Yield stability analysis of maize hybrids using the self-organizing map of Kohonen
- PDF / 620,596 Bytes
- 10 Pages / 547.087 x 737.008 pts Page_size
- 74 Downloads / 194 Views
(0123456789().,-volV) ( 01234567 89().,-volV)
Yield stability analysis of maize hybrids using the self-organizing map of Kohonen Luiz Rafael Clovis . Carlos Alberto Scapim . Ronald Jose´ Barth Pinto . Marcelo Vivas . Janeo Eusta´quio de Almeida Filho . Antonio Teixeira do Amaral Ju´nior
Received: 16 April 2018 / Accepted: 19 August 2020 Ó Springer Nature B.V. 2020
Abstract The purpose of this study is to classify 32 commercial maize hybrids with regard to grain yield stability by using an artificial neural network procedure. The hybrids were evaluated at five locations, in two late growing seasons. Each replication (R1 and R2) of the response variable was used as a network input signal to trigger the network learning process. The underlying network model has a topology consisting of two neurons in the input layer and ten neurons arranged in a two-dimensional grid. The competitive process was induced by the random presentation of an input vector x ¼ ½x1 ; x2 ; . . .; xn T from the network training set, without specifying a desired output. A grid neuron y responded best to this stimulus. Thus, the neuron with the shortest Euclidean distance between the input vector and the respective weight vector wi ¼ ½wi1 ; wi2 ; . . .; win T , at moment t, was selected as the winner. The winning neuron L. R. Clovis C. A. Scapim R. J. B. Pinto Departamento de Agronomia, Universidade Estadual de Maringa´ (UEM), Maringa´, PR 87020-900, Brazil M. Vivas A. T. do Amaral Ju´nior (&) Centro de Cieˆncias e Tecnologias Agropecua´rias, Universidade Estadual do Norte Fluminense Darcy Ribeiro (UENF), Av. Alberto Lamego, 2000, Parque Califo´rnia, Campos dos Goytacazes, RJ 28013-600, Brazil e-mail: [email protected] J. E. de Almeida Filho Bayer Cropsciece, Estrada da Invernadinha, 2000, Coxilha, RS CEP 99145-000, Brazil
indicates the center of a topological neighborhood of cooperative neurons. The adaptive process occurred via applying an adjustment Dwij to the synaptic weights wij during learning, until convergence of the network. The results showed that the classes of hybrids with the same performance pattern across environments were not altered by the network, confirming the high yield stability and satisfactory overall performance associated with higher grain yield means (above 6 t ha-1). The single-cross hybrid 10 (CD387) stood out at all locations in both years, with unaltered data classification by the network. Therefore, it was considered to be stable in all environments, without performance variation over the years, as well as adaptable. Keywords Artificial neural networks Second growing season Maize hybrids Grain yield
Introduction Currently, several statistical methods are being developed and applied for genotype adaptability and stability analysis. In addition, new procedures are being proposed to improve the interpretation of genotype–environment interactions, including Bayesian procedures applied to frequentist analyses (Couto et al. 2015; Correa et al. 2016).
123
161
Page 2 of 10
Methodologies that estima
Data Loading...
