Neural Network Algorithms for Ozone Profile Retrieval from ESA-Envisat SCIAMACHY and NASA-Aura OMI Satellite Data

Author

Sellitto, A. Pasquale ; Del Frate, B. Fabio ; Solimini, C. Domenico ; Retscher, D. Christian ; Bojkov, E. Bojan ; Bhartia, F. Pawan K

Author_Institution

Earth Obs. Lab., Tor Vergata Univ., Rome

Volume

3

fYear

2008

fDate

7-11 July 2008

Abstract

In this paper we report on the design of Neural Networks algorithms to retrieve height resolved ozone information from Envisat SCIAMACHY and Aura OMI Level 1 data. We defined as input-output pairs the matching of (a) SCIAMACHY UV/VIS reflectances with ozonesondes concentrations, and(b) OMI UV/VIS reflectances with MLS concentrations. Design issues, as input vector dimensionality reduction, vertical resolution problems and topology selection are here analyzed. The inversion results are presented and discussed, with a special emphasis to retrievals at tropospheric height levels.

Keywords

atmospheric chemistry; atmospheric composition; atmospheric measuring apparatus; geophysics computing; neural nets; oxygen; ozone; remote sensing; troposphere; Aura mission; ESA; Envisat; European Space Agency; MLS concentration; NASA; O₃; OMI satellite data; SCIAMACHY instrument; SCanning Imaging Absorption spectroMeter for Atmospheric CHartographY; UV relfectance; VIS reflectance; imaging spectrometer; neural network algorithm; ozone profile retrieval; ozonesonde concentration; tropospheric height level; Atmospheric measurements; Earth; Information retrieval; Instruments; Neural networks; Pollution measurement; Remote monitoring; Satellites; Spatial resolution; Terrestrial atmosphere; Atmospheric profiling; Neural networks; UV/VIS satellite data analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International

Conference_Location

Boston, MA

Print_ISBN

978-1-4244-2807-6

Electronic_ISBN

978-1-4244-2808-3

Type

conf

DOI

10.1109/IGARSS.2008.4779310

Filename

4779310