Early Detection of Stripe Rust in Winter Wheat Using Deep Residual Neural Networks

Stripe rust (Pst) is a major disease of wheat crops leading untreated to severe yield losses. The use of fungicides is often essential to control Pst when sudden outbreaks are imminent. Sensors capable of detecting Pst in wheat crops could optimize the use of fungicides and improve disease monitoring in high-throughput field phenotyping. Now, deep learning provides new tools for image recognition and may pave the way for new camera based sensors that can identify symptoms in early stages of a disease outbreak within the field. The aim of this study was to teach an image classifier to detect Pst symptoms in winter wheat canopies based on a deep residual neural network (ResNet). For this purpose, a large annotation database was created from images taken by a standard RGB camera that was mounted on a platform at a height of 2 m. Images were acquired while the platform was moved over a randomized field experiment with Pst-inoculated and Pst-free plots of winter wheat. The image classifier was trained with 224 × 224 px patches tiled from the original, unprocessed camera images. The image classifier was tested on different stages of the disease outbreak. At patch level the image classifier reached a total accuracy of 90%. To test the image classifier on image level, the image classifier was evaluated with a sliding window using a large striding length of 224 px allowing for fast test performance. At image level, the image classifier reached a total accuracy of 77%. Even in a stage with very low disease spreading (0.5%) at the very beginning of the Pst outbreak, a detection accuracy of 57% was obtained. Still in the initial phase of the Pst outbreak with 2 to 4% of Pst disease spreading, detection accuracy with 76% could be attained. With further optimizations, the image classifier could be implemented in embedded systems and deployed on drones, vehicles or scanning systems for fast mapping of Pst outbreaks.

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

Fungicide efficacy and the impact of stripe rust on spring and winter wheat in South Africa

South African Journal of Plant and Soil ◽

10.1080/02571862.2003.10634898 ◽

2003 ◽

Vol 20 (1) ◽

pp. 11-17 ◽

Cited By ~ 6

Author(s):

W. H.P. Boshoff ◽

Z. A. Pretorius ◽

B. D. van Niekerk

Keyword(s):

South Africa ◽

Winter Wheat ◽

Stripe Rust ◽

Fungicide Efficacy ◽

The Impact

Download Full-text

Classification and Regression Models for Genomic Selection of Skewed Phenotypes: A Case for Disease Resistance in Winter Wheat (Triticum aestivum L.)

10.1101/2021.12.16.472985 ◽

2021 ◽

Author(s):

Lance F Merrick ◽

Dennis N Lozada ◽

Xianming Chen ◽

Arron H Carter

Keyword(s):

Support Vector Machine ◽

Winter Wheat ◽

Genomic Selection ◽

Stripe Rust ◽

Regression Models ◽

Prediction Models ◽

Support Vector ◽

Classification Models ◽

Breeding Lines ◽

Classification And Regression

Most genomic prediction models are linear regression models that assume continuous and normally distributed phenotypes, but responses to diseases such as stripe rust (caused by Puccinia striiformis f. sp. tritici) are commonly recorded in ordinal scales and percentages. Disease severity (SEV) and infection type (IT) data in germplasm screening nurseries generally do not follow these assumptions. On this regard, researchers may ignore the lack of normality, transform the phenotypes, use generalized linear models, or use supervised learning algorithms and classification models with no restriction on the distribution of response variables, which are less sensitive when modeling ordinal scores. The goal of this research was to compare classification and regression genomic selection models for skewed phenotypes using stripe rust SEV and IT in winter wheat. We extensively compared both regression and classification prediction models using two training populations composed of breeding lines phenotyped in four years (2016-2018, and 2020) and a diversity panel phenotyped in four years (2013-2016). The prediction models used 19,861 genotyping-by-sequencing single-nucleotide polymorphism markers. Overall, square root transformed phenotypes using rrBLUP and support vector machine regression models displayed the highest combination of accuracy and relative efficiency across the regression and classification models. Further, a classification system based on support vector machine and ordinal Bayesian models with a 2-Class scale for SEV reached the highest class accuracy of 0.99. This study showed that breeders can use linear and non-parametric regression models within their own breeding lines over combined years to accurately predict skewed phenotypes.

Download Full-text

Spectral differences of opposite sides of stripe rust infested winter wheat leaves using ASD's Leaf Clip

2012 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss.2012.6352090 ◽

2012 ◽

Cited By ~ 1

Author(s):

Jinling Zhao ◽

Lin Yuan ◽

Juhua Luo ◽

Shizhou Du ◽

Linsheng Huang ◽

...

Keyword(s):

Winter Wheat ◽

Stripe Rust ◽

Wheat Leaves

Download Full-text

Environmental Conditions Associated with Stripe Rust in Kansas Winter Wheat

Plant Disease ◽

10.1094/pdis-11-15-1321-re ◽

2016 ◽

Vol 100 (11) ◽

pp. 2306-2312 ◽

Cited By ~ 5

Author(s):

B. S. Grabow ◽

D. A. Shah ◽

E. D. DeWolf

Keyword(s):

Soil Moisture ◽

Winter Wheat ◽

Stripe Rust ◽

Yield Loss ◽

Initial Step ◽

Disease Forecasting ◽

Estimation Equations ◽

Forecasting System ◽

Moisture Conditions ◽

General Estimation

Stripe rust has reemerged as a problematic disease in Kansas wheat. However, there are no stripe rust forecasting models specific to Kansas wheat production. Our objective was to identify environmental variables associated with stripe rust epidemics in Kansas winter wheat as an initial step in the longer-term goal of developing predictive models for stripe rust to be used within the state. Mean yield loss due to stripe rust on susceptible varieties was estimated from 1999 to 2012 for each of the nine Kansas crop reporting districts (CRD). A CRD was classified as having experienced a stripe rust epidemic when yield loss due to the disease equaled or exceeded 1%, and a nonepidemic otherwise. Epidemics were further classified as having been moderate or severe if yield loss was 1 to 14% or greater than 14%, respectively. The binary epidemic categorizations were linked to a matrix of 847 variables representing monthly meteorological and soil moisture conditions. Classification trees were used to select variables associated with stripe rust epidemic occurrence and severity (conditional on an epidemic having occurred). Selected variables were evaluated as predictors of stripe rust epidemics within a general estimation equations framework. The occurrence of epidemics within CRD was linked to soil moisture during the fall and winter months. In the spring, severe epidemics were linked to optimal (7 to 12°C) temperatures. Simple environmentally based stripe rust models at the CRD level may be combined with field-level disease observations and an understanding of varietal reaction to stripe rust as part of an operational disease forecasting system in Kansas.

Download Full-text