Data driven discovery and quantification of hyperspectral leaf reflectance phenotypes across a maize diversity panel
[1];
[3];
[1]
- Quantitative Life Sciences Initiative University of Nebraska‐Lincoln Lincoln Nebraska USA, Center for Plant Science Innovation University of Nebraska‐Lincoln Lincoln Nebraska USA, Department of Agronomy and Horticulture University of Nebraska‐Lincoln Lincoln Nebraska USA
- Quantitative Life Sciences Initiative University of Nebraska‐Lincoln Lincoln Nebraska USA, Center for Plant Science Innovation University of Nebraska‐Lincoln Lincoln Nebraska USA, Department of Agronomy and Horticulture University of Nebraska‐Lincoln Lincoln Nebraska USA, Department of Plant Molecular Ecophysiology, Institute of Plant Experimental Biology and Biotechnology, Faculty of Biology University of Warsaw Warsaw Poland
- Department of Mechanical Engineering Iowa State University Ames Iowa USA, Translational AI Research and Education Center Iowa State University Ames Iowa USA
- Quantitative Life Sciences Initiative University of Nebraska‐Lincoln Lincoln Nebraska USA, Center for Plant Science Innovation University of Nebraska‐Lincoln Lincoln Nebraska USA, Department of Agronomy and Horticulture University of Nebraska‐Lincoln Lincoln Nebraska USA, Advanced Diagnostic Laboratory, Department of Quantitative Health Sciences Mayo Clinic Rochester Minnesota USA
- Center for Plant Science Innovation University of Nebraska‐Lincoln Lincoln Nebraska USA, Department of Biological Systems Engineering University of Nebraska‐Lincoln Lincoln Nebraska USA
Abstract 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.
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- SC0020355
- OSTI ID:
- 2483850
- Journal Information:
- Plant Phenome Journal, Journal Name: Plant Phenome Journal Journal Issue: 1 Vol. 7; ISSN 2578-2703
- Publisher:
- Wiley Blackwell (John Wiley & Sons)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer
The Global Spectra-Trait Initiative: A database of paired leaf spectroscopy and functional traits associated with leaf photosynthetic capacity