A Web Based Solution to Detect Rice Leaf Blast Disease using Convolutional Neural Network

Multiple constraints affect rice yields and global production in West Africa. Among these constraints are viral, bacterial and fungal pathogens. We aimed to describe the spatiotemporal patterns of occurrence and incidence of multiple rice diseases in farmers’ fields in contrasting rice growing systems in western Burkina Faso. For this purpose, we selected a set of three pairs of sites, each comprising an irrigated area and a neighboring rainfed lowland, and studied them over four consecutive years. We first performed interviews with the rice farmers to better characterize the management practices at the different sites. This study revealed that the transplanting of rice and the possibility of growing rice twice a year are restricted to irrigated areas, while other practices, such as the use of registered rice cultivars, fertilization and pesticides, are not specific but differ between the two rice growing systems. Then, we performed symptom observations at these study sites to monitor the following four diseases: yellow mottle disease, Bacterial Leaf Streak (BLS), rice leaf blast and brown spot. The infection rates were found to be higher in irrigated areas than in rainfed lowlands, both when analyzing all observed symptoms together (any of the four diseases) and when specifically considering each of the two diseases: BLS and rice leaf blast. Brown spot was particularly prevalent in all six study sites, while yellow mottle disease was particularly structured geographically. Various diseases were frequently found together in the same field (co-occurrence) or even on the same plant (coinfection), especially in irrigated areas.

Get full-text (via PubEx)

Classification of Rice Leaf Blast Severity Using Hyperspectral Imaging

10.21203/rs.3.rs-1164957/v1 ◽

2021 ◽

Author(s):

Guosheng Zhang ◽

Tongyu Xu ◽

Youwen Tian ◽

Shuai Feng ◽

Dongxue Zhao ◽

...

Keyword(s):

Hyperspectral Imaging ◽

Spectral Reflectance ◽

Support Vector ◽

Growth Stages ◽

Leaf Blast ◽

Full Spectrum ◽

Rice Leaf ◽

Svm Model ◽

Rice Leaf Blast ◽

Different Growth Stages

Abstract Background: Hyperspectral imaging is an emerging technology applied in plant disease research, including disease detection, multiple disease identification, disease severity assessment, and disease resistance evaluation. Rice leaf blast is prevalent all over the world and is a serious threat to rice yield and quality. In this paper, the standard deviation (STD) of the spectral reflectance of whole leaves was calculated and a support vector machine (SVM) model was built to classify the degree of rice leaf blast at different growth stages.Results: The classification accuracy of the full-spectrum-based SVM model at jointing stage, booting stage and heading stage was 94.44%, 81.58% and 80.48%, respectively. The corresponding macro recall values were 0.9714, 0.715 and 0.79. The average STD of the spectral reflectance of the whole leaf differed not only within samples with different disease grades, but also those with the same disease level. Conclusion: The STD of the spectral reflectance of whole leaf could be utilized to classify the rice leaf blast degree at different growth stages. The classification method was derived from physiological phenomena that were visible to the naked eye, making it more intuitive and convincing.

Get full-text (via PubEx)