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

Abstract

Soybean has a recognized narrow genetic base that often makes it difficult to visualize available genetic and phenotypic variability and identify superior genotypes during the selection process. However, the phenotypic expression of soybean plants is highly affected by 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 (RMG) for the optimization of the phenotypic expression of its genotype. Based on the above, this study aimed to evaluate the efficiency of artificial neural networks (ANNs) as a tool for the correct discrimination and classification of tropical soybean genotypes according to their relative maturity group during the population selection process with the aim of optimizing the phenotypic performance of these selected genotypes. For this purpose, three biparental populations were synthesized, one with a wide genetic variability for the RMG character obtained from the hybridization between genitors of maturity groups RMG 5 (Sub-tropical 23° LS) × RMG 9.4 (Tropical 0° LS) and two populations with a narrow variability obtained between genitors RMG 7.3 (Tropical 20° LS) × RMG 9.4 and RMG 5.3 × RMG 6.7, respectively. Criteria for comparing the developed ANN architecture with Fisher’s linear and Anderson’s quadratic parametric discriminant methodologies were applied to the data for the discrimination and classification of the genotypes. ANN showed an apparent error rate of less than 8.16% as well as a low influence of environmental factors, correctly classifying the genotypes in the populations even in cases of reduced genetic variability such as in the RMG 5 × RMG 6 population. In contrast, the discriminant functions were inefficient in correctly classifying the genotypes in the populations with genealogical similarity (RMG 5 × RMG 6) and wide genetic variability, with an error rate of more than 50%. Based on the results of this study, ANN can be used for the discrimination of genotypes in the initial generations of selection in breeding programs for the development of high performance cultivars for wide and reduced photoperiod amplitudes, even with fewer selection environments, more efficiently, and with fewer time and resources applied. As a result of similarity between the parents, ANN can correctly classify genotypes from populations with a narrow genetic base, in addition to pure lines and genotypes with a high degree of inbreeding.

Maize Yield Prediction using Artificial Neural Networks based on a Trial Network Dataset

“…ANNs are being applied with different models or architectures to solve common problems in plant breeding and genotype x environment interactions and other agriculture situations. This can be observed when determining drought tolerance indices for durum wheat and identifying their efficiency in relation to other methods [12], parents for crossings in breeding programs [13] and, selected soybean plants in segregating populations of different maturity groups [14]. A machine learning approach was used in the automatic irrigation system based on humidity and temperature in the soil in [15].…”

Application of Artificial Neural Networks to Predict Genotypic Values of Soybean Derived from Wide and Restricted Crosses for Relative Maturity Groups

“…In contrast to both parametric and non-parametric analyses, artificial neural networks (ANNs) offer distinct advantages that render them better suited for particular scenarios. Consequently, they play a valuable role in the selection and development stages, as described in [9], and exhibit a high predictive capacity, as demonstrated in [10]. Artificial neural networks (ANNs) are machine-learning models inspired by the human brain and have shown promise in various areas, such as pattern recognition, natural language processing, and computer vision.…”

Reconhecimento de padrões e organização da diversidade em acessos de soja (Glycine max (L.) Merrill) do sul do Brasil

“…A análise classificatória tem como objetivo a obtenção de funções que consigam classificar um indivíduo em uma população conhecida com base em um conjunto de dados sobre informações mensuradas, a fim de minimizar a classificação errônea (SANT'ANNA et al, 2018;SKOWRONSKI, 2021;CRUZ et al, 2022). Essa análise leva em consideração o conjunto total de dados, que é divido em 80% para treinamento e 20% para validação, que é a classificação dos indivíduos (AMARAL et al, 2022). A partir do momento em que indivíduos são classificados corretamente, tais funções podem ser utilizadas para a classificação de indivíduos desconhecidos (SANT'ANNA et al, 2018).…”

“…A análise discriminante proposta por Anderson em 1958 gera funções resultantes da combinação linear de características previamente avaliadas a respeito dos indivíduos sabidamente pertencentes a populações diferentes (SANT'ANNA et al, 2018;CRUZ et al, 2022). Amaral et al (2022) encontraram uma Taxa de Erro Aparente (AER) de 58,6% e 50,59% ao utilizar as metodologias de Fisher e Anderson respectivamente, para classificar genótipos referentes a 11 populações de diferentes grupos de maturidade relativa de soja. Esses autores argumentam que diversos fatores podem levar a classificações errôneas das análises discriminantes.…”

“…Esses autores argumentam que diversos fatores podem levar a classificações errôneas das análises discriminantes. Destaca-se a grande semelhança em genealogia e origem das populações, número insuficiente de variáveis analisadas, baixa qualidade discriminatória, e a utilização de uma abordagem estatística inadequada (AMARAL et al, 2022). Oliveira et al (2021) encontraram taxa de acerto de 93,33 % ao classificar grupos varietais de Coffea canephora, Nogueira et al (2008) encontraram AER de 12,73% e 9,09%) e (1,82% e 16,36%) respectivamente para classificação em de indivíduos de soja em 11 cultivares diferentes de acordo com quatro épocas de semeadura.…”