Application of multilayer perceptron to high-resolution infrared measurement retrieval / Gribanov K.G., Toptygin A.Yu., Zakharov V.I. // Proceedings of SPIE - The International Society for Optical Engineering. - 2006. - V. 6580, l. .

ISSN:
0277786X
Type:
Conference Paper
Abstract:
Multilayer perceptron (MLP) as universal approximates may be used for fast retrieval of atmospheric parameters such as vertical profiles of temperature, humidity and concentration of absorbing gases from high-resolution infrared spectra measured by satellite sensors. On the one hand, the number of spectral channels even necessary for retrieval of particular atmospheric parameter is very high, so practical use of MLP needs for effective compression of spectral data with tolerable loss of accuracy. On the other hand, algorithm of error back propagation becomes more effective if the input data vector contains uncorrelated values with zero means, their covariance are approximately equal, and information content of training set is maximized. The modified method of principal components (or empirical orthogonal functions expansion) satisfies to all above requirements. The MLP may be constructed using relevant truncated vectors of principal components as input and output data. Such MLP has fewer dimensions (the number of input, output and hidden neurons) and requires less time for training than MLP using the high-resolution spectrum as input vector and set of vertical profiles of atmospheric parameters as output vector. The developed technique was applied to AIRS observations to retrieve temperature, humidity and methane content. The empirical orthogonal functions were obtained as eigenvectors of matrix G = Se-1/2SRS e-1/2, where SR is sample covariance matrix built on real AIRS measurements over given region, and Se is error covariance matrix characterizing the sensor. The set of measured and model profiles as well as surface temperature and pressure were used for construction of empirical orthogonal functions to represent output data of MLP as truncated expansion. Error profiles and examples of temperature and methane maps are presented.
Author keywords:
Remote sensing
Index keywords:
Atmospheric humidity; Atmospheric structure; Atmospheric temperature; Data compression; Infrared spectroscopy; Remote sensing; Satellites; Atmospheric parameters; Data vectors; Multilayer perceptron (
DOI:
10.1117/12.724933
Смотреть в Scopus:
https://www.scopus.com/inward/record.uri?eid=2-s2.0-33846847607&doi=10.1117%2f12.724933&partnerID=40&md5=1ec1bab283e3eb37575f49eb08f6f375
Соавторы в МНС:
Другие поля
Поле Значение
Art. No. 65800R
Link https://www.scopus.com/inward/record.uri?eid=2-s2.0-33846847607&doi=10.1117%2f12.724933&partnerID=40&md5=1ec1bab283e3eb37575f49eb08f6f375
Affiliations Global Ecology and Remote Sensing Lab., Physics Department, Ural State University, 51, Lenin ave., 620083, Yekaterinburg, Russian Federation
Author Keywords Remote sensing
References Pagano, T.S., Aumann, H.H., Hagan, D., Overoye, K., Prelaunch and In-Flight Radiometer Calibration of the Atmospheric Infrared Sounder (AIRS) (2003) IEEE Transactions on Geoscience and Remote Sensing, 41 (2), pp. 343-351; Beer, R., Glavich, T.A., Rider, T.M., Tropospheric emission spectrometer for Earth Observing System's Aura satellite (2001) Applied Optics, 40 (15), p. 2356; Javelle, P., IASI instrument overview (1994) Proc. Fifth Workshop on ASSFTS, pp. 1-20. , Nov. 30th-Dec.2nd; Hamazaki, T., Kaneko, Y., Kuze, A., Carbon dioxide monitoring from the GOSAT satellite (2004) Proceedings of XXth ISPRS congress, , July 12-23, Istanbul, Turkey; Uspensky, A.B., Romanov, S.V., Trotsenko, A.N., Application of principal component method for the analysis of high-resolution infrared spectra measured from satellites (2003) Issledovanie Zemli iz Kosmosa, (3), pp. 26-33. , in Russian; Churnside, J.H., Stermitz, T.A., Shroeder, J.A., Temperature profiling with neural network inversion of microwave radiometer data (1994) J. Atmos. Oceanic Technol, 11 (1), pp. 105-109; Hadji-Lazaro, J., Clerbaux, C., Thiria, S., An inversion algorithm using neural networks to retrieve atmospheric CO total columns from high resolution nadir radiances (1999) J. Geophys. Res, 104 (D19), pp. 23841-23854; Gribanov, K.G., Zakharov, V.I., Neural network solution for temperature profile retrieval from infrared spectra with high spectral resolution (2004) Atmospheric Science Letters, 5, pp. 1-11. , doi:10.1016/j.atmoscilet.2003.10.002; Haykin, S., (1998) Neural Networks: A Comprehensive Foundation, , 2nd Edition, Prentice Hall; Rumelhart, D.E., Hinton, G.E., Williams, R.J., Learning internal representations by error propagation (1986) Parallel Distributed Processing: Explorations in the Macrostructure of Cognition, 1, pp. 318-362. , edited by D.E. Rumelhart and J.L. McClelland, pp, MIT Press, Cambridge; Chevallier, F., Chédin, A., Cheruy, F., Morcrette, J.J., TIGR-like atmospheric-profile databases for accurate radiative-flux computation (2000) Quart. J. of the Roy. Met. Soc. Part B, 126 (563), pp. 777-785; Gribanov, K.G., Zakharov, V.I., Tashkun, S.A., Tyuterev, V.G., A new software for radiative transfer calculations and its application to IMG/ADEOS data (2001) JQSRT, 68 (4), pp. 435-451; ftp://ftp.cdc.noaa.gov/Datasets/ncep.reanalysis.dailyavgs/pressure/air. 2005.nc; Toptygin, A.Y., Gribanov, K.G., Imasu, R., Bleuten, W., Zakharov, V.I., Seasonal methane content in atmosphere of the permafrost boundary zone in Western Siberia determined from IMG/ADEOS and AIRS/AQUA data (2005) SPIE Proc, 5655, pp. 508-514
Correspondence Address Gribanov, K.G.; Global Ecology and Remote Sensing Lab., Physics Department, Ural State University, 51, Lenin ave., 620083, Yekaterinburg, Russian Federation; email: kgribanov@remotesensing.ru
Sponsors Optical Society of America;SPIE Russia Chapter;Russian Foundation for Basic Research;Bruker LTD., Russia
Conference name 15th Symposium on High-Resolution Molecular Spectroscopy
Conference date 18 July 2006 through 21 July 2006
Conference location Nizhny Novgorod
Conference code 69133
ISBN 0819467022; 9780819467027
CODEN PSISD
Language of Original Document English
Abbreviated Source Title Proc SPIE Int Soc Opt Eng
Source Scopus