Geodesic
Investigation of different topologies of neural networks for data assimilation
Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika, Tome 3 (2014) no. 4, pp. 96-108 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

Neural networks have emerged as a novel scheme for a data assimilation process. Neural network techniques are applied for data assimilation in the Lorenz chaotic system. A radial basis function and a multilayer perceptron neural networks are trained employing 1000, 2000, and 4000 examples. Three different observation intervals are used: 0.01, 0.06 and 0.1 s. The performance of the data assimilation technique is investigated for different architectures of these neural networks.
Keywords: Neural Network
Mots-clés : data assimilation, Data Assimilation. 
@article{VYURV_2014_3_4_a6,
     author = {F. P. H\"arter and H. F. Campos Velho},
     title = {Investigation of different topologies of neural networks for data assimilation},
     journal = {Vestnik \^U\v{z}no-Uralʹskogo gosudarstvennogo universiteta. Seri\^a Vy\v{c}islitelʹna\^a matematika i informatika},
     pages = {96--108},
     year = {2014},
     volume = {3},
     number = {4},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/VYURV_2014_3_4_a6/}
}
TY  - JOUR
AU  - F. P. Härter
AU  - H. F. Campos Velho
TI  - Investigation of different topologies of neural networks for data assimilation
JO  - Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika
PY  - 2014
SP  - 96
EP  - 108
VL  - 3
IS  - 4
UR  - http://geodesic.mathdoc.fr/item/VYURV_2014_3_4_a6/
LA  - en
ID  - VYURV_2014_3_4_a6
ER  - 
%0 Journal Article
%A F. P. Härter
%A H. F. Campos Velho
%T Investigation of different topologies of neural networks for data assimilation
%J Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika
%D 2014
%P 96-108
%V 3
%N 4
%U http://geodesic.mathdoc.fr/item/VYURV_2014_3_4_a6/
%G en
%F VYURV_2014_3_4_a6
F. P. Härter; H. F. Campos Velho. Investigation of different topologies of neural networks for data assimilation. Vestnik Ûžno-Uralʹskogo gosudarstvennogo universiteta. Seriâ Vyčislitelʹnaâ matematika i informatika, Tome 3 (2014) no. 4, pp. 96-108. http://geodesic.mathdoc.fr/item/VYURV_2014_3_4_a6/

[1] P. Zannetti, Air Pollution Modeling, Computational Mechanics Publications, UK, 1990

[2] R. Daley, Atmospheric Data Analysis, Cambridge University Press, Cambridge, 1991

[3] A.F. Bennet, Inverse Methods in Physical Oceanography, Cambridge University Press, Cambridge, 1992

[4] A.G. Nowosad, A. Rios Neto, H.F. de Campos Velho, “Data Assimilation Using an Adaptative Kalman Filter and Laplace Transform”, Hybrid Methods in Engineering, 2:3 (2000), 291–310

[5] S. Haykin, Neural Networks: A Comprehensive Foundation, Macmillan, New York

[6] E. Lorenz, “Deterministic Nonperiodic Flow”, Journal of Atmospheric Sciences, 20 (1963), 130–141

[7] F. Girosi,T. Poggio, “Networks and the best approximation property”, Biological Cibernetic, 45 (1990), 169–176

[8] A. Jazwinsky, Stochastic Processes and Filtering Theory, Academic Press, New York–London, 1970