Dataset Information

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

ABSTRACT: 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.

SUBMITTER: Bai X

PROVIDER: S-EPMC9627309 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Bai Xiulin X Zhou Yujie Y Feng Xuping X Tao Mingzhu M Zhang Jinnuo J Deng Shuiguang S Lou Binggan B Yang Guofeng G Wu Qingguan Q Yu Li L Yang Yong Y He Yong Y

Frontiers in plant science 20221019

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 d ...[more]

PMID: 36340356

Similar Datasets

Project description:Potential biological control agents for two major rice diseases, sheath blight and bacterial panicle blight, were isolated from rice plants in this study. Rice-associated bacteria (RABs) isolated from rice plants grown in the field were tested for their antagonistic activities against the rice pathogens, Rhizoctonia solani and Burkholderia glumae, which cause sheath blight and bacterial panicle blight, respectively. Twenty-nine RABs were initially screened based on their antagonistic activities against both R. solani and B. glumae. In follow-up retests, 26 RABs of the 29 RABs were confirmed to have antimicrobial activities, but the rest three RABs did not reproduce any observable antagonistic activity against R. solani or B. glumae. According to16S rDNA sequence identity, 12 of the 26 antagonistic RABs were closest to Bacillus amyloliquefaciens, while seven RABs were to B. methylotrophicus and B, subtilis, respectively. The 16S rDNA sequences of the three non-antagonistic RABs were closest to Lysinibacillus sphaericus (RAB1 and RAB12) and Lysinibacillus macroides (RAB5). The five selected RABs showing highest antimicrobial activities (RAB6, RAB9, RAB16, RAB17S, and RAB18) were closest to B. amyloliquefaciens in DNA sequence of 16S rDNA and gyrB, but to B. subtilis in that of recA. These RABs were observed to inhibit the sclerotial germination of R. solani on potato dextrose agar and the lesion development on detached rice leaves by artificial inoculation of R. solani. These antagonistic RABs also significantly suppressed the disease development of sheath blight and bacterial panicle blight in a field condition, suggesting that they can be potential biological control agents for these rice diseases. However, these antagonistic RABs showed diminished disease suppression activities in the repeated field trial conducted in the following year probably due to their reduced antagonistic activities to the pathogens during the long-term storage in -70C, suggesting that development of proper storage methods to maintain antagonistic activity is as crucial as identification of new biological control agents.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets