Leaf and canopy reflectance spectrometry applied to the estimation of angular leaf spot disease severity of common bean crops

Fertilization Strategies in Huanglongbing-Infected Citrus latifolia and Their Physiological and Hormonal Effects

Huanglongbing disease (HLB), caused by Candidatus Liberibacter asiaticus (CLas), affects all commercial citrus species. Persian lime (Citrus latifolia Tanaka), a crop of global economic importance, has shown tolerance to this disease. Efforts are focused on extending the productive life of diseased trees through effective agronomic management. This study aimed to evaluate how different fertilization strategies influence the physiological and hormonal responses of Citrus latifolia on both healthy and HLB-affected plants. It compared the effects of low (Ma-1), medium (Ma-2), and high (Ma-3) doses of macronutrients, with and without the addition of micronutrients (Mi-1), using either soil (Mi-2) or foliar (Mi-3) applications. Treatments were applied every 18 days for one year. C. latifolia showed tolerance; however, HLB infection negatively affected growth parameters, photosynthetic activity, vascular bundle anatomy, reflectance at 550 and 790 nm, carbohydrate metabolism, and the concentration of salicylic acid and its biosynthetic precursors. The hormonal response showed higher levels of benzoic acid and lower levels of salicylic acid than those reported in susceptible citrus. Plants treated with low doses of macronutrients along with soil-applied micronutrients (Ma-1 + Mi-2) showed a 17.9% increase in growth, a 31.3% larger canopy volume, and an 83.3% reduction in starch accumulation compared to the treatment with high doses of macronutrients and both soil and foliar applied micronutrients (Ma-3 + Mi-3). These findings indicate that split soil fertilization with low-dose macronutrients and micronutrients might influence plant physiological responses, potentially improving disease management and decreasing fertilizer inputs.

Development of a vegetation canopy reflectance sensor and its diurnal applicability under clear sky conditions

The spectral reflectance provides valuable information regarding vegetation growth and plays an important role in agriculture, forestry, and grassland management. In this study, a small, portable vegetation canopy reflectance (VCR) sensor that can operate throughout the day was developed. The sensor includes two optical bands at 710 nm and 870 nm, with the light separated by filters, and has a field of view of 28°. It is powered by two 14500 rechargeable batteries and uses Wi-Fi for data transmission. The calibration of the sensor was performed using an integrating sphere, and a solar altitude correction model was constructed. The sensor's accuracy was validated using a standard reflectance gray scale board. The results indicate that the root mean square error (RMSE) and mean absolute error (MAE) at 710 nm were 1.07% and 0.63%, respectively, while those at 870 nm were 0.94% and 0.50%, respectively. Vegetation at 14 sites was measured using both the VCR sensor and an Analytical Spectral Devices (ASD) spectroradiometer at nearly the same time for each site. The results show that the reflectance values measured by both devices were closely aligned. Measurements of Bermuda grass vegetation on clear days revealed that the intra-day reflectance range at 710 nm narrowed from 12.3-19.2% before solar altitude correction to 11.1-13.4% after correction, and the coefficient of variation (CV) decreased from 10.86% to 2.93%. Similarly, at 870 nm, the intra-day reflectance range decreased from 41.6-60.3% to 39.0-42.0%, and the CV decreased from 9.69% to 1.53%. In summary, this study offers a fundamental tool for monitoring vegetation canopy reflectance in the field, which is crucial for advancing high-quality agricultural, grassland, and forest management practices.

Classification models for Tobacco Mosaic Virus and Potato Virus Y using hyperspectral and machine learning techniques

Tobacco Mosaic Virus (TMV) and Potato Virus Y (PVY) pose significant threats to crop production. Non-destructive and accurate surveillance is crucial to effective disease control. In this study, we propose the adoption of hyperspectral and machine learning technologies to discern the type and severity of tobacco leaves affected by PVY and TMV infection. Initially, we applied three preprocessing methods - Multivariate Scattering Correction (MSC), Standard Normal Variate (SNV), and Savitzky-Golay smoothing filter (SavGol) - to corrected the leaf full-length spectral sheet data (350-2500nm). Subsequently, we employed two classifiers, support vector machine (SVM) and random forest (RF), to establish supervised classification models, including binary classification models (healthy/diseased leaves or PVY/TMV infected leaves) and six-class classification models (healthy and various severity levels of diseased leaves). Based on the core evaluation index, our models achieved accuracies in the range of 91-100% in the binary classification. In general, SVM demonstrated superior performance compared to RF in distinguishing leaves infected with PVY and TMV. Different combinations of preprocessing methods and classifiers have distinct capabilities in the six-class classification. Notably, SavGol united with SVM gave an excellent performance in the identification of different PVY severity levels with 98.1% average precision, and also achieved a high recognition rate (96.2%) in the different TMV severity level classifications. The results further highlighted that the effective wavelengths captured by SVM, 700nm and 1800nm, would be valuable for estimating disease severity levels. Our study underscores the efficacy of integrating hyperspectral technology and machine learning, showcasing their potential for accurate and non-destructive monitoring of plant viral diseases.

Advancements in Imaging Sensors and AI for Plant Stress Detection: A Systematic Literature Review

Integrating imaging sensors and artificial intelligence (AI) have contributed to detecting plant stress symptoms, yet data analysis remains a key challenge. Data challenges include standardized data collection, analysis protocols, selection of imaging sensors and AI algorithms, and finally, data sharing. Here, we present a systematic literature review (SLR) scrutinizing plant imaging and AI for identifying stress responses. We performed a scoping review using specific keywords, namely abiotic and biotic stress, machine learning, plant imaging and deep learning. Next, we used programmable bots to retrieve relevant papers published since 2006. In total, 2,704 papers from 4 databases (Springer, ScienceDirect, PubMed, and Web of Science) were found, accomplished by using a second layer of keywords (e.g., hyperspectral imaging and supervised learning). To bypass the limitations of search engines, we selected OneSearch to unify keywords. We carefully reviewed 262 studies, summarizing key trends in AI algorithms and imaging sensors. We demonstrated that the increased availability of open-source imaging repositories such as PlantVillage or Kaggle has strongly contributed to a widespread shift to deep learning, requiring large datasets to train in stress symptom interpretation. Our review presents current trends in AI-applied algorithms to develop effective methods for plant stress detection using image-based phenotyping. For example, regression algorithms have seen substantial use since 2021. Ultimately, we offer an overview of the course ahead for AI and imaging technologies to predict stress responses. Altogether, this SLR highlights the potential of AI imaging in both biotic and abiotic stress detection to overcome challenges in plant data analysis.

Combining canopy reflectance spectrometry and genome-wide prediction to increase response to selection for powdery mildew resistance in cultivated strawberry

High-throughput phenotyping is an emerging approach in plant science, but thus far only a few applications have been made in horticultural crop breeding. Remote sensing of leaf or canopy spectral reflectance can help breeders rapidly measure traits, increase selection accuracy, and thereby improve response to selection. In the present study, we evaluated the integration of spectral analysis of canopy reflectance and genomic information for the prediction of strawberry (Fragaria × ananassa) powdery mildew disease. Two multi-parental breeding populations of strawberry comprising a total of 340 and 464 pedigree-connected seedlings were evaluated in two separate seasons. A single-trait Bayesian prediction method using 1001 spectral wavebands in the ultraviolet-visible-near infrared region (350-1350 nm wavelength) combined with 8552 single nucleotide polymorphism markers showed up to 2-fold increase in predictive ability over models using markers alone. The integration of high-throughput phenotyping was further validated independently across years/trials with improved response to selection of up to 90%. We also conducted Bayesian multi-trait analysis using the estimated vegetative indices as secondary traits. Three vegetative indices (Datt3, REP_Li, and Vogelmann2) had high genetic correlations (rA) with powdery mildew visual ratings with average rA values of 0.76, 0.71, and 0.71, respectively. Increasing training population sizes by incorporating individuals with only vegetative index information yielded substantial increases in predictive ability. These results strongly indicate the use of vegetative indices as secondary traits for indirect selection. Overall, combining spectrometry and genome-wide prediction improved selection accuracy and response to selection for powdery mildew resistance, demonstrating the power of an integrated phenomics-genomics approach in strawberry breeding.

Classification of soybean frogeye leaf spot disease using leaf hyperspectral reflectance

In this study, the feasibility of classifying soybean frogeye leaf spot (FLS) is investigated. Leaf images and hyperspectral reflectance data of healthy and FLS diseased soybean leaves were acquired. First, image processing was used to classify FLS to create a reference for subsequent analysis of hyperspectral data. Then, dimensionality reduction methods of hyperspectral data were used to obtain the relevant information pertaining to FLS. Three single methods, namely spectral index (SI), principal component analysis (PCA), and competitive adaptive reweighted sampling (CARS), along with a PCA and SI combined method, were included. PCA was used to select the effective principal components (PCs), and evaluate SIs. Characteristic wavelengths (CWs) were selected using CARS. Finally, the full wavelengths, CWs, effective PCs, SIs, and significant SIs were divided into 14 datasets (DS1-DS14) and used as inputs to build the classification models. Models' performances were evaluated based on the classification accuracy for both the overall and individual classes. Our results suggest that the FLS comprised of five classes based on the proportion of total leaf surface covered with FLS. In the PCA and SI combination model, 5 PCs and 20 SIs with higher weight coefficient of each PC were extracted. For hyperspectral data, 20 CWs and 26 effective PCs were also selected. Out of the 14 datasets, the model input variables provided by five datasets (DS2, DS3, DS4, DS10, and DS11) were more superior than those of full wavelengths (DS1) both in support vector machine (SVM) and least squares support vector machine (LS-SVM) classifiers. The models developed using these five datasets achieved overall accuracies ranging from 91.8% to 94.5% in SVM, and 94.5% to 97.3% in LS-SVM. In addition, they improved the classification accuracies by 0.9% to 3.6% (SVM) and 0.9% to 3.7% (LS-SVM).