La Trobe
1190364_Koh,J_2022.pdf (923.56 kB)
Download file

Automated hyperspectral vegetation index derivation using a hyperparameter optimisation framework for high-throughput plant phenotyping

Download (923.56 kB)
journal contribution
posted on 2022-03-30, 02:51 authored by JCO Koh, BP Banerjee, German SpangenbergGerman Spangenberg, Surya KantSurya Kant
Hyperspectral vegetation indices (VIs) are widely deployed in agriculture remote sensing and plant phenotyping to estimate plant biophysical and biochemical traits. However, existing VIs consist mainly of simple two-band indices that limit the net performance and often do not generalise well for traits other than those for which they were originally designed. We present an automated hyperspectral vegetation index (AutoVI) system for the rapid generation of novel two- to six-band trait-specific indices in a streamlined process covering model selection, optimisation and evaluation, driven by the tree parzen estimator algorithm. Its performance was tested in generating novel indices to estimate chlorophyll and sugar contents in wheat. Results showed that AutoVI can rapidly generate complex novel VIs (at least a four-band index) that correlated strongly (R2 > 0.8) with measured chlorophyll and sugar contents in wheat. Automated hyperspectral vegetation index-derived indices were used as features in simple and stepwise multiple linear regressions for chlorophyll and sugar content estimation, and outperformed the results achieved with the existing 47 VIs and those provided using partial least squares regression. The AutoVI system can deliver novel trait-specific VIs readily adoptable to high-throughput plant phenotyping platforms and should appeal to plant scientists and breeders. A graphical user interface for the AutoVI is provided here.


Publication Date



New Phytologist






(p. 2659-2670)





Rights Statement

© 2022 The Authors New Phytologist © 2022 New Phytologist Foundation This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.