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.
Funder
Ministry of Science and Higher Education of the Russian Federation
Subject
Plant Science,Ecology,Ecology, Evolution, Behavior and Systematics
Reference59 articles.
1. The Potential Role of Neglected and Underutilised Crop Species as Future Crops under Water Scarce Conditions in Sub-Saharan Africa;Chivenge;Int. J. Environ. Res. Public Health,2015
2. Sensory characteristics of chemical compounds potentially associated with beany aroma in foods;Chambers;J. Sens. Stud.,2004
3. Green gram and black gram: Prospects of cultivation and breeding in Russian Federation;Vishnyakova;Vavilov J. Genet. Breed.,2018
4. Collections of Mungbean [Vigna radiata (L.) R. Wilczek] and urdbean [V. mungo (L.) Hepper] in Vavilov Institute (VIR): Traits diversity and trends in the breeding process over the last 100 years;Burlyaeva;Genet. Resour. Crop. Evol.,2019
5. Schafleitner, R., Nair, R.M., Rathore, A., Wang, Y.W., Lin, C.Y., Chu, S.H., Lin, P.Y., Chang, J.C., and Ebert, A.W. (2015). The AVRDC—The World Vegetable Center mung bean (Vigna radiata) core and mini core collections. BMC Genom., 16.