Identification of Rice Sheath Blight through Spectral Responses Using Hyperspectral Images

Spectral characterization and severity assessment of rice blast disease using univariate and multivariate models

Rice is the staple food of more than half of the population of the world and India as well. One of the major constraints in rice production is frequent occurrence of pests and diseases and one of them is rice blast which often causes yield loss varying from 10 to 30%. Conventional approaches for disease assessment are time-consuming, expensive, and not real-time; alternately, sensor-based approach is rapid, non-invasive and can be scaled up in large areas with minimum time and effort.  In the present study, hyperspectral remote sensing for the characterization and severity assessment of rice blast disease was exploited. Field experiments were conducted with 20 genotypes of rice having sensitive and resistant cultivars grown under upland and lowland conditions at Almora, Uttarakhand, India. The severity of the rice blast was graded from 0 to 9 in accordance to International Rice Research Institute (IRRI).  Spectral observations in field were taken using a hand-held portable spectroradiometer in range of 350-2500 nm followed by spectral discrimination of different disease severity levels using Jeffires-Matusita (J-M) distance. Then, evaluation of 26 existing spectral indices (r≥0.8) was done corresponding to blast severity levels and linear regression prediction models were also developed. Further, the proposed ratio blast index (RBI) and normalized difference blast index (NDBI) were developed using all possible combinations of their correlations with severity level followed by their quantification to identify the best indices. Thereafter, multivariate models like support vector machine regression (SVM), partial least squares (PLS), random forest (RF), and multivariate adaptive regression spline (MARS) were also used to estimate blast severity. Jeffires-Matusita distance was separating almost all severity levels having values >1.92 except levels 4 and 5. The 26 prediction models were effective at predicting blast severity with R² values from 0.48 to 0.85. The best developed spectral indices for rice blast were RBI (R1148, R1301) and NDBI (R1148, R1301) with R² of 0.85 and 0.86, respectively. Among multivariate models, SVM was the best model with calibration R²=0.99; validation R²=0.94, RMSE=0.7, and RPD=4.10. The methodology developed paves way for early detection and large-scale monitoring and mapping using satellite remote sensors at farmers' fields for developing better disease management options.

Evaluation of rice bacterial blight severity from lab to field with hyperspectral imaging technique

Hyperspectral imaging technique combined with machine learning is a powerful tool for the evaluation of disease phenotype in rice disease-resistant breeding. However, the current studies are almost carried out in the lab environment, which is difficult to apply to the field environment. In this paper, we used visible/near-infrared hyperspectral images to analysis the severity of rice bacterial blight (BB) and proposed a novel disease index construction strategy (NDSCI) for field application. A designed long short-term memory network with attention mechanism could evaluate the BB severity robustly, and the attention block could filter important wavelengths. Best results were obtained based on the fusion of important wavelengths and color features with an accuracy of 0.94. Then, NSDCI was constructed based on the important wavelength and color feature related to BB severity. The correlation coefficient of NDSCI extended to the field data reached -0.84, showing good scalability. This work overcomes the limitations of environmental conditions and sheds new light on the rapid measurement of phenotype in disease-resistant breeding.

An intelligent monitoring system of diseases and pests on rice canopy

Accurate and timely surveys of rice diseases and pests are important to control them and prevent the reduction of rice yields. The current manual survey method of rice diseases and pests is time-consuming, laborious, highly subjective and difficult to trace historical data. To address these issues, we developed an intelligent monitoring system for detecting and identifying the disease and pest lesions on the rice canopy. The system mainly includes a network camera, an intelligent detection model of diseases and pests on rice canopy, a web client and a server. Each camera of the system can collect rice images in about 310 m² of paddy fields. An improved model YOLO-Diseases and Pests Detection (YOLO-DPD) was proposed to detect three lesions of Cnaphalocrocis medinalis, Chilo suppressalis, and Ustilaginoidea virens on rice canopy. The residual feature augmentation method was used to narrow the semantic gap between different scale features of rice disease and pest images. The convolution block attention module was added into the backbone network to enhance the regional disease and pest features for suppressing the background noises. Our experiments demonstrated that the improved model YOLO-DPD could detect three species of disease and pest lesions on rice canopy at different image scales with an average precision of 92.24, 87.35 and 90.74%, respectively, and a mean average precision of 90.11%. Compared to RetinaNet, Faster R-CNN and Yolov4 models, the mean average precision of YOLO-DPD increased by 18.20, 6.98, 6.10%, respectively. The average detection time of each image is 47 ms. Our system has the advantages of unattended operation, high detection precision, objective results, and data traceability.

The Impact of NPV on the Spectral Parameters in the Yellow-Edge, Red-Edge and NIR Shoulder Wavelength Regions in Grasslands

Even though research has shown that the spectral parameters of yellow-edge, red-edge and NIR (near-infrared) shoulder wavelength regions are able to estimate green cover and leaf area index (LAI), a large amount of dead materials in grasslands challenges the accuracy of their estimation using hyperspectral remote sensing. However, the exact impact of dead vegetation cover on these spectral parameters remains unclear. Therefore, we evaluated the influences of dead materials on the spectral parameters in the wavelength regions of yellow-edge, red-edge and NIR shoulder by comparing normalized difference vegetation indices (NDVI) including the common red valley at 670 nm and NDVI using the red valley extracted by a new statistical method. This method, based on the concept of segmented linear regression, was developed to extract the spectral parameters and calculate NDVI automatically from the hyper-spectra. To fully understand the impact of dead cover on the spectral parameters (i.e., consider full coverage combinations of green vegetation, dead materials and bare soil), both in situ measured and simulated hyper-spectra were analyzed. The impact of dead cover on LAI estimation by those spectral parameters and NDVI were also evaluated. The results show that: (i) without considering the influence of bare soil, dead materials decreases the slope of red-edge, the slope of NIR shoulder and NDVI, while dead materials increases the slope of yellow-edge; (ii) the spectral characteristics of red valley disappear when dead cover exceeds 67%; (iii) large amount of dead materials also result in a blue shift of the red-edge position; (iv) accurate extraction of the red valley position enhances LAI estimation and reduces the influences of dead materials using hyperspectral NDVI; (v) the accuracy of LAI estimation using the slope of yellow-edge, the slope of red-edge, red-edge position and NDVI significantly drops when dead cover exceeds 72.3–74.5% (variation among indices).

A Novel Guanine Elicitor Stimulates Immunity in Arabidopsis and Rice by Ethylene and Jasmonic Acid Signaling Pathways

Rice sheath blight (ShB) caused by Rhizoctonia solani is one of the most destructive diseases in rice. Fungicides are widely used to control ShB in agriculture. However, decades of excessive traditional fungicide use have led to environmental pollution and increased pathogen resistance. Generally, plant elicitors are regarded as environmentally friendly biological pesticides that enhance plant disease resistance by triggering plant immunity. Previously, we identified that the plant immune inducer ZhiNengCong (ZNC), a crude extract of the endophyte, has high activity and a strong ability to protect plants against pathogens. Here, we further found that guanine, which had a significant effect on inducing plant resistance to pathogens, might be an active component of ZNC. In our study, guanine activated bursts of reactive oxygen species, callose deposition and mitogen-activated protein kinase phosphorylation. Moreover, guanine-induced plant resistance to pathogens depends on ethylene and jasmonic acid but is independent of the salicylic acid signaling pathway. Most importantly, guanine functions as a new plant elicitor with broad-spectrum resistance to activate plant immunity, providing an efficient and environmentally friendly biological elicitor for bacterial and fungal disease biocontrol.

Early Detection and Classification of Tomato Leaf Disease Using High-Performance Deep Neural Network

Tomato is one of the most essential and consumable crops in the world. Tomatoes differ in quantity depending on how they are fertilized. Leaf disease is the primary factor impacting the amount and quality of crop yield. As a result, it is critical to diagnose and classify these disorders appropriately. Different kinds of diseases influence the production of tomatoes. Earlier identification of these diseases would reduce the disease’s effect on tomato plants and enhance good crop yield. Different innovative ways of identifying and classifying certain diseases have been used extensively. The motive of work is to support farmers in identifying early-stage diseases accurately and informing them about these diseases. The Convolutional Neural Network (CNN) is used to effectively define and classify tomato diseases. Google Colab is used to conduct the complete experiment with a dataset containing 3000 images of tomato leaves affected by nine different diseases and a healthy leaf. The complete process is described: Firstly, the input images are preprocessed, and the targeted area of images are segmented from the original images. Secondly, the images are further processed with varying hyper-parameters of the CNN model. Finally, CNN extracts other characteristics from pictures like colors, texture, and edges, etc. The findings demonstrate that the proposed model predictions are 98.49% accurate.

Hyperspectral Imaging Combined With Deep Transfer Learning for Rice Disease Detection

Various rice diseases threaten the growth of rice. It is of great importance to achieve the rapid and accurate detection of rice diseases for precise disease prevention and control. Hyperspectral imaging (HSI) was performed to detect rice leaf diseases in four different varieties of rice. Considering that it costs much time and energy to develop a classifier for each variety of rice, deep transfer learning was firstly introduced to rice disease detection across different rice varieties. Three deep transfer learning methods were adapted for 12 transfer tasks, namely, fine-tuning, deep CORrelation ALignment (CORAL), and deep domain confusion (DDC). A self-designed convolutional neural network (CNN) was set as the basic network of the deep transfer learning methods. Fine-tuning achieved the best transferable performance with an accuracy of over 88% for the test set of the target domain in the majority of transfer tasks. Deep CORAL obtained an accuracy of over 80% in four of all the transfer tasks, which was superior to that of DDC. A multi-task transfer strategy has been explored with good results, indicating the potential of both pair-wise, and multi-task transfers. A saliency map was used for the visualization of the key wavelength range captured by CNN with and without transfer learning. The results indicated that the wavelength range with and without transfer learning was overlapped to some extent. Overall, the results suggested that deep transfer learning methods could perform rice disease detection across different rice varieties. Hyperspectral imaging, in combination with the deep transfer learning method, is a promising possibility for the efficient and cost-saving field detection of rice diseases among different rice varieties.

Novel Feature-Extraction Methods for the Estimation of Above-Ground Biomass in Rice Crops

Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and compared against an assembled ground-truth biomass measurements taken by destructive sampling. The proposed GBF-Sm-Bs approach outperformed competing methods by obtaining biomass estimation correlation of 0.995 with R2=0.991 and RMSE=45.358 g. This result increases the precision in the biomass estimation by around 62.43% compared to previous works.

Scaling-Based Two-Step Reconstruction in Full Polarization-Compressed Hyperspectral Imaging

Polarized hyperspectral images can reflect the rich physicochemical characteristics of targets. Meanwhile, the contained plentiful information also brings great challenges to signal processing. Although compressive sensing theory provides a good idea for image processing, the simplified compression imaging system has difficulty in reconstructing full polarization information. Focused on this problem, we propose a two-step reconstruction method to handle polarization characteristics of different scales progressively. This paper uses a quarter-wave plate and a liquid crystal tunable filter to achieve full polarization compression and hyperspectral imaging. According to their numerical features, the Stokes parameters and their modulation coefficients are simultaneously scaled. The first Stokes parameter is reconstructed in the first step based on compressive sensing. Then, the last three Stokes parameters with similar order of magnitude are reconstructed in the second step based on previous results. The simulation results show that the two-step reconstruction method improves the reconstruction accuracy by 7.6 dB for the parameters that failed to be reconstructed by the non-optimized method, and reduces the reconstruction time by 8.25 h without losing the high accuracy obtained by the current optimization method. This feature scaling method provides a reference for the fast and high-quality reconstruction of physical quantities with obvious numerical differences.