AUTHOR=Amaral Lígia de Oliveira , Miranda Glauco Vieira , Val Bruno Henrique Pedroso , Silva Alice Pereira , Moitinho Alyce Carla Rodrigues , Unêda-Trevisoli Sandra Helena 

TITLE=Artificial Neural Network for Discrimination and Classification of Tropical Soybean Genotypes of Different Relative Maturity Groups

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.814046

DOI=10.3389/fpls.2022.814046

ISSN=1664-462X

ABSTRACT=Soybean plants are affected by their photoperiod and, the cultivation of a given variety is performed in the latitude range that presents ideal conditions for its development based on its relative maturity group. This study aimed to classify soybean genotypes from a population with wide genetic variability and two populations with narrow variability in terms of the relative maturity character using an artificial neural network (ANN). The three soybean populations were obtained from biparental crosses between genitors of maturity groups RMG 5 (sub-tropical 23° LS) × RMG 9 (tropical 0° SL), RMG 7 (tropical 20° SL) × RMG 9, and RMG 5 × RMG 7. Criteria for comparing the developed ANN architecture and Fisher's linear and Anderson's quadratic parametric discriminant methodologies were applied to the data for the discrimination and classification of the genotypes. The ANN showed an apparent error rate below 8.16%, in addition to the low influence of environmental factors, correctly classifying the genotypes in the populations, even in cases of reduced genetic variability, e.g., in the RMG 5 × RMG 6 population. In contrast, the discriminant functions proved inefficient in correctly classifying the genotypes in the populations with genealogical similarity (RMG 5 × RMG 6) and wide genetic variability, presenting an error rate above 50%. Based on the results of this study, the ANN can be used for the discrimination of genotypes in the initial generations of selection in breeding programs. This will lead to the development of high-performance cultivars for elongated and reduced photoperiod amplitudes at a single selection site efficiently with reduced time and resources. ANN correctly classifies narrow-base and pure lineage populations.