@Article{AnochiTorrCamp:2020:TwGeAp,
author = "Anochi, Juliana Aparecida and Torres, Reynier Hern{\'a}ndez and
Campos Velho, Haroldo Fraga de",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)} and {Instituto Nacional de
Pesquisas Espaciais (INPE)}",
title = "Two geoscience applications by optimal neural network
architecture",
journal = "Pure and Applied Geophysics",
year = "2020",
volume = "177",
number = "6",
pages = "2663--268",
month = "June",
keywords = "Metaheuristics, optimization problem, neural network, data
assimilation, climate precipitation prediction, monoobjective
problem, multi-objective problem.",
abstract = "Nowadays, artificial neural networks have been successfully
applied on several research and application fields. An appropriate
configuration for a neural network is a complex task, and it often
requires the knowledge of an expert on the application. A
technique for automatic configuration for a neural network is
formulated as an optimization problem. Two strategies are
considered: a mono-objective minimization problem, using
multiparticle collision algorithm (MPCA); and a multi-objective
minimization problem addressed by the non-dominated sorting
genetic algorithm (NSGA-II). The proposed optimization approaches
were tested for two application in geosciences: data assimilation
for wave evolution equation, and the mesoscale seasonal climate
prediction for precipitation. Better results with automatic
configuration were obtained for data assimilation than those
obtained by network defined by an expert. For climate seasonal
precipitation, automatic configuration presented better
predictions were presented than ones carried out by an expert. For
the worked examples, the NSGA-II presented a superior result for
the worked experiments.",
doi = "10.1007/s00024-019-02386-y",
url = "http://dx.doi.org/10.1007/s00024-019-02386-y",
issn = "0033-4553",
language = "en",
targetfile = "anochi_two.pdf",
urlaccessdate = "03 jun. 2024"
}