The prospects of quantitative phenotyping of oilseed crops.

Plant phenotyping is a comprehensive evaluation of complex traits in plants, such as growth, development, resistance, architecture, physiology, ecology, yield, as well as the basic measurement of individual quantitative parameters that form the basis for more complex traits. This article provides an analysis of visualization methods applied in plant phenotyping and presents software for image processing. The analysis included the most significant global research in plant phenotyping. The directions of work on plant phenotyping were carried out by well-known geneticists, breeders, and engineers at the Institute of Oil Crops of the National Academy of Agrarian Sciences. Based on the global experience and the results of research at the Institute of Oilseed Crops of the National Academy of Agrarian Sciences, we propose the following development of plant phenotyping in domestic agricultural science. Integrated approaches of well-known selection-process methodologies, from molecular to field, are necessary for the development of sustainable agriculture, ensuring high yields, and the use of limited resources. Despite significant progress in the molecular and genetic approaches in recent years, quantitative analysis and systematization of plant phenotypes (plant structures and functions) have become major challenges. Plant phenotyping is a science that combines genomics, ecophysiology, and plant agronomy using modern automated selection and systematization methods. The functional plant body (phenotype) is formed during plant growth and development through dynamic interactions between genotype and the surrounding environment in which plants grow. These interactions determine the practical result of crop cultivation in terms of quantity and quality of production. This includes crop yield and its quality: oil content, seed size, shape, and seed density, among other factors. Systematizing oilseed crops based on a complex of phenotypic characteristics, taking into account gene penetrance and trait inheritance, will reduce the time and effort required for decision-making. Mechanotronic systems for material separation, selection, and classification using neural networks will significantly reduce costs. Therefore, one of the solutions to this problem is the development of a methodology for systematic genotyping of sunflower based on phenotypic expression using neural networks. [ABSTRACT FROM AUTHOR]