@Article{HärterCamp:2010:MuPeNe,
author = "H{\"a}rter, Fabr{\'{\i}}cio Pereira and Campos Velho, Haroldo
Fraga de",
affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto
Nacional de Pesquisas Espaciais (INPE)}",
title = "Multlayer perceptron neural network in a data assimilation
scenario",
journal = "Engineering Applications of Computational Fluid Mechanics",
year = "2010",
volume = "4",
number = "2",
pages = "237--245",
keywords = "Data assimilation, Extended Kalman filter, Artificial neural
network, Multi-layer perceptron, Dynamo atmospheric model.",
abstract = "Multilayer Perceptron Neural Network (MLP-NN) have been
successfully applied to solve nonlinear problems in meteorology
and oceanography. In this work, MLP-NN is applied to completely
emulate an Extended Kalman Filter (EKF) in a data assimilation
scenario. Data assimilation is a process for producing a good
combination of data from observations and data from a mathematical
model. This is a fundamental issue in an operational prediction
system. The one-dimensional shallow water equation DYNAMO-1D is
employed here for testing the assimilation schemes. The DYNAMO
model is derived from depth-integrating the Navier-Stokes
equations, in the case where the horizontal length scale is much
greater than the vertical length scale, where the Coriolis force
is also considered in atmospheric flows. Techniques, such as
Extend Kalman Filter, are available to track non-linear dynamical
models under certain conditions. Under strong non-linearity, the
fourth-order moment EKF works well when applied to high
dimensional state space for data assimilation, but the
computational burden is a barrier in this kind of application.
Artificial Neural Network (ANN) is an alternative solution for
this computational complexity problem, once the ANN is trained
offline with a high order Kalman filter, even though this Kalman
filter has high computational cost (which is not a problem during
ANN training phase). The results achieved in this research
encourage us to apply this technique on operational models.
However, it is not yet possible to assure convergence in high
dimensional problems.",
doi = "10.1080/19942060.2010.11015313",
url = "http://dx.doi.org/10.1080/19942060.2010.11015313",
issn = "1994-2060",
label = "lattes: 5142426481528206 2 H{\"a}rterCamp:2010:MuPeNe",
language = "en",
urlaccessdate = "29 jun. 2024"
}