scholarly journals Toward a Reliable Evaluation of Forecasting Systems for Plant Diseases: A Case Study Using Fusarium Head Blight of Wheat

Plant Disease ◽  
2012 ◽  
Vol 96 (6) ◽  
pp. 889-896 ◽  
Author(s):  
S. Landschoot ◽  
W. Waegeman ◽  
K. Audenaert ◽  
J. Vandepitte ◽  
G. Haesaert ◽  
...  
Keyword(s):  
Fusarium Head Blight ◽  
Cross Validation ◽  
Mean Squared Error ◽  
Plant Diseases ◽  
Coefficient Of Determination ◽  
Linear Regression Models ◽  
Head Blight ◽  
Evaluation Strategies ◽  
The Cross ◽  
Validation Strategy

Despite great efforts to forecast plant diseases, many of the existing systems often fall short in providing farmers with accurate predictions. One of the main problems arises from the existence of year and location effects, so that more advanced procedures are required for evaluating existing systems in an unbiased manner. This paper illustrates the case of Fusarium head blight of winter wheat in Belgium. We present a new cross-validation strategy that enables the evaluation of the predictive performance of a forecasting system for years and locations that are different from the years and locations on which the forecast was developed. Four different cross-validation strategies and five regression techniques are used. The results demonstrated that traditional evaluation strategies are too optimistic in their predictions, whereas the cross-year cross-location validation strategy yielded more realistic outcomes. Using this procedure, the mean squared error increased and the coefficient of determination decreased in predicting disease severity and deoxynivalenol content, suggesting that existing evaluation strategies may generate a substantial optimistic bias. The strongest discrepancies between the cross-validation strategies were observed for multiple linear regression models.

scholarly journals Soybean Yield Estimation and Its Components: A Linear Regression Approach

Agriculture ◽  
2020 ◽  
Vol 10 (8) ◽  
pp. 348
Author(s):  
Marcelo Chan Fu Wei ◽  
José Paulo Molin
Keyword(s):  
Linear Regression ◽  
Mean Squared Error ◽  
Limiting Factors ◽  
Training Dataset ◽  
Coefficient Of Determination ◽  
Validation Dataset ◽  
Learning Approaches ◽  
Linear Regression Models ◽  
Yield Estimation ◽  
Soybean Yield

Soybean yield estimation is either based on yield monitors or agro-meteorological and satellite imagery data, but they present several limiting factors regarding on-farm decision level. Aware that machine learning approaches have been largely applied to estimate soybean yield and the availability of data regarding soybean yield and its components (number of grains (NG) and thousand grains weight (TGW)), there is an opportunity to study their relationships. The objective was to explore the relationships between soybean yield and its components, generate equations to estimate yield and evaluate its prediction accuracy. The training dataset was composed of soybean yield and its components’ data from 2010 to 2019. Linear regression models based on NG, TGW and yield were fitted on the training dataset and applied to a validation dataset composed of 58 on-field collected samples. It was found that globally TGW and NG presented weak (r = 0.50) and strong (r = 0.92) linear relationships with yield, respectively. In addition to that, applying the fitted models to the validation dataset, model based on NG presented the highest accuracy, coefficient of determination (R2) of 0.70, mean absolute error (MAE) of 639.99 kg ha−1 and root mean squared error (RMSE) of 726.67 kg ha−1.

scholarly journals Effectiveness of marker-based selection for Fusarium head blight resistance in spring wheat

2011 ◽  
Vol 47 (Special Issue) ◽  
pp. S123-S129 ◽  
Author(s):  
J. Chrpová ◽  
V. Šíp ◽  
T. Sedláček ◽  
L. Štočková ◽  
O. Veškrna ◽  
...  
Keyword(s):  
Fusarium Head Blight ◽  
Spring Wheat ◽  
Recombinant Inbred Lines ◽  
Wheat Variety ◽  
Fusarium Head Blight Resistance ◽  
Head Blight ◽  
No Donor ◽  
Selection For ◽  
The Cross ◽  
Sumai 3

The effect of selection for two donor-QTL from Fusarium head blight (FHB) resistant spring wheat variety Sumai 3 on the reduction of deoxynivalenol (DON) content and FHB index was evaluated in field trials over two years (2008, 2009) following artificial inoculation with Fusarium culmorum. This study was conducted on populations of recombinant inbred lines derived from two crosses, Sumai 3/Swedget and Sumai 3/SG-S 191-01. DON content and FHB index were significantly reduced in both crosses in the genotype classes with two stacked donor QTL on chromosomes 3B and 5A in comparison to genotype classes with no donor QTL. In the cross Sumai 3/Swedget the selection for QTL alleles from 3B and 5A resulted in a 63.4% reduction in DON content, and a 51.8% reduction in the FHB index. Similarly, there was a 35.9% and 31.9% reduction, respectively, in the cross Sumai 3/SG-S 191-01. The single effect of the donor-QTL allele from 3B was significant only in the cross Sumai 3/Swedjet. The presence or absence of awns affected both DON content and FHB index in both populations, but was only significantly in the cross Sumai 3/SG-S 191-01. In this cross the effect of selection for fully awned genotypes was particularly evident on a reduction of both DON and FHB index in classes with neither donor QTL, or the 3B QTL. However, the data indicate that the “awnedness” effect on FHB resistance may be highly variable and is probably greater on reducing FHB symptoms than on DON content. The results confirmed that marker-based introgression of resistance QTLs on chromosomes 3B and 5A in traditional breeding materials can enrich populations for resistance types, but it was also shown that the effect of marker-based selection need not be large in all crosses and a similar effect can probably be reached by indirect selection for some FHB-related traits.

scholarly journals Genetics of Fusarium head blight resistance in three wheat genotypes

2019 ◽  
Vol 79 (3) ◽  
Author(s):  
Satish . Kumar ◽  
M. S. Saharan ◽  
Vipin . Panwar ◽  
Ravish . Chatrath ◽  
G. P. Singh
Keyword(s):  
Fusarium Head Blight ◽  
Animal Health ◽  
Fusarium Head Blight Resistance ◽  
Plant Diseases ◽  
Complex Nature ◽  
Head Blight ◽  
Sources Of Resistance ◽  
Chinese Wheat Cultivar ◽  
Chinese Wheat ◽  
Sumai 3

Fusarium head blight (FHB) is global concern as recent outbreaks reported in Canada, Europe, Asia, Australia and South America. The disease has emerged as one of the most important plant diseases worldwide in 21st century. One of the major threats posed by FHB fungus is the mycotoxin production which is harmful to human and animal health. Development of disease resistant cultivars is the only effective method for managing the disease. Control of these pathogen / Fusarium spp. is also challenging due to limited sources of known resistance. The famous Chinese wheat cultivar Sumai 3 and Frontana are the main sources of resistance to this disease. For genetic analysis and incorporation of FHB resistance into recently released high yielding wheat cultivars, HD 2967 and DPW 621-50, crosses were made with Sumai 3, Frontana and Aldan. The F2 plants from the crosses HD 2967/Frontana (140), HD 2967/Aldan (150), HD 2967/Sumai 3 (169) and DPW 621-50/Sumai 3 (182) were screened for resistance under controlled conditions. Disease score was recorded to identify resistant, moderately resistant and susceptible plants. The genetic ratios for resistance to FHB indicated a complex nature of resistance in all the three donors.

scholarly journals Green-Synthesization of Silver Nanoparticles Using Endophytic Bacteria Isolated from Garlic and Its Antifungal Activity against Wheat Fusarium Head Blight Pathogen Fusarium graminearum

Nanomaterials ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 219 ◽  
Author(s):  
Ezzeldin Ibrahim ◽  
Muchen Zhang ◽  
Yang Zhang ◽  
Afsana Hossain ◽  
Wen Qiu ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Silver Nanoparticles ◽  
Antifungal Activity ◽  
Fusarium Head Blight ◽  
Fusarium Graminearum ◽  
Plant Diseases ◽  
Head Blight ◽  
Mycelium Growth ◽  
Biosynthesized Agnps

Nanoparticles are expected to play a vital role in the management of future plant diseases, and they are expected to provide an environmentally friendly alternative to traditional synthetic fungicides. In the present study, silver nanoparticles (AgNPs) were green synthesized through the mediation by using the endophytic bacterium Pseudomonas poae strain CO, which was isolated from garlic plants (Allium sativum). Following a confirmation analysis that used UV–Vis, we examined the in vitro antifungal activity of the biosynthesized AgNPs with the size of 19.8–44.9 nm, which showed strong inhibition in the mycelium growth, spore germination, the length of the germ tubes, and the mycotoxin production of the wheat Fusarium head blight pathogen Fusarium graminearum. Furthermore, the microscopic examination showed that the morphological of mycelia had deformities and collapsed when treated with AgNPs, causing DNA and proteins to leak outside cells. The biosynthesized AgNPs with strong antifungal activity were further characterized based on analyses of X-ray diffraction, transmission electron microscopy, scanning electron microscopy, EDS profiles, and Fourier transform infrared spectroscopy. Overall, the results from this study clearly indicate that the biosynthesized AgNPs may have a great potential in protecting wheat from fungal infection.

scholarly journals Quantitative Activity Structure Relationship (QSAR) of a Series of Azetidinones Derived from Dapsone by the Method of Density Functional Theory (DFT)

2017 ◽  
Vol 8 (2) ◽  
pp. 55
Author(s):  
Jean Stéphane N’DRI ◽  
Mamadou Guy-Richard KONÉ ◽  
Charles Guillaume KODJO ◽  
Sopi Thomas AFFI ◽  
Ahmont Landry Claude KABLAN ◽  
...  
Keyword(s):  
Escherichia Coli ◽  
Antibacterial Activity ◽  
Dipole Moment ◽  
Standard Deviation ◽  
Density Functional ◽  
Cross Validation ◽  
Molecular Descriptors ◽  
Coefficient Of Determination ◽  
Test Set ◽  
The Cross

This QSAR study, which involved a series of Azetidinones derived from 4,4'-diaminodiphenylsulfone (dapsone), yielded two models based on molecular descriptors and the antibacterial activities Escherichia coli and Staphylococcus aureus.The molecular descriptors were obtained by applying the methods of quantum chemistry at the B3LYP/6-31G (d) level. The statistical indicators of the first model which is a function of the Escherichia coli activity are: the coefficient of determination R<sup>2</sup> equals 0.992, the standard deviation S equals 0.342, the Fischer coefficient F equals 185.088 and the cross-validation coefficient Q<sup>2</sup><sub>CV</sub> equals 0.992. Those of the second model showing the activity of Staphylococcus aureus are: the regression coefficient R<sup>2</sup>= 0.987, a standard deviation S=0.193, the Fischer coefficient F=114.955 and the cross-validation coefficient Q<sup>2</sup><sub>CV</sub>= 0.987. These models have good statistical performances. The quantum descriptors of dipole moment (μ), global softness (σ) and electronegativity (χ) are responsible of the antibacterial activity of the Azetidinones derived from dapsone. In addition, the dipole moment is the priority descriptor for the prediction of the antibacterial activity of the studied compounds. The Eriksson et al. acceptance criteria used for the test set is verified. The values of the dtheo/dexp ratio of the theoretical and experimental activities for the test set tend towards unity.

scholarly journals Presence of the Weakly Pathogenic Fusarium poae in the Fusarium Head Blight Disease Complex Hampers Biocontrol and Chemical Control of the Virulent Fusarium graminearum Pathogen

2021 ◽  
Vol 12 ◽  
Author(s):  
Jiang Tan ◽  
Noémie De Zutter ◽  
Sarah De Saeger ◽  
Marthe De Boevre ◽  
Trang Minh Tran ◽  
...  
Keyword(s):  
Fusarium Head Blight ◽  
Control Strategies ◽  
Fusarium Species ◽  
Plant Diseases ◽  
Streptomyces Rimosus ◽  
Defense System ◽  
Head Blight ◽  
Disease Complex ◽  
Blight Disease ◽  
Multiple Pathogens

Fusarium head blight (FHB) in wheat (Triticum aestivum L.) is caused by a consortium of mutually interacting Fusarium species. In the field, the weakly pathogenic F. poae often thrives on the infection sites of the virulent F. graminearum. In this ecological context, we investigated the efficacy of chemical and biocontrol agents against F. graminearum in wheat ears. For this purpose, one fungicide comprising prothioconazole + spiroxamine and two bacterial biocontrol strains, Streptomyces rimosus LMG 19352 and Rhodococcus sp. R-43120 were tested for their efficacy to reduce FHB symptoms and mycotoxin (deoxynivalenol, DON) production by F. graminearum in presence or absence of F. poae. Results showed that the fungicide and both actinobacterial strains reduced FHB symptoms and concomitant DON levels in wheat ears inoculated with F. graminearum. Where Streptomyces rimosus appeared to have direct antagonistic effects, Rhodococcus and the fungicide mediated suppression of F. graminearum was linked to the archetypal salicylic acid and jasmonic acid defense pathways that involve the activation of LOX1, LOX2 and ICS. Remarkably, this chemical- and biocontrol efficacy was significantly reduced when F. poae was co-inoculated with F. graminearum. This reduced efficacy was linked to a suppression of the plant’s intrinsic defense system and increased levels of DON. In conclusion, our study shows that control strategies against the virulent F. graminearum in the disease complex causing FHB are hampered by the presence of the weakly pathogenic F. poae. This study provides generic insights in the complexity of control strategies against plant diseases caused by multiple pathogens.

scholarly journals Is Disease Intensity a Good Surrogate for Yield Loss or Toxin Contamination? A Case Study with Fusarium Head Blight of Wheat

2020 ◽  
Vol 110 (10) ◽  
pp. 1632-1646
Author(s):  
Laurence V. Madden ◽  
Pierce A. Paul
Keyword(s):  
Fusarium Head Blight ◽  
Yield Loss ◽  
Coefficient Of Determination ◽  
Head Blight ◽  
Toxin Concentration ◽  
Individual Level ◽  
Effect Of Treatment ◽  
Experimental Treatments ◽  
Surrogate Index

Sometimes plant pathologists assess disease intensity when they are primarily interested in other response variables, such as yield loss or toxin concentration in harvested products. In these situations, disease intensity potentially could be considered a surrogate of yield or toxin. A surrogate is a variable which can be used instead of the variable of interest in the evaluation of experimental treatments or in making predictions. Surrogates can be measured earlier, more conveniently, or more cheaply than the variable of primary interest, but the reliability or validity of the surrogate must be shown. We demonstrate ways of quantifying two facets of surrogacy by using a protocol originally developed by Buyse and colleagues for medical research. Coefficient-of-determination type statistics can be used to conveniently assess the strength of surrogacy on a unitless scale. As a case study, we evaluated whether field severity of Fusarium head blight (i.e., FHB index) can be used as a surrogate for yield loss and deoxynivalenol (DON) toxin concentration in harvested wheat grain. Bivariate mixed models and corresponding approximations were fitted to data from 82 uniform fungicide trials conducted from 2008 to 2013. Individual-level surrogacy—for predicting the variable of interest (yield or DON) from the surrogate (index) in plots with the same treatment—was very low. Trial-level surrogacy—for predicting the effect of treatment (e.g., mean difference) for the variable of interest based on the effect of the treatment on the surrogate (index)—was moderate for yield, and only low for DON. Challenges in using disease severity as a surrogate for yield and toxin are discussed.

scholarly journals Isotonic regression analysis of Guzerá cattle growth curves

Revista CERES ◽  
2018 ◽  
Vol 65 (1) ◽  
pp. 24-27 ◽  
Author(s):  
Adriano Rodrigues ◽  
Lucas Monteiro Chaves ◽  
Fabyano Fonseca Silva ◽  
Idalmo Pereira Garcia ◽  
Darlene Ana Souza Duarte ◽  
...  
Keyword(s):  
Goodness Of Fit ◽  
Mean Squared Error ◽  
Least Squares Method ◽  
Age Groups ◽  
Growth Curves ◽  
Generalized Least Squares ◽  
Isotonic Regression ◽  
Coefficient Of Determination ◽  
Linear Regression Models ◽  
Generalized Least Squares Method

ABSTRACT The objective of this study was to apply data transformation via isotonic regression in growth curves studies of Guzerá cattle whose data presented disturbances characterized by decreased body weight in certain age groups. Weight-age data were collected on newly weaned Guzerá males according to the methodology of weight gain tests (WGT) defined by the Brazilian Association of Zebu Breeders (ABCZ). The Logistic, Von Bertalanffy and Gompertz models were fitted to weight-age data using the generalized least squares method for non-linear regression models through the Gauss-Newton algorithm. The proposed transformation based on isotonic regression theory proved to be efficient; and the Logistic model was the best to describe the growth of animals, with a high percentage of convergence (100%) and goodness of fit assessed by the mean squared error (MSE) and the coefficient of determination (R2).

scholarly journals PSXI-22 Prediction quality of cattle behavior traits evaluated through different cross-validation strategies using wearable sensor data and machine learning algorithms

2020 ◽  
Vol 98 (Supplement_4) ◽  
pp. 383-383
Author(s):  
Leonardo Augusto Coelho Ribeiro ◽  
Tiago Bresolin ◽  
Guilherme J M Rosa ◽  
Daniel Rume Casagrande ◽  
Marina De Arruda Camargo Danes ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Accuracy ◽  
Cross Validation ◽  
Grazing Management ◽  
Sensor Data ◽  
Accelerometer Data ◽  
Wearable Sensor ◽  
Prediction Quality ◽  
The Cross ◽  
Validation Strategy

Abstract Wearable sensors have been adopted as an alternative for real-time monitoring of cattle feeding behavior in grazing systems. However, even using machine learning (ML) techniques confounding effects such as cross-validation strategy may inflate the prediction quality. Our objective was to evaluate the effect of different cross-validation strategies on the prediction of grazing activities in cattle using wearable sensor data and ML algorithms. Six Nellore bulls (345 ± 21 kg) had their behavior visually classified as grazing or not-grazing for a period of 15 days. Generalized Linear Model (GLM), Random Forest (RF), and Artificial Neural Network (ANN) were employed to predict behavior (grazing or not-grazing) using 3-axis accelerometer data. For each analytical method, three cross-validation strategies were evaluated: holdout, leave-one-animal-out (LOAO), and leave-one-day-out (LODO). Algorithms were trained using similar dataset sizes (holdout: n = 57,862; LOAO: n = 56,786; LODO: n = 56,672). Regardless of the cross-validation strategy, GLM achieved the worst prediction accuracy (53%) compared to the ML techniques (65% for both RF and ANN). ANN performed slightly better than RF for LOAO (73%) and LODO (64%) cross-validation strategies. The holdout yielded the highest accuracy values for all three ML approaches (GLM: 59%, RF: 76%, and ANN: 74%), followed by LODO (58%) and LOAO (55%). In conclusion, the GLM approach was not adequate to predict grazing behavior, regardless of the cross-validation strategy. The greater prediction accuracy observed for holdout cross-validation may simply indicate a lack of data independence and the presence of carry-over effects from animals and grazing management. Our results suggest that generalizing predictive models to unknown (not used for training) animals or grazing management may incur in poor prediction quality. The results highlight the need for using biological knowledge to define the validation strategy that is closer to the real-life situation.

Sign in / Sign up

Export Citation Format

Share Document