Analysis of hyperspectral images for detection of drought stress and recovery in maize plants in a high-throughput phenotyping platform

•The use of the standard normal variate (SNV) to eliminate linear effects.•The use of a clustering approach to remove pixels that exhibit nonlinear effects.•The development of a data-driven spectral analysis method to charecterize plant growth dynamics.•The validation the proposed method by a large-scale study of water-stress and recovery of maize plants.