The efficiency of artificial neural networks (ANN) to model complex problems may enable the prediction of characteristics that are hard to measure, providing better results than the traditional indirect selection. Thus, this study aimed to investigate the potential of using artificial neural networks (ANN) for indirect selection against early flowering in lettuce, identify the influence of genotype by environment interaction in this strategy and compare your results with the traditional indirect selection. The number of days to anthesis were used as the desired output and the information of six characteristics (fresh weight of shoots, mass of marketable fresh matter of shoots, commercial dry matter of shoots, average diameter of the head, head circumference and leaf number) as input file for the training of the ANN-MLP (Perceptron Multi-Layer). The use of ANN has great potential adjustment for indirect selection for genetic improvement of lettuce against early flowering. The selection based on the predicted values by network provided estimates of gain selection largest that traditional indirect selection. The ANN trained with data from an experiment have low power extrapolation to another experiment, due to effect of interaction genotype by environment. The ANNs trained simultaneously with data from different experiments presented greater predictive power and extrapolation.
Sweet potato is one of the most cultivated tuberous roots in tropical and subtropical regions permitting several ways of use. Despite its potential use, sweet potato has been little studied. We evaluated the performance of sweet potato roots, forage productivity and its silage at different harvesting times and cultivation environments and we identified the most superior clones under different soil and climatic conditions. Six sweet potato clones (BD-38, BD-45, BD-25, BD-31TO, BD-15 and BD-08) belonging to germplasm bank of UFVJM in addition to two standard cultivars Brazlândia Rosada and Princesa were grown in two cultivation sites (JK campus and Forquilha farm). The trial was conducted in split plots in randomized block design with three harvest times (120, 150 and 180 days after planting). The mean root weight obtained from Forquilha farm was on average 30.2% higher than those obtained from JK campus. Regardless the site, harvesting at 150 days after planting was the optimal time for maximizing root production. The irregularity of root shape increased when the harvesting date was postpone, probably due to greater exposure to environmental factors. Crude protein, fibers, ash and starch, were not affected by local x cultivar interaction except for starch content that depended on the clone and site interaction.
. 2013. Seleção de genótipos de alface para cultivo protegido: divergência genética e importância de caracteres. Horticultura Brasileira 31: 260-265.
Seleção de genótipos de alface para cultivo protegido: divergência genética e importância de caracteres
RESUMO: Durante o ciclo vegetativo da couve é possível fazer várias colheitas. Dessa forma, é necessário estabelecer o número mínimo de colheitas que possibilita a seleção confiável de genótipos superiores. Objetivou-se estimar o número mínimo de medições para a seleção de clones de couve com maior eficiência e confiabilidade por meio do estudo de repetibilidade. O experimento foi conduzido na Universidade Federal dos Vales do Jequitinhonha e Mucuri, utilizando o delineamento em blocos casualizados com 27 genótipos de couve, quatro repetições e cinco indivíduos por parcela. Durante 10 semanas foram avaliadas semanalmente a altura das plantas, diâmetro do caule, comprimento e largura do limbo foliar, número de folhas comerciais, número de folhas totais e número de brotações. Foram utilizados os métodos da análise de variância, componentes principais e análise estrutural no estudo de repetibilidade. As características estudadas tiveram altas estimativas do coeficiente de repetibilidade. Apenas três colheitas possibilitam a seleção confiável dos melhores genótipos para todas as características avaliadas.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.