Current phenotyping technology fulfills tasks that are congruent with many “classical” measurements in agronomy or botany. Howerver, despite measuring the same object, data might lack comparability. One challenge is matching growth stages with non-invasive phenotyping data. Scientists at Rothamsted Research used machine learning methods to derive growth stage information in wheat from Field Scanalyzer-captured images.
Sadeghi-Tehran, Pouria; Sabermanesh, Kasra; Virlet, Nicolas; Hawkesford, Malcolm J. (2017): Automated Method to Determine Two Critical Growth Stages of Wheat: Heading and Flowering. In: Front. Plant Sci. 8, S. 252. DOI: 10.3389/fpls.2017.00252.