellite Imagery for the Detection of Soybean Sudden Death Syndrome

Machine learning in the classification of asian rust severity in soybean using hyperspectral sensor

Traditional monitoring of asian soybean rust severity is a time- and labor-intensive task, as it requires visual assessments by skilled professionals in the field. Thus, the use of remote sensing and machine learning (ML) techniques in data processing has emerged as an approach that can increase efficiency in disease monitoring, enabling faster, more accurate and time- and labor-saving evaluations. The aims of the study were: (i) to identify the spectral signature of different levels of Asian soybean rust severity; (ii) to identify the most accurate machine learning algorithm for classifying disease severity levels; (iii) which spectral input provides the highest classification accuracy for the algorithms; (iv) to determine a sample size of leaves that guarantees the best accuracy for the algorithms. A field experiment was carried out in the 2022/2023 harvest in a randomized block design with a 6x3 factorial scheme (ML algorithms x severity levels) and four replications. Disease severity levels assessed were: healthy leaves, 25 % severity, and 50 % severity. Leaf hyperspectral analysis was carried out over a wide range from 350 to 2500 nm. From this analysis, 28 spectral bands were extracted, seeking to distinguish the spectral signature for each severity level with the least input dataset. Data was subjected to machine learning analysis using Artificial Neural Network (ANN), REPTree (DT) and J48 decision trees, Random Forest (RF), and Support Vector Machine (SVM) algorithms, as well as a traditional classification method (Logistic Regression - LR). Two different input datasets were tested for each algorithm: the full spectrum (ALL) provided by the sensor and the 28 spectral bands (SB). Tests with different sample sizes were also conducted to investigate the algorithms' ability to detect severity levels with a reduced sample size. Our findings indicate differences between the spectral curves for the severity levels assessed, which makes it possible to differentiate between healthy plants with low and high severity using hyperspectral sensing. SVM was the most accurate algorithm for classifying severity levels by using all the spectral information as input. This algorithm also provided high classification accuracy when using smaller leaf samples. This study reveals that hyperspectral sensing and the use of ML algorithms provide an accurate classification of different levels of Asian rust severity, and can be powerful tools for a more efficient disease monitoring process.

Current and emerging trends in techniques for plant pathogen detection

Plant pathogenic microorganisms cause substantial yield losses in several economically important crops, resulting in economic and social adversity. The spread of such plant pathogens and the emergence of new diseases is facilitated by human practices such as monoculture farming and global trade. Therefore, the early detection and identification of pathogens is of utmost importance to reduce the associated agricultural losses. In this review, techniques that are currently available to detect plant pathogens are discussed, including culture-based, PCR-based, sequencing-based, and immunology-based techniques. Their working principles are explained, followed by an overview of the main advantages and disadvantages, and examples of their use in plant pathogen detection. In addition to the more conventional and commonly used techniques, we also point to some recent evolutions in the field of plant pathogen detection. The potential use of point-of-care devices, including biosensors, have gained in popularity. These devices can provide fast analysis, are easy to use, and most importantly can be used for on-site diagnosis, allowing the farmers to take rapid disease management decisions.

Estimating probability of visual detection of exotic pests and diseases in the grains industry—An expert elicitation approach

Participants in the grains industry undertake general surveillance monitoring of grain crops for early detection of pests and diseases. Evaluating the adequacy of monitoring to ensure successful early detection relies on understanding the probability of detection of the relevant exotic crop pests and diseases. Empirical data on probability of detection is often not available. Our aim was to both gain a better understanding of how agronomists undertake visual crop surveillance, and use this insight to help inform structured expert judgments about the probability of early detection of various exotic grain pests and diseases. In our study we surveyed agronomists under a state funded program to identify survey methods used to undertake visual inspection of grain crops, and their confidence in detecting pests and diseases using the associated methods. We then elicited expert judgments on the probabilities of visual detection by agronomists of key exotic pests and diseases, and compared these estimates with the self-assessments of confidence made by agronomists. Results showed that agronomists used a systematic approach to visual crop inspection but that they were not confident in detecting exotic pests and diseases, with the exception of pest and diseases that affect leaves. They were most confident in visually detecting Barley stripe rust and Russian wheat aphid; however, confidence in detecting the latter was influenced by recent training. Expert judgments on the ability of agronomists to visually detect exotic pests and diseases early was in accordance with agronomists’ self-rated confidence of detection but highlighted uncertainty around the ability of agronomists in detecting non-leaf pests and diseases. The outcomes of the study demonstrated the utility of structured expert elicitation as a cost-effective tool for reducing knowledge gaps around the sensitivity of general surveillance for early detection, which in turn improves area freedom estimates.

Rice False Smut Detection and Prescription Map Generation in a Complex Planting Environment, with Mixed Methods, Based on Near Earth Remote Sensing

Rice false smut is known as the cancer of rice. The disease is becoming increasingly prominent and is one of the major diseases in rice. However, prevention and treatment of this disease relies on “Centralized pesticide spraying”. However, indiscriminate spraying leads to more pesticide residue, and impacts ecological and food safety. To obtain more objective results, different experimental planting forms are necessary. This study collected data at a complex planting environment based on “near earth remote sensing” using a frame-based hyperspectral device. We used mixed detection methods to differentiate between healthy rice and U. virens infected rice. There were 49 arrangements and more than 196 differentiation models between healthy and diseased rice, including 7 sowing data plots, 2 farm management types, and 23 pattern recognition methods. Finally, the real accuracy was mostly above 95%. In particular, with the increase of epoch and iteration, feature sequences based on deep learning could achieve better results; most of the accuracies were 100% with 100 epochs. We also found that differentiation accuracy was not necessarily correlated with the sowing dates and farm management. Finally, the detection method was verified according to the actual investigation results in the field. The prescription map of disease incidence was generated, which provided a theoretical basis for the follow-up precision plant protection work.

Plant Disease Sensing: Studying Plant-Pathogen Interactions at Scale

Plant disease threatens the environmental and financial sustainability of crop production, causing $220 billion in annual losses. The dire threat disease poses to modern agriculture demands tools for better detection and monitoring to prevent crop loss and input waste. The nascent discipline of plant disease sensing, or the science of using proximal and/or remote sensing to detect and diagnose disease, offers great promise to extend monitoring to previously unachievable resolutions, a basis to construct multiscale surveillance networks for early warning, alert, and response at low latency, an opportunity to mitigate loss while optimizing protection, and a dynamic new dimension to agricultural systems biology. Despite its revolutionary potential, plant disease sensing remains an underdeveloped discipline, with challenges facing both fundamental study and field application. This article offers a perspective on the current state and future of plant disease sensing, highlights remaining gaps to be filled, and presents a bold vision for the future of global agriculture.

Current recommendations and novel strategies for sustainable management of soybean sudden death syndrome

The increase in food production requires reduction of the damage caused by plant pathogens, minimizing the environmental impact of management practices. Soil-borne pathogens are among the most relevant pathogens that affect soybean crop yield. Soybean sudden death syndrome (SDS), caused by several distinct species of Fusarium, produces significant yield losses in the leading soybean-producing countries in North and South America. Current management strategies for SDS are scarce since there are no highly resistant cultivars and only a few fungicide seed treatments are available. Because of this, innovative approaches for SDS management need to be developed. Here, we summarize recently explored strategies based on plant nutrition, biological control, priming of plant defenses, host-induced gene silencing, and the development of new SDS-resistance cultivars using precision breeding techniques. Finally, sustainable management of SDS should also consider cultural control practices with minimal environmental impact. © 2021 Society of Chemical Industry.

Plant pest surveillance: from satellites to molecules

Plant pests and diseases impact both food security and natural ecosystems, and the impact has been accelerated in recent years due to several confounding factors. The globalisation of trade has moved pests out of natural ranges, creating damaging epidemics in new regions. Climate change has extended the range of pests and the pathogens they vector. Resistance to agrochemicals has made pathogens, pests, and weeds more difficult to control. Early detection is critical to achieve effective control, both from a biosecurity as well as an endemic pest perspective. Molecular diagnostics has revolutionised our ability to identify pests and diseases over the past two decades, but more recent technological innovations are enabling us to achieve better pest surveillance. In this review, we will explore the different technologies that are enabling this advancing capability and discuss the drivers that will shape its future deployment.

Integrating Spectral Information and Meteorological Data to Monitor Wheat Yellow Rust at a Regional Scale: A Case Study

Wheat yellow rust has a severe impact on wheat production and threatens food security in China; as such, an effective monitoring method is necessary at the regional scale. We propose a model for yellow rust monitoring based on Sentinel-2 multispectral images and a series of two-stage vegetation indices and meteorological data. Sensitive spectral vegetation indices (single- and two-stage indices) and meteorological features for wheat yellow rust discrimination were selected using the random forest method. Wheat yellow rust monitoring models were established using three different classification methods: linear discriminant analysis (LDA), support vector machine (SVM), and artificial neural network (ANN). The results show that models based on two-stage indices (i.e., those calculated using images from two different days) significantly outperform single-stage index models (i.e., those calculated using an image from a single day), the overall accuracy improved from 63.2% to 78.9%. The classification accuracies of models combining a vegetation index with meteorological feature are higher than those of pure vegetation index models. Among them, the model based on two-stage vegetation indices and meteorological features performs best, with a classification accuracy exceeding 73.7%. The SVM algorithm performed best for wheat yellow rust monitoring among the three algorithms; its classification accuracy (84.2%) was ~10.5% and 5.3% greater than those of LDA and ANN, respectively. Combined with crop growth and environmental information, our model has great potential for monitoring wheat yellow rust at a regional scale. Future work will focus on regional-scale monitoring and forecasting of crop disease.

A Gated Recurrent Units (GRU)-Based Model for Early Detection of Soybean Sudden Death Syndrome through Time-Series Satellite Imagery

In general, early detection and timely management of plant diseases are essential for reducing yield loss. Traditional manual inspection of fields is often time-consuming and laborious. Automated imaging techniques have recently been successfully applied to detect plant diseases. However, these methods mostly focus on the current state of the crop. This paper proposes a gated recurrent unit (GRU)-based model to predict soybean sudden death syndrome (SDS) disease development. To detect SDS at a quadrat level, the proposed method uses satellite images collected from PlanetScope as the training set. The pixel image data include the spectral bands of red, green, blue and near-infrared (NIR). Data collected during the 2016 and 2017 soybean-growing seasons were analyzed. Instead of using individual static imagery, the GRU-based model converts the original imagery into time-series data. SDS predictions were made on different data scenarios and the results were compared with fully connected deep neural network (FCDNN) and XGBoost methods. The overall test accuracy of classifying healthy and diseased quadrates in all methods was above 76%. The test accuracy of the FCDNN and XGBoost were 76.3–85.5% and 80.6–89.2%, respectively, while the test accuracy of the GRU-based model was 82.5–90.4%. The calculation results show that the proposed method can improve the detection accuracy by up to 7% with time-series imagery. Thus, the proposed method has the potential to predict SDS at a future time.