Phenotyping and predicting wheat spike characteristics using image analysis and machine learning

Improvements in trait phenotyping are needed to increase the quantity and quality of data available for genetic improvement of crops. In this study, we used moderate throughput image analysis and machine learning as a pipeline for phenotyping a key wheat spike characteristic: spikelet number per spi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Plant phenome journal 2023-12, Vol.6 (1), p.n/a
Hauptverfasser: Hammers, Mik, Winn, Zachary J., Ben‐Hur, Asa, Larkin, Dylan, Murry, Jamison, Mason, Richard Esten
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Improvements in trait phenotyping are needed to increase the quantity and quality of data available for genetic improvement of crops. In this study, we used moderate throughput image analysis and machine learning as a pipeline for phenotyping a key wheat spike characteristic: spikelet number per spike. A population of 594 soft red winter wheat inbred lines was evaluated in the field for 2 years and images of wheat spikes were taken and used to train deep‐learning algorithms to predict spikelet number. A total of 12,717 images were used to train, test, and validate a basic regression convolutional neural network (CNN), a visual geometry group application regression model, VGG16, the ResNet152V2 model, and the EfficientNetV2L model. The EfficientNetV2L model was the most accurate, having the lowest mean absolute error, second lowest root mean square error, and highest coefficient of determination (mean absolute error [MAE] = 0.60, root mean square error [RMSE] = 0.79, and R2 = 0.90). The ResNet152V2 model was slightly less accurate with a slightly better fit (MAE = 0.61,m RMSE = 0.78, and R2 = 0.87), followed by the basic CNN (MAE = 0.75, RMSE = 1.00, and R2 = 0.74) and finally by the VGG16 (MAE = 1.51, RMSE = 1.29, and R2 = 0.076). With an average error of just above one half of a spikelet, utilizing image analysis and machine learning counting methods could be used for multiple breeding applications, including direct selection of spikelet number, to provide data to identify quantitative trait loci, or for training whole genome selection models. Core Ideas High‐throughput phenotyping methods are needed to make larger quantities of phenotypic data accessible to researchers and plant breeders. Imaging is valuable for high‐throughput phenotyping and can be used for collecting quantitative plant traits. Machine learning algorithms can be used as an efficient analysis pipeline to create high‐throughput phenotyping methods for collecting trait data from wheat spikes.
ISSN:2578-2703
2578-2703
DOI:10.1002/ppj2.20087