Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2021.10.27.466056

Automated Hyperspectral Vegetation Index Derivation Using A Hyperparameter Optimization Framework for High-Throughput Plant Phenotyping

Koh, J.·Banerjee, B.·Spangenberg, G.·Kant, S.
View original source ↗Export metadata ↓

Abstract

O_LIHyperspectral 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 2-band indices which limits the net performance and often do not generalize well for other traits than they were originally designed for. C_LIO_LIWe present an automated hyperspectral vegetation index (AutoVI) system for the rapid generation of novel 2- to 6-band trait-specific indices in a streamlined process covering model selection, optimization 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. C_LIO_LIResults show that AutoVI can rapidly generate complex novel VIs ([≥]4-band index) which correlated strongly (R2 > 0.8) with measured chlorophyll and sugar contents in wheat. AutoVI-derived indices were used as features in simple and stepwise multiple linear regression for chlorophyll and sugar content estimation, and outperformed results achieved with existing 47 VIs and those provided by partial least squares regression. C_LIO_LIThe AutoVI system can deliver novel trait-specific VIs readily adoptable in high-throughput plant phenotyping platforms and should appeal to plant scientists and breeders. A graphical user interface of AutoVI is herein provided. C_LI

Source connections

Explore related subjects

plant biologyPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Koh, J., Banerjee, B., Spangenberg, G., Kant, S.. 2021-10-28. Automated Hyperspectral Vegetation Index Derivation Using A Hyperparameter Optimization Framework for High-Throughput Plant Phenotyping. https://doi.org/10.1101/2021.10.27.466056

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Secondary growth in the tomato stem is suppressed by the flowering regulators FUL2 and STM3

Herbaceous eudicot crops such as tomato accumulate substantial amounts of secondary xylem in their stems, particularly in the basal part. As plants progress from the vegetative phase to flowering and fruit development, secondary growth continues to provide mechanical support and facilitate transport. To uncover how secondary growth is regulated in the tomato stem, we used laser capture microdissection RNA-seq to establish tissue-specific transcriptomic profiles. This revealed that key regulators associated with wood formation in poplar are also acting in tomato. Furthermore, we found that the flowering regulators FUL2 and STM3 are substantially expressed in xylem tissue. Subsequent functional analysis identified FUL2 and STM3 as key repressors of secondary growth, with ful2 or stm3 knock-out mutants exhibiting strongly increased secondary growth in older tomato stems. Notably, a higher order mutant in which both ful2 and stm3 were knocked out displays a similar non-additive phenotype, indicating, together with yeast two-hybrid data showing physical interaction, that FUL2 and STM3 act together in a complex. The expression levels of both genes remain low until after the floral transition but strongly rise during subsequent stem development. Transcriptomic analyses in ful2, stm3, and wild-type stems at stages before and after detectable anatomical differences, showed that the FUL2-STM3 complex represses distinct sets of NAC and MYB candidate regulators associated with xylem development. Interestingly, FUL2 and STM3 control these regulators in a stage- and position-dependent way, with candidates showing upregulation only at later stages in mid-height stems being already upregulated at earlier stages in basal stem regions. Our findings provide a tissue-resolved transcriptomic resource for tomato stems and reveal a role for FUL2 and STM3 in limiting secondary xylem accumulation as stem development progresses.

plant biology↗
bioRxiv2026

Geometric Morphometrics of Pistillate Flowers in Astrocaryum sect. Huicungo (Arecaceae): Taxonomic Implications for the Peruvian Species

The taxonomy of the Amazonian palm clade Astrocaryum sect. Huicungo remains controversial due to deep discordances between traditional classifications based on qualitative floral traits and recent phylogenomic evidence. To address this, landmark-based two-dimensional geometric morphometrics (4 landmarks, 16 semilandmarks) was applied to evaluate the symmetric component of shape variation in calyx and corolla structures across 549 pistillate flowers from the 11 Peruvian species. Although multivariate analyses (PCA, CVA) revealed continuous morphological variation and extensive phenotypic overlap, perianth geometry retained a significant diagnostic signal. Cross-validated classification rates demonstrated that the corolla exhibited higher discriminatory power than the calyx, while the combined perianth analysis (calyx + corolla) maximized taxonomic assignment accuracy. Furthermore, Mahalanobis distance-based clustering did not replicate traditional subsections: A. chonta and A. ulei exhibited divergent architectures, whereas A. carnosum, A. faranae, and A. huicungo shared profound geometric similarity. This study demonstrates that quantitative perianth morphometrics is a valuable tool for species delimitation in Astrocaryum, supporting the re-evaluation of traditional taxonomic boundaries through an integrative approach.

plant biology↗
bioRxiv2026

Multi-Criteria Evaluation of Hibiscus mutabilis Cultivars for Food Development Using Delphi and Analytic Hierarchy Process

This study evaluated 11 Hibiscus mutabilis cultivars from Chengdu Botanical Garden to assess their quality for food use and identify promising cultivars. An evaluation framework was developed using the Delphi method to select indicators and the analytic hierarchy process (AHP) to determine their weights. Overall scores ranged from 2.5785 to 3.6043, and the cultivars were classified into three grades. Grade I included Hibiscus mutabilis 'Bairi Huacai', Hibiscus mutabilis 'Chongbanbai' and Hibiscus mutabilis 'Jinqiusong'; Grade II included Hibiscus mutabilis 'Jinqiuhong', Hibiscus mutabilis 'Zuifurong', Hibiscus mutabilis 'Danbanhong', Hibiscus mutabilis 'Jinxiuzi', Hibiscus mutabilis 'Jinbiyu' and Hibiscus mutabilis 'Caixia'; whereas Grade III included Hibiscus mutabilis 'Mudanfen' and Hibiscus mutabilis 'Jinrui'. In summary, Hibiscus mutabilis 'Bairi Huacai', Hibiscus mutabilis 'Chongbanbai' and Hibiscus mutabilis 'Jinqiusong' are the preferred cultivars for food processing and development. The framework provides a basis for cultivar screening and further evaluation of H. mutabilis flowers for food use.

plant biology↗