Peanut Leaf Wilting Estimation From RGB Color Indices and Logistic Models

Technological Progress Toward Peanut Disease Management: A Review

Peanut (Arachis hypogea L.) crops in the southeastern U.S. suffer significant yield losses from diseases like leaf spot, southern blight, and stem rot. Traditionally, growers use conventional boom sprayers, which often leads to overuse and wastage of agrochemicals. However, advances in computer technologies have enabled the development of precision or variable-rate sprayers, both ground-based and drone-based, that apply agrochemicals more accurately. Historically, crop disease scouting has been labor-intensive and costly. Recent innovations in computer vision, artificial intelligence (AI), and remote sensing have transformed disease identification and scouting, making the process more efficient and economical. Over the past decade, numerous studies have focused on developing technologies for peanut disease scouting and sprayer technology. The current research trend shows significant advancements in precision spraying technologies, facilitating smart spraying capabilities. These advancements include the use of various platforms, such as ground-based and unmanned aerial vehicle (UAV)-based systems, equipped with sensors like RGB (red-blue-green), multispectral, thermal, hyperspectral, light detection and ranging (LiDAR), and other innovative detection technologies, as highlighted in this review. However, despite the availability of some commercial precision sprayers, their effectiveness is limited in managing certain peanut diseases, such as white mold, because the disease affects the roots, and the chemicals often remain in the canopy, failing to reach the soil where treatment is needed. The review concludes that further advances are necessary to develop more precise sprayers that can meet the needs of large-scale farmers and significantly enhance production outcomes. Overall, this review paper aims to provide a review of smart spraying techniques, estimating the required agrochemicals and applying them precisely in peanut fields.

Integrating Remote Sensing and Soil Features for Enhanced Machine Learning-Based Corn Yield Prediction in the Southern US

Efficient and reliable corn (Zea mays L.) yield prediction is important for varietal selection by plant breeders and management decision-making by growers. Unlike prior studies that focus mainly on county-level or controlled laboratory-scale areas, this study targets a production-scale area, better representing real-world agricultural conditions and offering more practical relevance for farmers. Therefore, the objective of our study was to determine the best combination of vegetation indices and abiotic factors for predicting corn yield in a rain-fed, production-scale area, identify the most suitable corn growth stage for yield estimation using machine learning, and identify the most effective machine learning model for corn yield estimation. Our study used high-resolution (6 cm) aerial multispectral imagery. Sixty-two different predictors, including soil properties (sand, silt, and clay percentages), slope, spectral bands (red, green, blue, red-edge, NIR), vegetation indices (GNDRE, NDRE, TGI), color-space indices, and wavelengths were derived from the multispectral data collected at the seven (V4, V5, V6, V7, V9, V12, and V14/VT) growth stages of corn. Four regression and machine learning algorithms were evaluated for yield prediction: linear regression, random forest, extreme gradient boosting, and gradient boosting regressor. A total of 6865 yield values were used for model training and 1716 for validation. Results show that, using random forest method, the V14/VT stage had the best yield predictions (RMSE of 0.52 Mg/ha for a mean yield of 10.19 Mg/ha), and yield estimation at V6 stage was still feasible. We concluded that integrating abiotic factors, such as slope and soil properties, significantly improved model accuracy. Among vegetation indices, TGI, HUE, and GNDRE performed better. Results from this study can help farmers or crop consultants plan ahead for future logistics through enhanced early-season yield predictions and support farm profitability and sustainability.

Multi-sensor and multi-temporal high-throughput phenotyping for monitoring and early detection of water-limiting stress in soybean

Soybean (Glycine max [L.] Merr.) production is susceptible to biotic and abiotic stresses, exacerbated by extreme weather events. Water limiting stress, that is, drought, emerges as a significant risk for soybean production, underscoring the need for advancements in stress monitoring for crop breeding and production. This project combined multi-modal information to identify the most effective and efficient automated methods to study drought response. We investigated a set of diverse soybean accessions using multiple sensors in a time series high-throughput phenotyping manner to: (1) develop a pipeline for rapid classification of soybean drought stress symptoms, and (2) investigate methods for early detection of drought stress. We utilized high-throughput time-series phenotyping using unmanned aerial vehicles and sensors in conjunction with machine learning analytics, which offered a swift and efficient means of phenotyping. The visible bands were most effective in classifying the severity of canopy wilting stress after symptom emergence. Non-visual bands in the near-infrared region and short-wave infrared region contribute to the differentiation of susceptible and tolerant soybean accessions prior to visual symptom development. We report pre-visual detection of soybean wilting using a combination of different vegetation indices and spectral bands, especially in the red-edge. These results can contribute to early stress detection methodologies and rapid classification of drought responses for breeding and production applications.

Investigating high throughput phenotyping based morpho-physiological and biochemical adaptations of indian pennywort (Centella asiatica L. urban) in response to different irrigation regimes

Indian pennywort (Centella asiatica L. Urban; Apiaceae) is a herbaceous plant used as traditional medicine in several regions worldwide. An adequate supply of fresh water in accordance with crop requirements is an important tool for maintaining the productivity and quality of medicinal plants. The objective of this study was to find a suitable irrigation schedule for improving the morphological and physiological characteristics, and crop productivity of Indian pennywort using high-throughput phenotyping. Four treatments were considered based on irrigation schedules (100, 75, 50, and 25% of field capacity denoted by I100 [control], I75, I50, and I25, respectively). The number of leaves, plant perimeter, plant volume, and shoot dry weight were sustained in I75 irrigated plants, whereas adverse effects on plant growth parameters were observed when plants were subjected to I25 irrigation for 21 days. Leaf temperature (Tleaf) was also retained in I75 irrigated plants, when compared with control. An increase of 2.0 °C temperature was detected in the Tleaf of plants under I25 irrigation treatment when compared with control. The increase in Tleaf was attributed to a decreased transpiration rate (R2 = 0.93), leading to an elevated crop water stress index. Green reflectance and leaf greenness remained unchanged in plants under I75 irrigation, while significantly decreased under I50 and I25 irrigation. These decreases were attributed to declined leaf osmotic potential, increased non-photochemical quenching, and inhibition of net photosynthetic rate (Pn). The asiatic acid and total centellosides in the leaf tissues, and centellosides yield of plants under I75 irrigation were retained when compared with control, while these parameters were regulated to maximal when exposed to I50 irrigation. Based on the results, I75 irrigation treatment was identified as the optimum irrigation schedule for Indian pennywort in terms of sustained biomass and a stable total centellosides. However, further validation in the field trials at multiple locations and involving different crop rotations is recommended to confirm these findings.

Comparison of Various Drought Resistance Traits in Soybean (Glycine max L.) Based on Image Analysis for Precision Agriculture

Drought is being annually exacerbated by recent global warming, leading to crucial damage of crop growth and final yields. Soybean, one of the most consumed crops worldwide, has also been affected in the process. The development of a resistant cultivar is required to solve this problem, which is considered the most efficient method for crop producers. To accelerate breeding cycles, genetic engineering and high-throughput phenotyping technologies have replaced conventional breeding methods. However, the current novel phenotyping method still needs to be optimized by species and varieties. Therefore, we aimed to assess the most appropriate and effective phenotypes for evaluating drought stress by applying a high-throughput image-based method on the nested association mapping (NAM) population of soybeans. The acquired image-based traits from the phenotyping platform were divided into three large categories-area, boundary, and color-and demonstrated an aspect for each characteristic. Analysis on categorized traits interpreted stress responses in morphological and physiological changes. The evaluation of drought stress regardless of varieties was possible by combining various image-based traits. We might suggest that a combination of image-based traits obtained using computer vision can be more efficient than using only one trait for the precision agriculture.

Evaluating Plant Drought Resistance with a Raspberry Pi and Time-lapse Photography

Identifying genetic variations or treatments that confer greater resistance to drought is paramount to ensuring sustainable crop productivity. Accurate and reproducible measurement of drought stress symptoms can be achieved via automated, image-based phenotyping. Many phenotyping platforms are either cost-prohibitive, require specific technical expertise, or are simply more complex than necessary to effectively evaluate drought resistance. Certain mutations, allelic variations, or treatments result in plants that constitutively use less water. To accurately identify genetic differences or treatments that confer a drought phenotype, plants from all experimental groups must be subjected to equal levels of drought stress. This can be easily achieved by growing and imaging plants that are grown in the same pot. Here, we provide a detailed protocol to configure a Raspberry Pi computer and camera module to image seedlings of multiple genotypes growing in shared pots and to transfer images and metadata via the cloud for downstream analyses. Also detailed is a method to calculate percent soil water content of pots while being imaged to allow for comparison of stress symptoms with water availability. This protocol was recently used to uncouple differential water usage from drought resistance in a dwarf Arabidopsis thaliana mutant chiquita1-1/cost1 compared to the wild-type control. It is cost effective, suitable for any plant species, customizable to various biological questions, and requires no prior experience with electronics or basic software programming.

Multi-locus genome-wide association studies reveal genomic regions and putative candidate genes associated with leaf spot diseases in African groundnut (Arachis hypogaea L.) germplasm

Early leaf spot (ELS) and late leaf spot (LLS) diseases are the two most destructive groundnut diseases in Ghana resulting in ≤ 70% yield losses which is controlled largely by chemical method. To develop leaf spot resistant varieties, the present study was undertaken to identify single nucleotide polymorphism (SNP) markers and putative candidate genes underlying both ELS and LLS. In this study, six multi-locus models of genome-wide association study were conducted with the best linear unbiased predictor obtained from 294 African groundnut germplasm screened for ELS and LLS as well as image-based indices of leaf spot diseases severity in 2020 and 2021 and 8,772 high-quality SNPs from a 48 K SNP array Axiom platform. Ninety-seven SNPs associated with ELS, LLS and five image-based indices across the chromosomes in the 2 two sub-genomes. From these, twenty-nine unique SNPs were detected by at least two models for one or more traits across 16 chromosomes with explained phenotypic variation ranging from 0.01 - 62.76%, with exception of chromosome (Chr) 08 (Chr08), Chr10, Chr11, and Chr19. Seventeen potential candidate genes were predicted at ± 300 kbp of the stable/prominent SNP positions (12 and 5, down- and upstream, respectively). The results from this study provide a basis for understanding the genetic architecture of ELS and LLS diseases in African groundnut germplasm, and the associated SNPs and predicted candidate genes would be valuable for breeding leaf spot diseases resistant varieties upon further validation.

A cooperative scheme for late leaf spot estimation in peanut using UAV multispectral images

In Australia, peanuts are mainly grown in Queensland with tropical and subtropical climates. The most common foliar disease that poses a severe threat to quality peanut production is late leaf spot (LLS). Unmanned aerial vehicles (UAVs) have been widely investigated for various plant trait estimations. The existing works on UAV-based remote sensing have achieved promising results for crop disease estimation using a mean or a threshold value to represent the plot-level image data, but these methods might be insufficient to capture the distribution of pixels within a plot. This study proposes two new methods, namely measurement index (MI) and coefficient of variation (CV), for LLS disease estimation on peanuts. We first investigated the relationship between the UAV-based multispectral vegetation indices (VIs) and the LLS disease scores at the late growth stages of peanuts. We then compared the performances of the proposed MI and CV-based methods with the threshold and mean-based methods for LLS disease estimation. The results showed that the MI-based method achieved the highest coefficient of determination and the lowest error for five of the six chosen VIs whereas the CV-based method performed the best for simple ratio (SR) index among the four methods. By considering the strengths and weaknesses of each method, we finally proposed a cooperative scheme based on the MI, the CV and the mean-based methods for automatic disease estimation, demonstrated by applying this scheme to the LLS estimation in peanuts.

Exploration of Alternative Approaches to Phenotyping of Late Leaf Spot and Groundnut Rosette Virus Disease for Groundnut Breeding

Late leaf spot (LLS), caused by Nothopassalora personata (Berk. & M.A Curt.), and groundnut rosette disease (GRD), [caused by groundnut rosette virus (GRV)], represent the most important biotic constraints to groundnut production in Uganda. Application of visual scores in selection for disease resistance presents a challenge especially when breeding experiments are large because it is resource-intensive, subjective, and error-prone. High-throughput phenotyping (HTP) can alleviate these constraints. The objective of this study is to determine if HTP derived indices can replace visual scores in a groundnut breeding program in Uganda. Fifty genotypes were planted under rain-fed conditions at two locations, Nakabango (GRD hotspot) and NaSARRI (LLS hotspot). Three handheld sensors (RGB camera, GreenSeeker, and Thermal camera) were used to collect HTP data on the dates visual scores were taken. Pearson correlation was made between the indices and visual scores, and logistic models for predicting visual scores were developed. Normalized difference vegetation index (NDVI) (r = -0.89) and red-green-blue (RGB) color space indices CSI (r = 0.76), v* (r = -0.80), and b* (r = -0.75) were highly correlated with LLS visual scores. NDVI (r = -0.72), v* (r = -0.71), b* (r = -0.64), and GA (r = -0.67) were best related to the GRD visual symptoms. Heritability estimates indicated NDVI, green area (GA), greener area (GGA), a*, and hue angle having the highest heritability (H ² > 0.75). Logistic models developed using these indices were 68% accurate for LLS and 45% accurate for GRD. The accuracy of the models improved to 91 and 84% when the nearest score method was used for LLS and GRD, respectively. Results presented in this study indicated that use of handheld remote sensing tools can improve screening for GRD and LLS resistance, and the best associated indices can be used for indirect selection for resistance and improve genetic gain in groundnut breeding.

Phenotyping and Quantitative Trait Locus Analysis for the Limited Transpiration Trait in an Upper-Mid South Soybean Recombinant Inbred Line Population ("Jackson" × "KS4895"): High Throughput Aquaporin Inhibitor Screening

Soybean is most often grown under rainfed conditions and negatively impacted by drought stress in the upper mid-south of the United States. Therefore, identification of drought-tolerance traits and their corresponding genetic components are required to minimize drought impacts on productivity. Limited transpiration (TRlim) under high vapor pressure deficit (VPD) is one trait that can help conserve soybean water-use during late-season drought. The main research objective was to evaluate a recombinant inbred line (RIL) population, from crossing two mid-south soybean lines ("Jackson" × "KS4895"), using a high-throughput technique with an aquaporin inhibitor, AgNO3, for the TRlim trait. A secondary objective was to undertake a genetic marker/quantitative trait locus (QTL) genetic analysis using the AgNO3 phenotyping results. A set of 122 soybean genotypes (120-RILs and parents) were grown in controlled environments (32/25-d/n °C). The transpiration rate (TR) responses of derooted soybean shoots before and after application of AgNO3 were measured under 37°C and >3.0 kPa VPD. Then, the decrease in transpiration rate (DTR) for each genotype was determined. Based on DTR rate, a diverse group (slow, moderate, and high wilting) of 26 RILs were selected and tested for the whole plant TRs under varying levels of VPD (0.0-4.0 kPa) at 32 and 37°C. The phenotyping results showed that 88% of slow, 50% of moderate, and 11% of high wilting genotypes expressed the TRlim trait at 32°C and 43, 10, and 0% at 37°C, respectively. Genetic mapping with the phenotypic data we collected revealed three QTL across two chromosomes, two associated with TRlim traits and one associated with leaf temperature. Analysis of Gene Ontologies of genes within QTL regions identified several intriguing candidate genes, including one gene that when overexpressed had previously been shown to confer enhanced tolerance to abiotic stress. Collectively these results will inform and guide ongoing efforts to understand how to deploy genetic tolerance for drought stress.

Aerial high-throughput phenotyping of peanut leaf area index and lateral growth

Leaf area index (LAI) is the ratio of the total one-sided leaf area to the ground area, whereas lateral growth (LG) is the measure of canopy expansion. They are indicators for light capture, plant growth, and yield. Although LAI and LG can be directly measured, this is time consuming. Healthy leaves absorb in the blue and red, and reflect in the green regions of the electromagnetic spectrum. Aerial high-throughput phenotyping (HTP) may enable rapid acquisition of LAI and LG from leaf reflectance in these regions. In this paper, we report novel models to estimate peanut (Arachis hypogaea L.) LAI and LG from vegetation indices (VIs) derived relatively fast and inexpensively from the red, green, and blue (RGB) leaf reflectance collected with an unmanned aerial vehicle (UAV). In addition, we evaluate the models' suitability to identify phenotypic variation for LAI and LG and predict pod yield from early season estimated LAI and LG. The study included 18 peanut genotypes for model training in 2017, and 8 genotypes for model validation in 2019. The VIs included the blue green index (BGI), red-green ratio (RGR), normalized plant pigment ratio (NPPR), normalized green red difference index (NGRDI), normalized chlorophyll pigment index (NCPI), and plant pigment ratio (PPR). The models used multiple linear and artificial neural network (ANN) regression, and their predictive accuracy ranged from 84 to 97%, depending on the VIs combinations used in the models. The results concluded that the new models were time- and cost-effective for estimation of LAI and LG, and accessible for use in phenotypic selection of peanuts with desirable LAI, LG and pod yield.

Identifying Optimal Wavelengths as Disease Signatures Using Hyperspectral Sensor and Machine Learning

Hyperspectral sensors combined with machine learning are increasingly utilized in agricultural crop systems for diverse applications, including plant disease detection. This study was designed to identify the most important wavelengths to discriminate between healthy and diseased peanut (Arachis hypogaea L.) plants infected with Athelia rolfsii, the causal agent of peanut stem rot, using in-situ spectroscopy and machine learning. In greenhouse experiments, daily measurements were conducted to inspect disease symptoms visually and to collect spectral reflectance of peanut leaves on lateral stems of plants mock-inoculated and inoculated with A. rolfsii. Spectrum files were categorized into five classes based on foliar wilting symptoms. Five feature selection methods were compared to select the top 10 ranked wavelengths with and without a custom minimum distance of 20 nm. Recursive feature elimination methods outperformed the chi-square and SelectFromModel methods. Adding the minimum distance of 20 nm into the top selected wavelengths improved classification performance. Wavelengths of 501–505, 690–694, 763 and 884 nm were repeatedly selected by two or more feature selection methods. These selected wavelengths can be applied in designing optical sensors for automated stem rot detection in peanut fields. The machine-learning-based methodology can be adapted to identify spectral signatures of disease in other plant-pathogen systems.