Title: Atmospheric temperature retrieval using a Radial Basis Function Neural Network

Authors: E.H. Shiguemori, J.D.S. Da Silva, H.F. De Campos Velho, J.C. Carvalho

Addresses: Laboratorio Associado de Computacao e Matematica Aplicada – LAC, Instituto Nacional de Pesquisas Espaciais – INPE, Sao Jose dos Campos, SP, Brazil; Instituto de Estudos Avancados – IEAv, Comando-Geral de Tecnologia Aeroespacial – CTA, Sao Jose dos Campos, SP, Brazil. ' Laboratorio Associado de Computacao e Matematica Aplicada – LAC, Instituto Nacional de Pesquisas Espaciais – INPE, Sao Jose dos Campos, SP, Brazil. ' Laboratorio Associado de Computacao e Matematica Aplicada – LAC, Instituto Nacional de Pesquisas Espaciais – INPE, Sao Jose dos Campos, SP, Brazil. ' Superintendencia de Administracao da Rede Hidrometeorologica – SAR, Agencia Nacional de Aguas – ANA, Brasilia, DF, Brazil

Abstract: Vertical temperature profiles are obtained from measured satellite radiance data by using a Radial Basis Function Neural Network (RBF-NN). The RBF-NN is trained with data provided by the direct model, characterised by the Radiative Transfer Equation. The results are compared with regularisation-based inverse solutions. The approach is tested using satellite radiances, and the inversion temperature profile is compared with radiosonde temperature measurements. Analysis reveals that the generated profiles are closely approximate to previous results, showing the methodology adequacy. ANNs are useful because of the parallelism and implementation simplicity, turn hardware implementation possible, that may imply in on-board and real-time systems.

Keywords: atmospheric temperature; inverse problems; radial basis function; neural networks; RBF-NN; temperature retrieval; vertical temperature profiles; satellite radiance data; radiative transfer equation; ANNs.

DOI: 10.1504/IJICT.2008.019104

International Journal of Information and Communication Technology, 2008 Vol.1 No.2, pp.224 - 239

Published online: 28 Jun 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article