Modeling of Flowering Time in Vigna radiata with Artificial Image Objects, Convolutional Neural Network and Random Forest

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.

Dynamical climatic model for time to flowering in Vigna radiata

BACKGROUND

Phenology data collected recently for about 300 accessions of Vigna radiata (mungbean) is an invaluable resource for investigation of impacts of climatic factors on plant development.

RESULTS

We developed a new mathematical model that describes the dynamic control of time to flowering by daily values of maximal and minimal temperature, precipitation, day length and solar radiation. We obtained model parameters by adaptation to the available experimental data. The models were validated by cross-validation and used to demonstrate that the phenology of adaptive traits, like flowering time, is strongly predicted not only by local environmental factors but also by plant geographic origin and genotype.

CONCLUSIONS

Of local environmental factors maximal temperature appeared to be the most critical factor determining how faithfully the model describes the data. The models were applied to forecast time to flowering of accessions grown in Taiwan in future years 2020-2030.

SPECIES DIVERSITY OF THE VIR COLLECTION OF GRAIN LEGUME GENETIC RESOURCES AND ITS USE IN DOMESTIC BREEDING

The world’s genebanks hold 7.5 million germplasm accessions of plant genetic resources (PGR). One of the qualitative characteristics of the PGR collections is the species diversity, in particular, the presence of crop wild relatives (CWR), which makes it possible to widen the use of gene pools in the breeding process. The collection of the Vavilov Institute (VIR) is one of the most diverse holdings in the number of plant species. A survey is provided here of the species diversity in VIR’s grain legume collection, and its use in domestic breeding practice is analyzed. Comparison of this diversity with the state of PGR exploitation in the world makes it possible to assess the prospects of more efficient utilization of gene pool potential, especially for species that are unjustifiably cultivated on a too small scale or even neglected as crops in this country. The VIR collection of grain legumes incorporates 196 species from 9 genera of the family Fabaceae. This number includes cultigens and CWR. The cultivars of 21 species of grain legumes listed in the State Register of Breeding Achievements (2018) are adapted to the soil and climate conditions of this country. However, the species diversity of the collection could be used more efficiently in domestic plant breeding and crop production. This concerns both underutilized crops in Russia (broad beans, lima beans and grass pea) and those whose adaptive potential is adjusted only to certain and limited areas of the Russian Federation (Tepary beans and Vigna spp.). It is also necessary to exploit more efficiently species of the wild flora, both for direct utilization as pastures, green manure or phytoremediation crops and for introgressive breeding and domestication (Vicia benghalensis L., V. narbonensis L., Lathyrus sylvestris L., Lupinus hartwegii Lindl., etc.). Incorporation of crop wild relatives into the breeding process is promising for crop improvement in a number of aspects: for example, to increase resistance to diseases, pests, abiotic stressors, etc.