Early detection of drought stress in Arabidopsis thaliana utilsing a portable hyperspectral imaging setup

Close-range hyperspectral imaging (HSI) of plants is now a potential tool for non-destructive extraction of plant functional traits. A major motivation is the plant phenotyping related applications where different plant genotypes are explored for different environmental conditions. HSI of Arabidopsis thaliana is of particular importance as it is a model organism in plant biology. In the present work, a portable HSI setup has been used for the monitoring of a set of 6 Arabidopsis thaliana plants. The plants were monitored under controlled watering conditions where 3 plants were watered as normal and the other 3 plants were given 50% of the normal volume of water. The images were pre-processed utilising the standard normal variate (SNV) and changes over time were evaluated using unsupervised clustering over the time series. The results showed an early detection of stress from day 4 onwards compared to the commonly used normalised difference vegetation index (NDVI), which provided detection from day 9