Data driven discovery and quantification of hyperspectral leaf reflectance phenotypes across a maize diversity panel

Estimates of plant traits derived from hyperspectral reflectance data have the potential to efficiently substitute for traits, which are time or labor intensive to manually score. Typical workflows for estimating plant traits from hyperspectral reflectance data employ supervised classification model...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Plant phenome journal Ročník 7; číslo 1
Hlavní autori: Tross, Michael C., Grzybowski, Marcin W., Jubery, Talukder Z., Grove, Ryleigh J., Nishimwe, Aime V., Torres‐Rodriguez, J. Vladimir, Sun, Guangchao, Ganapathysubramanian, Baskar, Ge, Yufeng, Schnable, James C.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Guilford John Wiley & Sons, Inc 01.12.2024
Wiley Blackwell (John Wiley & Sons)
Wiley
Predmet:
Chlorophyll
Corn
Data collection
Datasets
Experiments
field experimentation
Genetic markers
Genome-wide association studies
genome-wide association study
Genotypes
labor
leaf reflectance
Leaves
phenotype
Phenotypes
Phenotypic variations
Phenotyping
Plant extracts
Quantitative genetics
Reflectance
Sensors
Sorghum
Variables
variance
Zea mays
ISSN:2578-2703, 2578-2703
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Estimates of plant traits derived from hyperspectral reflectance data have the potential to efficiently substitute for traits, which are time or labor intensive to manually score. Typical workflows for estimating plant traits from hyperspectral reflectance data employ supervised classification models that can require substantial ground truth datasets for training. We explore the potential of an unsupervised approach, autoencoders, to extract meaningful traits from plant hyperspectral reflectance data using measurements of the reflectance of 2151 individual wavelengths of light from the leaves of maize (Zea mays) plants harvested from 1658 field plots in a replicated field trial. A subset of autoencoder‐derived variables exhibited significant repeatability, indicating that a substantial proportion of the total variance in these variables was explained by difference between maize genotypes, while other autoencoder variables appear to capture variation resulting from changes in leaf reflectance between different batches of data collection. Several of the repeatable latent variables were significantly correlated with other traits scored from the same maize field experiment, including one autoencoder‐derived latent variable (LV8) that predicted plant chlorophyll content modestly better than a supervised model trained on the same data. In at least one case, genome‐wide association study hits for variation in autoencoder‐derived variables were proximal to genes with known or plausible links to leaf phenotypes expected to alter hyperspectral reflectance. In aggregate, these results suggest that an unsupervised, autoencoder‐based approach can identify meaningful and genetically controlled variation in high‐dimensional, high‐throughput phenotyping data and link identified variables back to known plant traits of interest. Core Ideas Autoencoder latent variables show stronger correlations with chlorophyll content than principal components. Autoencoder‐derived latent variable exhibits modestly better performance than partial least squares regression supervised model. Latent variables derived from autoencoders are significantly associated with genetic markers. Latent variables capture variance in traits that are transferrable across species and years. Significant proportions of total variance in individual latent variables are attributable to genetics.
Bibliografia:Assigned to Associate Editor Keshav Singh.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
USDOE
DE‐SC0020355
ISSN:2578-2703
2578-2703
DOI:10.1002/ppj2.20106