Comparison and Combination of Thermal, Fluorescence, and Hyperspectral Imaging for Monitoring Fusarium Head Blight of Wheat on Spikelet Scale

Optical sensors have shown high capabilities to improve the detection and monitoring of plant disease development. This study was designed to compare the feasibility of different sensors to characterize Fusarium head blight (FHB) caused by Fusarium graminearum and Fusarium culmorum. Under controlled conditions, time-series measurements were performed with infrared thermography (IRT), chlorophyll fluorescence imaging (CFI), and hyperspectral imaging (HSI) starting 3 days after inoculation (dai). IRT allowed the visualization of temperature differences within the infected spikelets beginning 5 dai. At the same time, a disorder of the photosynthetic activity was confirmed by CFI via maximal fluorescence yields of spikelets (Fm) 5 dai. Pigment-specific simple ratio PSSRa and PSSRb derived from HSI allowed discrimination between Fusarium-infected and non-inoculated spikelets 3 dai. This effect on assimilation started earlier and was more pronounced with F. graminearum. Except the maximum temperature difference (MTD), all parameters derived from different sensors were significantly correlated with each other and with disease severity (DS). A support vector machine (SVM) classification of parameters derived from IRT, CFI, or HSI allowed the differentiation between non-inoculated and infected spikelets 3 dai with an accuracy of 78, 56 and 78%, respectively. Combining the IRT-HSI or CFI-HSI parameters improved the accuracy to 89% 30 dai.

Download Full-text

Using UAV-Based Hyperspectral Imagery to Detect Winter Wheat Fusarium Head Blight

Remote Sensing ◽

10.3390/rs13153024 ◽

2021 ◽

Vol 13 (15) ◽

pp. 3024

Author(s):

Huiqin Ma ◽

Wenjiang Huang ◽

Yingying Dong ◽

Linyi Liu ◽

Anting Guo

Keyword(s):

Winter Wheat ◽

Fusarium Head Blight ◽

Hyperspectral Imagery ◽

Spectral Feature ◽

Support Vector ◽

Detection Accuracy ◽

Feature Combination ◽

Field Scale ◽

Head Blight ◽

Detection Model

Fusarium head blight (FHB) is a major winter wheat disease in China. The accurate and timely detection of wheat FHB is vital to scientific field management. By combining three types of spectral features, namely, spectral bands (SBs), vegetation indices (VIs), and wavelet features (WFs), in this study, we explore the potential of using hyperspectral imagery obtained from an unmanned aerial vehicle (UAV), to detect wheat FHB. First, during the wheat filling period, two UAV-based hyperspectral images were acquired. SBs, VIs, and WFs that were sensitive to wheat FHB were extracted and optimized from the two images. Subsequently, a field-scale wheat FHB detection model was formulated, based on the optimal spectral feature combination of SBs, VIs, and WFs (SBs + VIs + WFs), using a support vector machine. Two commonly used data normalization algorithms were utilized before the construction of the model. The single WFs, and the spectral feature combination of optimal SBs and VIs (SBs + VIs), were respectively used to formulate models for comparison and testing. The results showed that the detection model based on the normalized SBs + VIs + WFs, using min–max normalization algorithm, achieved the highest R2 of 0.88 and the lowest RMSE of 2.68% among the three models. Our results suggest that UAV-based hyperspectral imaging technology is promising for the field-scale detection of wheat FHB. Combining traditional SBs and VIs with WFs can improve the detection accuracy of wheat FHB effectively.

Download Full-text

Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural network

Computers and Electronics in Agriculture ◽

10.1016/j.compag.2021.106483 ◽

2021 ◽

Vol 190 ◽

pp. 106483

Author(s):

Shizhuang Weng ◽

Kaixuan Han ◽

Zhaojie Chu ◽

Gongqin Zhu ◽

Cunchuan Liu ◽

...

Keyword(s):

Neural Network ◽

Fusarium Head Blight ◽

Hyperspectral Imaging ◽

Convolution Neural Network ◽

Head Blight ◽

Wheat Kernels

Download Full-text

Chemotype and aggressiveness evaluation of Fusarium graminearum and Fusarium culmorum isolates from wheat fields in Wisconsin

Plant Disease ◽

10.1094/pdis-06-20-1376-re ◽

2021 ◽

Author(s):

Brian Mueller ◽

Carol Groves ◽

Damon L. Smith

Keyword(s):

Growth Rate ◽

Fusarium Head Blight ◽

Fusarium Graminearum ◽

Fusarium Culmorum ◽

Head Blight ◽

Growing Seasons ◽

Progress Curve ◽

Sporulation Capacity ◽

Derivatives Of

Fusarium graminearum commonly causes Fusarium head blight (FHB) on wheat, barley, rice, and oats. Fusarium graminearum produces nivalenol and deoxynivalenol (DON) and forms derivatives of DON based on its acetylation sites. The fungus is profiled into chemotypes based on DON derivative chemotypes (3 acetyldeoxynivalenol (3ADON) chemotype; 15 acetyldeoxynivalenol (15ADON) chemotype) and/or the nivalenol (NIV) chemotype. The current study assessed the Fusarium population found on wheat and the chemotype profile of the isolates collected from 2016 and 2017 in Wisconsin. Fusarium graminearum was isolated from all locations sampled in both 2016 and 2017. Fusarium culmorum was isolated only from Door County in 2016. Over both growing seasons, 91% of isolates were identified as the 15ADON chemotype while 9% of isolates were identified as the 3ADON chemotype. Aggressiveness was quantified by area under disease progress curve (AUDPC). The isolates with the highest AUDPC values were from the highest wheat producing cropping districts in the state. Deoxynivalenol production in grain and sporulation and growth rate in vitro were compared to aggressiveness in the greenhouse. Our results showed that 3ADON isolates in Wisconsin were among the highest in sporulation capacity, growth rate, and DON production in grain. However, there were no significant differences in aggressiveness between the 3ADON and 15ADON isolates. The results of this research detail the baseline frequency and distribution of 3ADON and 15ADON chemotypes observed in Wisconsin. Chemotype distributions within populations of F. graminearum in Wisconsin should continue to be monitored in the future.

Download Full-text

The Influence of the Dilution Rate on the Aggressiveness of Inocula and the Expression of Resistance against Fusarium Head Blight in Wheat

Plants ◽

10.3390/plants9080943 ◽

2020 ◽

Vol 9 (8) ◽

pp. 943 ◽

Cited By ~ 1

Author(s):

Beata Toth ◽

Andrea Gyorgy ◽

Monika Varga ◽

Akos Mesterhazy

Keyword(s):

Fusarium Head Blight ◽

Dilution Rate ◽

Fusarium Graminearum ◽

Fusarium Culmorum ◽

Disease Index ◽

Head Blight ◽

Important Trait

In previous research, conidium concentrations varying between 10,000 and 1,000,000/mL have not been related to any aggressiveness test. Therefore, two Fusarium graminearum and two Fusarium culmorum isolates were tested in the field on seven genotypes highly differing in resistance at no dilution, and 1:1, 1:2, 1:4, 1:8, and 1:16 dilutions in two years (2013 and 2014). The isolates showed different aggressiveness, which changed significantly at different dilution rates for disease index (DI), Fusarium-damaged kernels (FDK), and deoxynivalenol (DON). The traits also had diverging responses to the infection. The effect of the dilution could not be forecasted. The genotype ranks also varied. Dilution seldomly increased aggressiveness, but often lower aggressiveness occurred at high variation. The maximum and minimum values varied between 15% and 40% for traits and dilutions. The reductions between the non-diluted and diluted values (total means) for DI ranged from 6% and 33%, for FDK 8.3–37.7%, and for DON 5.8–44.8%. The most sensitive and most important trait was DON. The introduction of the aggressiveness test provides improved regulation compared to the uncontrolled manipulation of the conidium concentration. The use of more isolates significantly increases the credibility of phenotyping in genetic and cultivar registration studies.

Download Full-text

Resistance to Fusarium head blight in spring barley

Czech Journal of Genetics and Plant Breeding ◽

10.17221/129/2010-cjgpb ◽

2011 ◽

Vol 47 (No. 2) ◽

pp. 58-63 ◽

Cited By ~ 5

Author(s):

J. Chrpová ◽

V. Šíp ◽

L. Štočková ◽

L. Stemberková ◽

L. Tvarůžek

Keyword(s):

Fusarium Head Blight ◽

Spring Barley ◽

Fusarium Culmorum ◽

Grain Weight ◽

Head Blight ◽

The Czech Republic ◽

Disease Symptoms ◽

Barley Cultivars ◽

Yield And Quality ◽

Medium Resistance

Fusarium head blight (FHB) is a fungal disease causing substantial yield and quality losses in barley. Genetic variation in deoxynivalenol (DON) content and and important yield traits in response to FHB were studied in 44 spring barley cultivars for two years following artificial inoculation with Fusarium culmorum under field conditions. The analysis of variance revealed that the largest effect on DON content and simultaneously on the reduction of thousand grain weight and grain weight per spike were due to the environmental conditions of the year, while the visual disease symptoms depended on the cultivars to a larger extent. All these traits were significantly interrelated. The most resistant cultivars Murasski mochi, Nordic, Krasnodarskij 35, Krasnodarskij 95, Nordus, and Usurijskij 8, together with the resistant check Chevron, showed the lowest DON content, the lowest expression of disease symptoms and the lowest reduction of TGW and GWS. However, most spring barley cultivars registered in the Czech Republic in recent years expressed susceptibility or medium resistance and were considerably affected by the disease. This increases the importance of breeding barley for resistance to FHB.

Download Full-text

Study of Resistance of Common Winter Wheat Lines to the Fusarium Head Blight (Fusarium Culmorum)

International Journal of Innovative Approaches in Agricultural Research ◽

10.29329/ijiaar.2018.151.3 ◽

2018 ◽

Vol 2 (3) ◽

pp. 167-176

Author(s):

Evgeniy Dimitrov ◽

◽

Zlatina Peycheva Uhr ◽

Blagoy Andonov ◽

Nikolaya Velcheva ◽

...

Keyword(s):

Winter Wheat ◽

Fusarium Head Blight ◽

Fusarium Culmorum ◽

Head Blight ◽

Wheat Lines

Download Full-text

Detection of Fusarium Head Blight in Wheat Ears Using Continuous Wavelet Analysis and PSO-SVM

Agriculture ◽

10.3390/agriculture11100998 ◽

2021 ◽

Vol 11 (10) ◽

pp. 998

Author(s):

Linsheng Huang ◽

Kang Wu ◽

Wenjiang Huang ◽

Yingying Dong ◽

Huiqin Ma ◽

...

Keyword(s):

Wavelet Analysis ◽

Fusarium Head Blight ◽

Detection Method ◽

Support Vector ◽

Spectral Features ◽

Continuous Wavelet ◽

Head Blight ◽

Detection Model ◽

Svm Algorithm ◽

Wavelet Features

Fusarium head blight, caused by a fungus, can cause quality deterioration and severe yield loss in wheat. It produces highly toxic deoxynivalenol, which is harmful to human and animal health. In order to quickly and accurately detect the severity of fusarium head blight, a method of detecting the disease using continuous wavelet analysis and particle swarm optimization support vector machines (PSO-SVM) is proposed in this paper. First, seven wavelet features for fusarium head blight detection were extracted using continuous wavelet analysis based on the hyperspectral reflectance of wheat ears. In addition, 16 traditional spectral features were selected using correlation analysis, including two continuous removal transformed spectral features, six differential spectral features, and eight vegetation indices. Finally, wavelet features and traditional spectral features were used as input features to construct fusarium head blight detection models in combination with the PSO-SVM algorithm, and the results were compared with those obtained using random forest (RF) and a back propagation neural network (BPNN). The results show that, under the same feature variables, the PSO-SVM detection method gave an overall higher accuracy than the BPNN detection method, while the overall accuracy of the RF detection model was the lowest. The overall accuracy of the RF, BPNN and PSO-SVM detection models with wavelet features was higher by 3.7%, 2.9% and 8.3% compared to the corresponding methodological models with traditional spectral features. The detection model with wavelet features combining the PSO-SVM algorithm gave the highest overall accuracies (93.5%) and kappa coefficients (0.903) in the six monitoring models. These results suggest that the PSO-SVM algorithm combined with continuous wavelet analysis can significantly improve the accuracy of fusarium head blight detection on the wheat ears scale.

Download Full-text

Classification of Rice and Starch Flours by Using Multiple Hyperspectral Imaging Systems and Chemometric Methods

Applied Sciences ◽

10.3390/app10196724 ◽

2020 ◽

Vol 10 (19) ◽

pp. 6724

Author(s):

Youngwook Seo ◽

Ahyeong Lee ◽

Balgeum Kim ◽

Jongguk Lim

Keyword(s):

Discriminant Analysis ◽

Hyperspectral Imaging ◽

Partial Least Square ◽

Hyperspectral Images ◽

Classification Model ◽

Support Vector ◽

Chemometric Methods ◽

Infrared Wavelength ◽

Linear Discriminant

(1) Background: The general use of food-processing facilities in the agro-food industry has increased the risk of unexpected material contamination. For instance, grain flours have similar colors and shapes, making their detection and isolation from each other difficult. Therefore, this study is aimed at verifying the feasibility of detecting and isolating grain flours by using hyperspectral imaging technology and developing a classification model of grain flours. (2) Methods: Multiple hyperspectral images were acquired through line scanning methods from reflectance of visible and near-infrared wavelength (400–1000 nm), reflectance of shortwave infrared wavelength (900–1700 nm), and fluorescence (400–700 nm) by 365 nm ultraviolet (UV) excitation. Eight varieties of grain flours were prepared (rice: 4, starch: 4), and the particle size and starch damage content were measured. To develop the classification model, four multivariate analysis methods (linear discriminant analysis (LDA), partial least-square discriminant analysis, support vector machine, and classification and regression tree) were implemented with several pre-processing methods, and their classification results were compared with respect to accuracy and Cohen’s kappa coefficient obtained from confusion matrices. (3) Results: The highest accuracy was achieved as 97.43% through short-wavelength infrared with normalization in the spectral domain. The submission of the developed classification model to the hyperspectral images showed that the fluorescence method achieves the highest accuracy of 81% using LDA. (4) Conclusions: In this study, the potential of non-destructive classification of rice and starch flours using multiple hyperspectral modalities and chemometric methods were demonstrated.

Download Full-text

Fast Detection of Sclerotinia Sclerotiorum on Oilseed Rape Leaves Using Low-Altitude Remote Sensing Technology

Sensors ◽

10.3390/s18124464 ◽

2018 ◽

Vol 18 (12) ◽

pp. 4464 ◽

Cited By ~ 3

Author(s):

Feng Cao ◽

Fei Liu ◽

Han Guo ◽

Wenwen Kong ◽

Chu Zhang ◽

...

Keyword(s):

Remote Sensing ◽

Oilseed Rape ◽

Sclerotinia Sclerotiorum ◽

Classification Accuracy ◽

Maximum Temperature ◽

Support Vector ◽

Simulation Platform ◽

Maximum Temperature Difference ◽

Thermal Images ◽

Low Altitude

Sclerotinia sclerotiorum, one of the major diseases infecting oilseed rape leaves, has seriously affected crop yield and quality. In this study, an indoor unmanned aerial vehicle (UAV) low-altitude remote sensing simulation platform was built for disease detection. Thermal, multispectral and RGB images were acquired before and after being artificially inoculated with Sclerotinia sclerotiorum on oilseed rape leaves. New image registration and fusion methods based on scale-invariant feature transform (SIFT) were presented to construct a fused database using multi-model images. The changes of temperature distribution in different sections of infected areas were analyzed by processing thermal images, the maximum temperature difference (MTD) on a single leaf reached 1.7 degrees Celsius 24 h after infection. Four machine learning models were established using thermal images and fused images respectively, including support vector machine (SVM), random forest (RF), K-nearest neighbor (KNN) and naïve Bayes (NB). The results demonstrated that the classification accuracy was improved by 11.3% after image fusion, and the SVM model obtained a classification accuracy of 90.0% on the task of classifying disease severity. The overall results indicated the UAV low-altitude remote sensing simulation platform equipped with multi-sensors could be used to early detect Sclerotinia sclerotiorum on oilseed rape leaves.

Download Full-text