Salinity stress has significant adverse effects on crop productivity and yield. The primary goal of this study was to quantitatively rank salt tolerance in wheat using hyperspectral imaging. Four wheat lines were assayed in a hydroponic system with control and salt treatments (0 and 200mM NaCl). Hyperspectral images were captured one day after salt application when there were no visual symptoms. Subsequent to necessary preprocessing tasks, two endmembers, each representing one of the treatment, were identified in each image using successive volume maximization. To simplify image analysis and interpretation, similarity of all pixels to the salt endmember was calculated by a technique proposed in this study, referred to as vector-wise similarity measurement. Using this approach allowed high-dimensional hyperspectral images to be reduced to one-dimensional gray-scale images while retaining all relevant information. Two methods were then utilized to analyze the gray-scale images: minimum difference of pair assignments and Bayesianmethod. The rankings of bothmethods were similar and consistent with the expected ranking obtained by conventional phenotyping experiments and historical evidence of salt tolerance. This research highlights the application of machine learning in hyperspectral image analysis for phenotyping of plants in a quantitative, interpretable, and non-invasive manner.
|Original language||English (US)|
|Journal||Asian Journal of Pharmaceutical and Clinical Research|
|State||Published - 2018|
Bibliographical noteFunding Information:
The authors gratefully acknowledge the funding from the United States Department of Agriculture-Agricultural Research Service, the National Science Foundation (IOS 1025881 and IOS 1361554), and Minnesota Agricultural Experiment Station. Financial support from the MnDRIVE Initiative provided as graduate student funding is also much appreciated. We thank Dr. Shuhei Nasuda from Kyoto University and the National BioResource Project of Japan for providing the seeds of wheat alloplasmic lines. We also would like to thank Mr. Alireza Mahdavian, Mr. Chuanqi Xie, and Mrs. Parisa Kafash for their help in setting up the imaging system and collecting data, and special thanks to Mr. Tyler Nigon for his valuable comments in the manuscript revision. We would also like to thank Dr. Felipe Acosta Archila for guidance on statistical analyses of biomass data.
The authors gratefully acknowledge the funding from the United States Department of Agriculture-Agricultural Research Service, the National Science Foundation (IOS 1025881 and IOS 1361554), and Minnesota Agricultural Experiment Station. Financial support from the MnDRIVE Initiative provided as graduate student funding is also much appreciated. We thank
© 2018 Moghimi, Yang, Miller, Kianian and Marchetto.
- Bayesian inference
- Histogram distance
- Hyperspectral imaging
- Image processing
- Machine learning
- Plant phenotyping
- Salt stress