Artificial neural networks classify cotton genotypes for fiber length

• Autor(a) principal: Carvalho,Luiz Paulo de
• Data de Publicação: 2018
• Outros Autores: Teodoro,Paulo Eduardo, Barroso,Lais Mayara Azevedo, Farias,Francisco José Correia, Morello,Camilo de Lellis, Nascimento,Moysés
• Tipo de documento: Relatório
• Idioma: eng
• Título da fonte: Crop Breeding and Applied Biotechnology
• Texto Completo: http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1984-70332018000200200
• topic: Genotype x environment interaction; artificial intelligence; Gossypium hirsutum

Abstract Fiber length is the main trait that needs to be improved in cotton. However, the presence of genotypes x environments interaction for this trait can hinder the recommendation of genotypes with greater length fibers. The aim of this study was to evaluate the adaptability and stability of the fibers length of cotton genotypes for recommendation to the Midwest and Northeast, using artificial neural networks (ANNs) and Eberhart and Russell method. Seven trials were carried out in the states of Ceará, Rio Grande do Norte, Goiás and Mato Grosso do Sul. Experimental design was a randomized block with four replications. Data were submitted to analysis of adaptability and stability through the Eberhart & Russell and ANNs methodologies. Based on these methods, the genotypes BRS Aroeira, CNPA CNPA 2009 42 and CNPA 2009 27 has better performance in unfavorable, general and favorable environment, respectively, for having fiber length above the overall mean of environments and high phenotypic stability.