AUTHOR=Das Choudhury Sruti , Guadagno Carmela Rosaria , Bashyam Srinidhi , Mazis Anastasios , Ewers Brent E. , Samal Ashok , Awada Tala 

TITLE=Stress phenotyping analysis leveraging autofluorescence image sequences with machine learning

JOURNAL=Frontiers in Plant Science

VOLUME=15

YEAR=2024

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2024.1353110

DOI=10.3389/fpls.2024.1353110

ISSN=1664-462X

ABSTRACT=<sec><title>Background</title><p>Autofluorescence-based imaging has the potential to non-destructively characterize the biochemical and physiological properties of plants regulated by genotypes using optical properties of the tissue. A comparative study of stress tolerant and stress susceptible genotypes of <italic>Brassica rapa</italic> with respect to newly introduced stress-based phenotypes using machine learning techniques will contribute to the significant advancement of autofluorescence-based plant phenotyping research.</p></sec><sec><title>Methods</title><p>Autofluorescence spectral images have been used to design a stress detection classifier with two classes, stressed and non-stressed, using machine learning algorithms. The benchmark dataset consisted of time-series image sequences from three <italic>Brassica rapa</italic> genotypes (<italic>CC</italic>, <italic>R500</italic>, and <italic>VT</italic>), extreme in their morphological and physiological traits captured at the high-throughput plant phenotyping facility at the University of Nebraska-Lincoln, USA. We developed a set of machine learning-based classification models to detect the percentage of stressed tissue derived from plant images and identified the best classifier. From the analysis of the autofluorescence images, two novel stress-based image phenotypes were computed to determine the temporal variation in stressed tissue under progressive drought across different genotypes, i.e., the average percentage stress and the moving average percentage stress.</p></sec><sec><title>Results</title><p>The study demonstrated that both the computed phenotypes consistently discriminated against stressed <italic>versus</italic> non-stressed tissue, with oilseed type (<italic>R500</italic>) being less prone to drought stress relative to the other two <italic>Brassica rapa</italic> genotypes (<italic>CC</italic> and <italic>VT</italic>).</p></sec><sec><title>Conclusion</title><p>Autofluorescence signals from the 365/400 nm excitation/emission combination were able to segregate genotypic variation during a progressive drought treatment under a controlled greenhouse environment, allowing for the exploration of other meaningful phenotypes using autofluorescence image sequences with significance in the context of plant science.</p></sec>