%0 Conference Proceedings
%4 sid.inpe.br/mtc-m18@80/2009/07.16.16.36
%2 sid.inpe.br/mtc-m18@80/2009/07.16.16.36.42
%T Preliminary results with neural network for data assimilation to the space weather
%D 2009
%8 July 28 ¨C August 1, 2008
%A Velho, Haroldo de Campos,
%A Härter, Fabrício P.,
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation National Institute of Meteorology (INMet)
%@electronicmailaddress haroldo@lac.inpe.br
%@electronicmailaddress fabricio.harter@inmet.gov.br
%E Scientific,
%E Sawant, Hanumant Shankar,
%E Rao, A. Pramesh,
%E Gopalswamy, Natchimuthukonar,
%E Hurford, Gordon J.,
%E Ananthakrishnan, Subramaniam,
%E Executive,
%E Fernandes, Francisco Carlos Rocha,
%E Moraes, Lu¨ªs Cesar Pereira de,
%B Brazilian Decimetric Array Workshop.
%C INPE
%P 161-168
%S Proceedings
%I INPE
%J São José dos Campos
%K NEURAL, NETWORK, ASSIMILATION, SPACE, WEATHER.
%X Data assimilation is an essential step for improving space weather operational forecasting by means of an appropriated combination between observational data and data from a mathematical model. In the present work data assimilation methods based on Kalman filter and artificial neural networks are applied to a three-wave model of auroral radio emissions. A novel data assimilation method is presented, whereby a multilayer perceptron neural network is trained to emulate a Kalman filter for data assimilation by using cross validation. The results obtained render support for the use of neural networks as an assimilation technique for space weather prediction.
%@language en
%3 BDA_proc25_Haroldo.pdf