Modeling of Flowering Time in Vigna radiata with Artificial Image Objects, Convolutional Neural Network and Random Forest
Journal
Plants
Journal Volume
11
Journal Issue
23
ISSN
2223-7747
Date Issued
2022-12-01
Author(s)
Maria Bavykina
Nadezhda Kostina
Roland Schafleitner
Eric Bishop-von Wettberg
Sergey V. Nuzhdin
Maria Samsonova
Vitaly Gursky
Konstantin Kozlov
DOI
10.3390/plants11233327
Abstract
Flowering time is an important target for breeders in developing new varieties adapted to changing conditions. In this work, a new approach is proposed in which the SNP markers influencing time to flowering in mung bean are selected as important features in a random forest model. The genotypic and weather data are encoded in artificial image objects, and a model for flowering time prediction is constructed as a convolutional neural network. The model uses weather data for only a limited time period of 5 days before and 20 days after planting and is capable of predicting the time to flowering with high accuracy. The most important factors for model solution were identified using saliency maps and a Score-CAM method. Our approach can help breeding programs harness genotypic and phenotypic diversity to more effectively produce varieties with a desired flowering time.
Subjects
artificial image objects
climatic factors
convolutional neural network
flowering time
GWAS
mung bean
random forest
Publisher
MDPI AG
Description
Article number 3327
Type
journal article