Envirotype approach for soybean genotype selection through the integration of georeferenced climate and genetic data using artificial neural networks

Abstract

The selection of better-evaluated genotypes for a target region depends on the characterization of the climate conditions of the environment. With the advancement of computer technology and daily available information about the weather, integrating such information in selection and interaction genotype x environment studies has become a challenge. This article presents the use of the technique of artificial neural networks associated with reaction norms for the processing of climate and geo-referenced data for the study of genetic behaviors and the genotype-environment interaction of soybean genotypes. The technique of self-organizing maps (SOM) consists of competitive learning between two layers of neurons; one is the input, which transfers the data to the map, and the other is the output, where the topological structure formed by the competition generates weights, which represent the dissimilarity between the neural units. The methodologies used to classify these neurons and form the target populations of environments (TPE) were the discriminant analysis (DA) and the principal component analysis (PCA). To study soybean genetic behavior within these TPEs, the random regression model was adopted to estimate the components of variance, and the reaction norms were adjusted through the Legendre polynomials. The SOM methodology allowed for an explanation of 99% of the variance of the climate data and the formation of well-structured TPEs, with the membership probability of the regions within the TPEs above 80%. The formation of these TPEs allowed us to identify and quantify the response of the genotypes to sensitive changes in the environment.