Create your own conference schedule! Click here for full instructions

The Virtual Conference is located at

Abstract Detail

Crops and Wild Relatives

Coelho, Daniel [1], Majumder, Sambadi [2], Dowell, Jordan [3], Goolsby, Eric [4], Mason, Chase [5].

Diversity in Leaf hyperspectral Reflectance across Cultivated Sunflower Germplasm.

Abstract: Cultivated sunflower is the third most important oilseed crop globally, with market classes consisting of multiple market classes and breeding pools. In this study, a diversity panel consisting of 288 genotypes of cultivated sunflower (Helianthus annuus L.) was phenotyped for leaf hyperspectral reflectance to estimate differentiation among breeding pools and market classes. Leaf reflectance was measured using a spectrometer capable of measuring reflectance from 210-1000nm. PCA was performed on the dataset and the resulting principal components were used to train an SVM (Support Vector Machine) model using unsupervised clustering. This was done separately to attempt prediction of breeding pool and market class from leaf reflectance. Separation by important features within a machine-learning framework can identify reflectance regions differentiated among genotypes. Future efforts with this data set will be focused on mapping hyperspectral reflectance and pigment characteristics through a genome-wide association study.

Log in to add this item to your schedule

1 - University of Central Florida, 14601 Old Thicket Trace, Winter Garden, FL, 34787, United States
2 - University Of Central Florida, Department Of Biology, 4110 Libra Drive, Orlando, FL, 32816, United States
3 - 11160 Sylvan Pond Circle, Orlando, FL, 32825, United States
4 - University of Central Florida, Department of Biology, 4110 Libra Drive, Orlando, FL, 32816, USA
5 - University Of Central Florida, Department Of Biology, 4110 Libra Dr, Orlando, FL, 32816, United States

Hyperspectral Reflectance
Machine learning.

Presentation Type: Poster
Session: P1, Crops and Wild Relatives Posters
Location: Virtual/Virtual
Date: Monday, July 19th, 2021
Time: 5:00 PM(EDT)
Number: P1CW009
Abstract ID:891
Candidate for Awards:None

Copyright © 2000-2021, Botanical Society of America. All rights reserved