Mauricio Horbach Barbosa

Artificial Neural Network and Multivariate Models Applied to Morphological Traits and Seeds of Common Beans Genotypes

The aimed to characterize common beans genotypes utilizing multivariate models and artificial neural network thru the agronomic attributes and seeds dimensions. The experiment was conducted in the 2017/2018 crop season at the city of Tenente Portela - RS. The experimental design was expanded blocs, were 53 segregating F2 populations and ten cultivars considered checks, disposed in four repetitions. The accurate characterization of bean genotypes can be based in the reproductive period, cycle and seeds length. Genotypes with longer cycle increase the potential of ramifications, legume and seeds magnitude per plant and increase the seeds yield independent of the commercial group. The use of biometric approach allows revealing patterns to the genotype grouping, being the patterns magnitude dependent of the intrinsic premises to the Standardized Average Euclidian Distance, Tocher optimized grouping and Artificial Neural Network with non-supervised learning. It is defined that the Artificial Neural Network are determinant to define associative patterns, being these inferences indispensable to the common beans genotype selection that answer the agronomic attributes and seeds production.

Multivariate approach in Eucalyptus and its effects in the genotypes à environments interaction

The study aimed at the selection and evaluation of Eucalyptus spp. clones for the production of wood by means of multivariate statistical techniques. A total of 84 Eucalyptus clones were used belonging to the breeding program in Rio Grande do Sul, Brazil, in a randomized block design, with 20 replicates. The selection of clones from their values of genetic divergence and heterogeneity in relation to the others can be used to increase variability in breeding populations. Improvement strategies such as the Intrapopulation Recurrent Selection can be fed from selections made based on these parameters, but also focusing on increasing productivity and improving wood technology. There is a great difference in behavior of the clones for each environment, demonstrating the influence of the genotype × environment interaction, which can be evaluated later in the clonal tests amplified or in the observation plantings of these clones that will serve for the future indication of genotypes for the commercial plantations

Adaptability, Stability and Multivariate Selection by Mixed Models

The aim of this work was to estimate the adaptability nand stability of grain yield per hectare and percentage of crude protein of nmaize grains combined in an index, and to establish a multicharacter selection nthrough mixed models based on an objective character and 15 auxiliary traits. nThe trials were conducted in the 2013/2014 agricultural year in four growing nenvironments of the Rio Grande do Sul, BR state. The experimental design was nrandomized blocks arranged in a factorial scheme, being four growing sites × 15 nsingle cross maize hybrids, arranged in three repetitions. The genotypic index, ncomposed by the grain yield and the crude protein percentage in the grains, is nthe best selection strategy to achieve maize superior genotypes. The nmultivariate genotypes selection, considering grain yield and crude protein, is nefficient. The genotypes FORMULA TL®, nAS1656PRO®, P30F53Hx®, nLG6304YG® and 30F53 are more adapted and stable nfor grain yield and percentage of crude protein, in the conditions of this nstudy. The mixed models were efficient to employ the multicharacter selection nand to contribute for maize genetic breeding.