%0 Conference Proceedings
%4 dpi.inpe.br/plutao/2012/11.28.16.47.53
%2 dpi.inpe.br/plutao/2012/11.28.16.47.54
%F lattes: 2720072834057575 2 SambattiAnLuCaShCa:2012:AuCoNe
%T Automatic configuration for neural network applied to atmospheric temperature profile identification
%D 2012
%A Sambatti, Sabrina Bergoch Monteiro,
%A Anochi, Juliana Aparecida,
%A Luz, Eduardo Fávero Pacheco da,
%A Carvalho, Adenilson R.,
%A Shiguemori, Elcio Hideiti,
%A Campos Velho, Haroldo Fraga de,
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@affiliation SERPRO
%@affiliation Instituto de Estudos Avançado (IEAv)
%@affiliation Instituto Nacional de Pesquisas Espaciais (INPE)
%@electronicmailaddress sabrinabms@gmail.com
%@electronicmailaddress juliana.anochi@lac.inpe.br
%@electronicmailaddress
%@electronicmailaddress
%@electronicmailaddress
%@electronicmailaddress haroldo@lac.inpe.br
%B International Conference on Engineering Optimization (EngOpt).
%C Rio de Janeiro - RJ
%8 2012
%S Proceedings
%K Atmospheric temperature profile, artificial neural network, optimized topology, inverse problem.
%X Multi-particle collision algorithm (MPCA) is applied to design an optimum architecture for a supervised ANN. The MPCA optimization algorithm emulates a collision process of multiple particles inspired in processes of a neutron traveling in a nuclear reactor. The procedure to carry out the automatic configuration for multi-layer perceptron (MLP) neural network is applied to identify the vertical temperature profiles are obtained from measured satellite radiance data. The MLP-NN is trained with data provided by the direct model characterized by the Radiative Transfer Equation (RTE). The MLP-NN results are compared to the ones computed using regularized inverse solutions. In addition to synthetic data (corrupted by noise), real radiation data from the HIRS/2 (High Resolution Infrared Radiation Sounder) is used as input for the MLP-NN to generate temperature profiles that are compared with the temperature profiles measured by a radiosonde. The comparison between the results obtined with automatic process and previous configuration chosen by an expert is evaluated.
%@language en
%3 sambatti_automatic.pdf